[{"data":1,"prerenderedAt":803},["ShallowReactive",2],{"/en-us/blog/mastering-gitlab-admin-tasks-with-gitlab-duo-chat":3,"navigation-en-us":41,"banner-en-us":451,"footer-en-us":461,"blog-post-authors-en-us-David O'Regan":702,"blog-related-posts-en-us-mastering-gitlab-admin-tasks-with-gitlab-duo-chat":717,"assessment-promotions-en-us":756,"next-steps-en-us":793},{"id":4,"title":5,"authorSlugs":6,"body":8,"categorySlug":9,"config":10,"content":14,"description":8,"extension":28,"isFeatured":12,"meta":29,"navigation":12,"path":30,"publishedDate":20,"seo":31,"stem":36,"tagSlugs":37,"__hash__":40},"blogPosts/en-us/blog/mastering-gitlab-admin-tasks-with-gitlab-duo-chat.yml","Mastering Gitlab Admin Tasks With Gitlab Duo Chat",[7],"david-oregan",null,"ai-ml",{"slug":11,"featured":12,"template":13},"mastering-gitlab-admin-tasks-with-gitlab-duo-chat",true,"BlogPost",{"title":15,"description":16,"authors":17,"heroImage":19,"date":20,"body":21,"category":9,"tags":22},"Mastering GitLab admin tasks with GitLab Duo Chat","Learn how to use Chat to streamline administrative tasks on self-managed instances, improving efficiency and problem-solving capabilities.",[18],"David O'Regan","https://res.cloudinary.com/about-gitlab-com/image/upload/v1749666405/Blog/Hero%20Images/GitLab_Duo_Blog_Hero_1800x945_r2_B__1_.png","2024-08-09","As a GitLab administrator managing a self-hosted instance, you often face complex challenges that require innovative solutions. Enter [GitLab Duo Chat](https://about.gitlab.com/gitlab-duo-agent-platform/) – your AI-powered assistant that can significantly streamline your administrative tasks. In this article, we'll explore how you can leverage GitLab Duo Chat to solve intricate problems efficiently, using a real-world example of updating group memberships across multiple groups.\n\n## The power of GitLab Duo Chat for admins\n\nGitLab Duo Chat is more than just conversational AI; it's a powerful tool that can assist with complex administrative tasks. By providing context-aware suggestions and code snippets, Chat can help you navigate through GitLab's extensive feature set and underlying architecture.\n\n### Case study: Updating group memberships\n\nLet's dive into a scenario where an admin needs to add an administrator user to multiple [groups](https://docs.gitlab.com/ee/user/group/) – in this case, 50,000 groups. This task, while conceptually simple, can be daunting due to its scale.\n\n\u003C!-- blank line -->\n\u003Cfigure class=\"video_container\">\n  \u003Ciframe src=\"https://www.youtube.com/embed/dBd957MK_DE?si=JYTzdRjVQHyB6rpl\" frameborder=\"0\" allowfullscreen=\"true\"> \u003C/iframe>\n\u003C/figure>\n\u003C!-- blank line -->\n\n## Step-by-step problem-solving with GitLab Duo Chat\n\n* **Initial approach:** Our first instinct might be to use GitLab's API, but with 50,000 groups, this could put significant strain on the system.\n* **Pivoting to the Rails console:** Instead, we can use the Rails console for a more efficient solution. Here's where Chat comes in handy.\n* **Crafting the solution:** Let's walk through the process of creating a Ruby script to accomplish our task:\n\n```python\ndef add_admin_to_groups(parent_group, admin_user)\n     unless parent_group.members.exists?(user_id: admin_user.id)\n       parent_group.add_owner(admin_user)\n       puts \"Added #{admin_user.name} to #{parent_group.name}\"\n     end\n\n    parent_group.descendants.each do |subgroup|\n      add_admin_to_groups(subgroup, admin_user)\n    end\n  end\n\n# Usage\n\nadmin_user = User.find_by(username: 'mr_admin')\nparent_group = Group.find_by(path: 'top_group')\nadd_admin_to_groups(parent_group, admin_user)\n```\n\n* **Iterative refinement:** Through conversation with Chat, we refined this script, addressing issues like method availability and parameter requirements.\n\n### Key takeaways\n\n#### Non-deterministic responses\n\nGitLab Duo Chat may provide different answers to the same question, encouraging exploration of multiple solutions. As an example:\n\nAn admin asks, ***How can I improve CI/CD pipeline performance?***\n\nChat's first response could be:\n***Consider using GitLab CI/CD caching to speed up subsequent pipeline runs. Here's an example .gitlab-ci.yml snippet:***\n\n```text\ncache:\n  key: ${CI_COMMIT_REF_SLUG}\n  paths:\n    - node_modules/    \n ```\n\n***This caches the `node_modules` directory, reducing build times for Node.js projects.***\n\nWhen asked again, Chat's second response could be: ***To improve CI/CD performance, try parallelizing your jobs. Here's an example:***\n```yaml\ntest:\n  parallel: 3\n```\n***This runs your test job across three parallel runners, potentially reducing overall pipeline duration.***\n\n### Error interpretation and debugging\n\nChat can help interpret error messages and suggest fixes. As an example, an admin encounters an error: \"fatal: reference is not a tree: 8a7d460\". They could ask Chat: ***I'm seeing this Git error. What does it mean and how can I fix it?***\n\nChat could respond with:\n\n***This error typically occurs when Git can't find a specific commit. It could be due to a corrupted repository or incomplete fetch. Try these steps:***\n* ***Run `git fsck` to check for corruption.***\n* ***If that doesn't work, try git fetch --all --prune to update all remotes.***\n* ***If the issue persists, you might need to re-clone the repository.***\n\n***Always back up your repository before attempting these fixes.***\n\n### Code optimization and refactoring\n\nChat can assist in optimizing and refactoring code for better performance.\n\nAn example: An admin wants to optimize a Gitaly configuration for a large instance. They could ask Chat: ***How can I optimize Gitaly for an instance with 10,000+ repositories?***\n\nChat could respond with: ***For a large instance, consider this optimized Gitaly configuration:***\n```text\n[concurrency]\nrpc_concurrency = 100\n\n[rate_limiting]\nrpc_rate_limit = 100\n\n[cgroups]\nmountpoint = '/sys/fs/cgroup'\nhierarchy_root = 'gitaly'\nmemory_bytes = 30000000000  # Adjust based on available memory\ncpu_shares = 1024\n```\n***This configuration increases concurrency, implements rate limiting to prevent overload, and uses cgroups (control groups) to manage resource allocation. Adjust values based on your specific hardware and needs.***\n\n## Best practices for using GitLab Duo Chat in admin tasks\n\n### Formulate queries clearly and provide context\n\nWhen using Chat, the quality of the response largely depends on the quality of your query. Clear, detailed questions that provide relevant context will yield more accurate and helpful answers.\n\nPoor query: ***Why is GitLab slow?***\n\nThis query lacks specifics and context, making it difficult for Chat to provide a targeted response. \n\nA better query would be: ***Our GitLab instance with 5,000 users and 3,000 projects is experiencing slow response times, especially during peak hours (9-11 AM EST). CPU usage on the application servers spikes to 90%. How can we diagnose and address this?***\n\nThis improved query provides crucial details:\n\n* scale of the instance (5,000 users, 3,000 projects)\n* nature of the problem (slow response times)\n* timing of the issue (peak hours, 9-11 AM EST)\n* observed symptoms (90% CPU spike)\n\nWith this information, Chat can provide more targeted advice.\n\nAn even better query would be: ***We're running GitLab 15.8.3 on a 3-node cluster (8 vCPUs, 32GB RAM each) with a separate PostgreSQL 13 database and Redis 6.2 instance. Our instance hosts 5,000 users and 3,000 projects. We're experiencing slow response times (average 5s, up from our usual 1s) during peak hours (9-11 AM EST), primarily affecting merge request creation and pipeline initiation. CPU usage on the application servers spikes to 90%, while database CPU remains under 60%. Gitaly CPU usage is around 70%. We've already increased Puma workers to 8 per node. What additional diagnostics should we run and what potential solutions should we consider?***\n\nThis query provides an extensive context, including:\n* GitLab version and infrastructure details\nspecific performance metrics (response time increase)\n* affected operations (merge requests, pipelines)\n* resource usage across different components\n* steps already taken to address the issue\n\nBy providing this level of detail, you enable Chat to:\n* understand the full scope of your environment\n* identify potential bottlenecks more accurately\n* suggest relevant diagnostic steps\n* propose solutions tailored to your specific setup\n\nAvoid recommending steps you've already taken.\n\nRemember, while GitLab Duo Chat is powerful, it's not omniscient. The more relevant information you provide, the better it can assist you. By following these guidelines, you'll get the most out of your interactions with Chat, leading to more effective problem-solving and administration of your GitLab instance.\n\n### Use GitLab Duo Chat's suggestions as a starting point and refine incrementally\n\nChat is an excellent tool for getting started with complex tasks, but it's most effective when used as part of an iterative process. Begin with a broad question, then use Chat's responses to guide your follow-up questions, gradually refining your understanding and solution.\n\n#### Initial query\n\nAdmin: ***How can I set up Geo replication for disaster recovery?***\n\nChat might respond with a basic setup guide, covering:\n- prerequisites for Geo setup\n- steps to configure the primary node\n- process for adding a secondary node\n- initial replication process\n\nThis provides a foundation, but complex setups like Geo often require more nuanced understanding. Here's how you might refine your queries:\n\n**- Follow-up Query 1**\n\nAdmin: ***How do I handle custom data in Geo replication?***\nThis question addresses a specific concern not covered in the initial setup. \n\n**- Follow-up Query 2**\n\nAdmin: ***What's the best way to test failover without disrupting production?***\n\nThis query focuses on a critical operational concern. \n\n**- Follow-up Query 3**\n\nAdmin: ***Can you help me create a runbook for Geo failover?***\n\nThis final query aims to consolidate the gathered information into a practical guide. The benefits of this incremental approach:\n\n1. By breaking down the complex topic of Geo replication into smaller, focused queries, you gain a more thorough understanding of the subject.\n2. Each follow-up question allows you to address specific concerns relevant to your environment, resulting in a more customized solution.\n3. The progression from setup to testing to creating a runbook ensures that you're not just understanding the theory, but also preparing for real-world implementation.\n4. The step-by-step process of refining your queries helps in better retention of the information, as you're actively engaging with the content.\n5. Follow-up questions often reveal aspects of the task you might not have initially considered, leading to a more robust final solution.\n\n#### Best practices for incremental refinement\n\n- Start with broad questions to establish a foundation.\n- Use Chat's responses to identify areas that need more clarification or detail.\n- Ask about specific scenarios or edge cases relevant to your environment.\n- Seek practical advice on implementation, testing, and maintenance.\n- Use your growing understanding to formulate increasingly specific and complex queries.\n- Periodically summarize your understanding and ask Chat to validate or correct it.\n\nRemember, while GitLab Duo Chat is a powerful tool, it's most effective when combined with your own critical thinking and domain knowledge. Use it to guide your learning and decision-making process, but always validate important information and test solutions in a safe environment before applying them to production systems.\n\n### Potential applications for self-managed GitLab instances\n\n#### User management at scale\n\nAdmin: ***We need to onboard 1,000 new users from an acquired company. The data is in a CSV file. How can we automate this process? I am an Admin, can I use a Python script for this?***\n\nChat: ***You can use GitLab's API for bulk user creation. Here's a Python script to get you started:***\n\n```python\nimport requests\nimport csv\n\ndef create_user(username, email, name, password):\n    url = 'https://gitlab.example.com/api/v4/users'\n    headers = {'PRIVATE-TOKEN': 'your_access_token'}\n    data = {\n        'username': username,\n        'email': email,\n        'name': name,\n        'password': password,\n        'skip_confirmation': True\n    }\n    response = requests.post(url, headers=headers, data=data)\n    return response.status_code == 201\n\nwith open('new_users.csv', 'r') as f:\n    reader = csv.reader(f)\n    for row in reader:\n        username, email, name, password = row\n        if create_user(username, email, name, password):\n            print(f\"Created user: {username}\")\n        else:\n            print(f\"Failed to create user: {username}\")\n\n```\n***This script reads user data from a CSV file and creates users via the GitLab API. Remember to handle errors and rate limiting for large batches.***\n\n#### Project and group administration\n\nAdmin: ***We need to implement a standardized project structure across our organization. How can we automate this? Assume I am an admin. Write me a script to do this via the API.***\n\nChat: ***You can use GitLab's API to create a project template and then apply it to new projects. Here's a bash script to create a new project with a standard structure:***\n\n```bash\n#!/bin/bash\n\nTOKEN=\"your_access_token\"\nGROUP_ID=\"your_group_id\"\n\ncreate_project() {\n  curl --header \"PRIVATE-TOKEN: $TOKEN\" \\\n  --data \"name=$1&namespace_id=$GROUP_ID\" \\\n  \"https://gitlab.example.com/api/v4/projects\"\n}\n\nadd_file() {\n  curl --request POST --header \"PRIVATE-TOKEN: $TOKEN\" \\\n  --form \"branch=main\" \\\n  --form \"content=$2\" \\\n  --form \"commit_message=Add $1\" \\\n  \"https://gitlab.example.com/api/v4/projects/$3/repository/files/$1\"\n}\n\nPROJECT_ID=$(create_project \"New-Standardized-Project\" | jq '.id')\n\nadd_file \"README.md\" \"# Welcome to our standardized project\" $PROJECT_ID\nadd_file \".gitlab-ci.yml\" \"stages:\\n  - build\\n  - test\\n  - deploy\" $PROJECT_ID\nadd_file \"CONTRIBUTING.md\" \"## How to contribute to this project\" $PROJECT_ID\n\necho \"Project created with ID: $PROJECT_ID\"\n```\n\n***This script creates a new project with a README, a basic CI/CD configuration, and a CONTRIBUTING guide. You can expand this to include more files or even clone a template repository.***\n\n#### Performance optimization\n\nAdmin: ***Our merge request creation process is slow. How can we diagnose and improve this? Assume I am an admin.***\n\nChat: ***As an instance admin, there are a few potential areas you can investigate to diagnose and improve the merge request creation process:\nDatabase Performance: The provided quotes show some example SQL queries related to merge request metrics. Slow database queries can significantly impact merge request creation performance. You should review the database performance, indexes, and query plans for any queries involved in the merge request creation process.***\n\n- ***Background jobs: Merge request creation may involve background jobs (e.g., for data processing, notifications, etc.). If these jobs are backed up or running slowly, it can impact the overall merge request creation time. Check the background job queues and workers.***\n- ***Code optimization: Analyze the code responsible for merge request creation to identify any potential bottlenecks or inefficiencies. This could include things like unnecessary database queries, inefficient algorithms, or lack of caching.***\n- ***Resource utilization: Monitor the resource utilization (CPU, memory, disk I/O) of the GitLab application servers during merge request creation. High resource utilization can lead to performance degradation.***\n- ***Network performance: If your GitLab instance is distributed across multiple nodes or servers, network performance between these components can impact merge request creation times. Check for any network bottlenecks or latency issues.***\n- ***Caching: Ensure that appropriate caching mechanisms are in place and functioning correctly. Inefficient or incorrect caching can lead to unnecessary overhead during merge request creation.***\n- ***Load testing: Perform load testing to simulate real-world scenarios and identify any performance bottlenecks or scalability issues that may arise under high load.***\n- ***Logging and monitoring: Enable detailed logging and monitoring for the merge request creation process. This can help identify specific areas of slowness or bottlenecks.***\n\n***To effectively diagnose and improve the merge request creation process, you'll likely need to combine multiple techniques, such as profiling, code analysis, database optimization, and load testing. Additionally, consulting the GitLab documentation and community resources can provide valuable insights and best practices specific to your GitLab version and configuration.***\n\n#### Troubleshooting complex issues\n\nAdmin: ***We're experiencing intermittent 502 errors on our GitLab instance. How can we troubleshoot this? I am an instance admin, how can I check the logs to find answers?***\n\nChat: ***To troubleshoot intermittent 502 errors on your GitLab instance as an admin, you can follow these steps:***\n\n***1. Check the main GitLab logs while reproducing the issue by running:***\n\n```shell\nsudo gitlab-ctl tail | tee /tmp/\u003Ccase-ID-and-keywords>.log\n```\n\n***2. Press Ctrl+C to stop tailing the logs.***\n\n***3. Run GitLabSOS to gather broader diagnostics about your instance:***\n\n```shell\nsudo /opt/gitlab/embedded/bin/gitlab-sos\n```\n\n***4. Use the fast-stats tool to analyze performance statistics from the logs:***\n\n```shell\nsudo /opt/gitlab/embedded/bin/fast-stats /var/log/gitlab/gitlab-rails/production.log\n```\n\n***5.Look for relevant log entries using the correlation ID that is present in most requests.***\n\n***6. Check the Pages logs (gitlab_pages_error.log) for any specific errors related to Pages communication issues with the GitLab API or loopback timeouts if using an AWS Network Load Balancer.***\n\n***7. Ensure your gitlab-secrets.json file is synced across all GitLab Pages instances if using `domain_config_source=auto`.***\n\n***8. If using systemd, configure GitLab Pages to listen on an explicit IP and port to avoid /tmp being cleaned up.***\n\n## Get started with GitLab Duo Chat\n\nGitLab Duo Chat is a powerful ally for administrators of self-managed GitLab instances. By leveraging its capabilities, you can tackle complex tasks more efficiently, learn new techniques, and ultimately become a more effective GitLab administrator.\n\nWe encourage you to experiment with Chat in your administrative workflows. Remember to use it responsibly and always verify the solutions it provides.\n\n> [Try GitLab Duo for free](https://about.gitlab.com/sales/).\n\n### Resources\n- [GitLab Duo documentation](https://docs.gitlab.com/ee/user/gitlab_duo/)\n- [GitLab Rails Console Cheat Sheet](https://docs.gitlab.com/ee/administration/operations/rails_console.html)\n- [GitLab API documentation](https://docs.gitlab.com/ee/api/)\n- [10 best practices for using AI-powered GitLab Duo Chat](https://about.gitlab.com/blog/10-best-practices-for-using-ai-powered-gitlab-duo-chat/)\n- [GitLab Duo Chat 101: Get more done on GitLab with our AI assistant](https://about.gitlab.com/blog/gitlab-duo-chat-101-get-more-done-on-gitlab-with-our-ai-assistant/)\n",[23,24,25,26,27],"AI/ML","tutorial","DevSecOps platform","features","product","yml",{},"/en-us/blog/mastering-gitlab-admin-tasks-with-gitlab-duo-chat",{"title":15,"description":16,"ogTitle":15,"ogDescription":16,"noIndex":32,"ogImage":19,"ogUrl":33,"ogSiteName":34,"ogType":35,"canonicalUrls":33},false,"https://about.gitlab.com/blog/mastering-gitlab-admin-tasks-with-gitlab-duo-chat","https://about.gitlab.com","article","en-us/blog/mastering-gitlab-admin-tasks-with-gitlab-duo-chat",[38,24,39,26,27],"aiml","devsecops-platform","aICMH_VWFMSxUrZ8QKOI3JoeYIe1ltS9VujySNaqaek",{"data":42},{"logo":43,"freeTrial":48,"sales":53,"login":58,"items":63,"search":371,"minimal":402,"duo":421,"switchNav":430,"pricingDeployment":441},{"config":44},{"href":45,"dataGaName":46,"dataGaLocation":47},"/","gitlab logo","header",{"text":49,"config":50},"Get free trial",{"href":51,"dataGaName":52,"dataGaLocation":47},"https://gitlab.com/-/trial_registrations/new?glm_source=about.gitlab.com&glm_content=default-saas-trial/","free trial",{"text":54,"config":55},"Talk to sales",{"href":56,"dataGaName":57,"dataGaLocation":47},"/sales/","sales",{"text":59,"config":60},"Sign in",{"href":61,"dataGaName":62,"dataGaLocation":47},"https://gitlab.com/users/sign_in/","sign in",[64,91,186,191,292,352],{"text":65,"config":66,"cards":68},"Platform",{"dataNavLevelOne":67},"platform",[69,75,83],{"title":65,"description":70,"link":71},"The intelligent orchestration platform for DevSecOps",{"text":72,"config":73},"Explore our Platform",{"href":74,"dataGaName":67,"dataGaLocation":47},"/platform/",{"title":76,"description":77,"link":78},"GitLab Duo Agent Platform","Agentic AI for the entire software lifecycle",{"text":79,"config":80},"Meet GitLab Duo",{"href":81,"dataGaName":82,"dataGaLocation":47},"/gitlab-duo-agent-platform/","gitlab duo agent platform",{"title":84,"description":85,"link":86},"Why GitLab","See the top reasons enterprises choose GitLab",{"text":87,"config":88},"Learn more",{"href":89,"dataGaName":90,"dataGaLocation":47},"/why-gitlab/","why gitlab",{"text":92,"left":12,"config":93,"link":95,"lists":99,"footer":168},"Product",{"dataNavLevelOne":94},"solutions",{"text":96,"config":97},"View all Solutions",{"href":98,"dataGaName":94,"dataGaLocation":47},"/solutions/",[100,124,147],{"title":101,"description":102,"link":103,"items":108},"Automation","CI/CD and automation to accelerate deployment",{"config":104},{"icon":105,"href":106,"dataGaName":107,"dataGaLocation":47},"AutomatedCodeAlt","/solutions/delivery-automation/","automated software delivery",[109,113,116,120],{"text":110,"config":111},"CI/CD",{"href":112,"dataGaLocation":47,"dataGaName":110},"/solutions/continuous-integration/",{"text":76,"config":114},{"href":81,"dataGaLocation":47,"dataGaName":115},"gitlab duo agent platform - product menu",{"text":117,"config":118},"Source Code Management",{"href":119,"dataGaLocation":47,"dataGaName":117},"/solutions/source-code-management/",{"text":121,"config":122},"Automated Software Delivery",{"href":106,"dataGaLocation":47,"dataGaName":123},"Automated software delivery",{"title":125,"description":126,"link":127,"items":132},"Security","Deliver code faster without compromising security",{"config":128},{"href":129,"dataGaName":130,"dataGaLocation":47,"icon":131},"/solutions/application-security-testing/","security and compliance","ShieldCheckLight",[133,137,142],{"text":134,"config":135},"Application Security Testing",{"href":129,"dataGaName":136,"dataGaLocation":47},"Application security testing",{"text":138,"config":139},"Software Supply Chain Security",{"href":140,"dataGaLocation":47,"dataGaName":141},"/solutions/supply-chain/","Software supply chain security",{"text":143,"config":144},"Software Compliance",{"href":145,"dataGaName":146,"dataGaLocation":47},"/solutions/software-compliance/","software compliance",{"title":148,"link":149,"items":154},"Measurement",{"config":150},{"icon":151,"href":152,"dataGaName":153,"dataGaLocation":47},"DigitalTransformation","/solutions/visibility-measurement/","visibility and measurement",[155,159,163],{"text":156,"config":157},"Visibility & Measurement",{"href":152,"dataGaLocation":47,"dataGaName":158},"Visibility and Measurement",{"text":160,"config":161},"Value Stream Management",{"href":162,"dataGaLocation":47,"dataGaName":160},"/solutions/value-stream-management/",{"text":164,"config":165},"Analytics & Insights",{"href":166,"dataGaLocation":47,"dataGaName":167},"/solutions/analytics-and-insights/","Analytics and insights",{"title":169,"items":170},"GitLab for",[171,176,181],{"text":172,"config":173},"Enterprise",{"href":174,"dataGaLocation":47,"dataGaName":175},"/enterprise/","enterprise",{"text":177,"config":178},"Small Business",{"href":179,"dataGaLocation":47,"dataGaName":180},"/small-business/","small business",{"text":182,"config":183},"Public Sector",{"href":184,"dataGaLocation":47,"dataGaName":185},"/solutions/public-sector/","public sector",{"text":187,"config":188},"Pricing",{"href":189,"dataGaName":190,"dataGaLocation":47,"dataNavLevelOne":190},"/pricing/","pricing",{"text":192,"config":193,"link":195,"lists":199,"feature":279},"Resources",{"dataNavLevelOne":194},"resources",{"text":196,"config":197},"View all resources",{"href":198,"dataGaName":194,"dataGaLocation":47},"/resources/",[200,233,251],{"title":201,"items":202},"Getting started",[203,208,213,218,223,228],{"text":204,"config":205},"Install",{"href":206,"dataGaName":207,"dataGaLocation":47},"/install/","install",{"text":209,"config":210},"Quick start guides",{"href":211,"dataGaName":212,"dataGaLocation":47},"/get-started/","quick setup checklists",{"text":214,"config":215},"Learn",{"href":216,"dataGaLocation":47,"dataGaName":217},"https://university.gitlab.com/","learn",{"text":219,"config":220},"Product documentation",{"href":221,"dataGaName":222,"dataGaLocation":47},"https://docs.gitlab.com/","product documentation",{"text":224,"config":225},"Best practice videos",{"href":226,"dataGaName":227,"dataGaLocation":47},"/getting-started-videos/","best practice videos",{"text":229,"config":230},"Integrations",{"href":231,"dataGaName":232,"dataGaLocation":47},"/integrations/","integrations",{"title":234,"items":235},"Discover",[236,241,246],{"text":237,"config":238},"Customer success stories",{"href":239,"dataGaName":240,"dataGaLocation":47},"/customers/","customer success stories",{"text":242,"config":243},"Blog",{"href":244,"dataGaName":245,"dataGaLocation":47},"/blog/","blog",{"text":247,"config":248},"Remote",{"href":249,"dataGaName":250,"dataGaLocation":47},"https://handbook.gitlab.com/handbook/company/culture/all-remote/","remote",{"title":252,"items":253},"Connect",[254,259,264,269,274],{"text":255,"config":256},"GitLab Services",{"href":257,"dataGaName":258,"dataGaLocation":47},"/services/","services",{"text":260,"config":261},"Community",{"href":262,"dataGaName":263,"dataGaLocation":47},"/community/","community",{"text":265,"config":266},"Forum",{"href":267,"dataGaName":268,"dataGaLocation":47},"https://forum.gitlab.com/","forum",{"text":270,"config":271},"Events",{"href":272,"dataGaName":273,"dataGaLocation":47},"/events/","events",{"text":275,"config":276},"Partners",{"href":277,"dataGaName":278,"dataGaLocation":47},"/partners/","partners",{"backgroundColor":280,"textColor":281,"text":282,"image":283,"link":287},"#2f2a6b","#fff","Insights for the future of software development",{"altText":284,"config":285},"the source promo card",{"src":286},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1758208064/dzl0dbift9xdizyelkk4.svg",{"text":288,"config":289},"Read the latest",{"href":290,"dataGaName":291,"dataGaLocation":47},"/the-source/","the source",{"text":293,"config":294,"lists":296},"Company",{"dataNavLevelOne":295},"company",[297],{"items":298},[299,304,310,312,317,322,327,332,337,342,347],{"text":300,"config":301},"About",{"href":302,"dataGaName":303,"dataGaLocation":47},"/company/","about",{"text":305,"config":306,"footerGa":309},"Jobs",{"href":307,"dataGaName":308,"dataGaLocation":47},"/jobs/","jobs",{"dataGaName":308},{"text":270,"config":311},{"href":272,"dataGaName":273,"dataGaLocation":47},{"text":313,"config":314},"Leadership",{"href":315,"dataGaName":316,"dataGaLocation":47},"/company/team/e-group/","leadership",{"text":318,"config":319},"Team",{"href":320,"dataGaName":321,"dataGaLocation":47},"/company/team/","team",{"text":323,"config":324},"Handbook",{"href":325,"dataGaName":326,"dataGaLocation":47},"https://handbook.gitlab.com/","handbook",{"text":328,"config":329},"Investor relations",{"href":330,"dataGaName":331,"dataGaLocation":47},"https://ir.gitlab.com/","investor relations",{"text":333,"config":334},"Trust Center",{"href":335,"dataGaName":336,"dataGaLocation":47},"/security/","trust center",{"text":338,"config":339},"AI Transparency Center",{"href":340,"dataGaName":341,"dataGaLocation":47},"/ai-transparency-center/","ai transparency center",{"text":343,"config":344},"Newsletter",{"href":345,"dataGaName":346,"dataGaLocation":47},"/company/contact/#contact-forms","newsletter",{"text":348,"config":349},"Press",{"href":350,"dataGaName":351,"dataGaLocation":47},"/press/","press",{"text":353,"config":354,"lists":355},"Contact us",{"dataNavLevelOne":295},[356],{"items":357},[358,361,366],{"text":54,"config":359},{"href":56,"dataGaName":360,"dataGaLocation":47},"talk to sales",{"text":362,"config":363},"Support portal",{"href":364,"dataGaName":365,"dataGaLocation":47},"https://support.gitlab.com","support portal",{"text":367,"config":368},"Customer portal",{"href":369,"dataGaName":370,"dataGaLocation":47},"https://customers.gitlab.com/customers/sign_in/","customer portal",{"close":372,"login":373,"suggestions":380},"Close",{"text":374,"link":375},"To search repositories and projects, login to",{"text":376,"config":377},"gitlab.com",{"href":61,"dataGaName":378,"dataGaLocation":379},"search login","search",{"text":381,"default":382},"Suggestions",[383,385,389,391,395,399],{"text":76,"config":384},{"href":81,"dataGaName":76,"dataGaLocation":379},{"text":386,"config":387},"Code Suggestions (AI)",{"href":388,"dataGaName":386,"dataGaLocation":379},"/solutions/code-suggestions/",{"text":110,"config":390},{"href":112,"dataGaName":110,"dataGaLocation":379},{"text":392,"config":393},"GitLab on AWS",{"href":394,"dataGaName":392,"dataGaLocation":379},"/partners/technology-partners/aws/",{"text":396,"config":397},"GitLab on Google Cloud",{"href":398,"dataGaName":396,"dataGaLocation":379},"/partners/technology-partners/google-cloud-platform/",{"text":400,"config":401},"Why GitLab?",{"href":89,"dataGaName":400,"dataGaLocation":379},{"freeTrial":403,"mobileIcon":408,"desktopIcon":413,"secondaryButton":416},{"text":404,"config":405},"Start free trial",{"href":406,"dataGaName":52,"dataGaLocation":407},"https://gitlab.com/-/trials/new/","nav",{"altText":409,"config":410},"Gitlab Icon",{"src":411,"dataGaName":412,"dataGaLocation":407},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1758203874/jypbw1jx72aexsoohd7x.svg","gitlab icon",{"altText":409,"config":414},{"src":415,"dataGaName":412,"dataGaLocation":407},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1758203875/gs4c8p8opsgvflgkswz9.svg",{"text":417,"config":418},"Get Started",{"href":419,"dataGaName":420,"dataGaLocation":407},"https://gitlab.com/-/trial_registrations/new?glm_source=about.gitlab.com/get-started/","get started",{"freeTrial":422,"mobileIcon":426,"desktopIcon":428},{"text":423,"config":424},"Learn more about GitLab Duo",{"href":81,"dataGaName":425,"dataGaLocation":407},"gitlab duo",{"altText":409,"config":427},{"src":411,"dataGaName":412,"dataGaLocation":407},{"altText":409,"config":429},{"src":415,"dataGaName":412,"dataGaLocation":407},{"button":431,"mobileIcon":436,"desktopIcon":438},{"text":432,"config":433},"/switch",{"href":434,"dataGaName":435,"dataGaLocation":407},"#contact","switch",{"altText":409,"config":437},{"src":411,"dataGaName":412,"dataGaLocation":407},{"altText":409,"config":439},{"src":440,"dataGaName":412,"dataGaLocation":407},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1773335277/ohhpiuoxoldryzrnhfrh.png",{"freeTrial":442,"mobileIcon":447,"desktopIcon":449},{"text":443,"config":444},"Back to pricing",{"href":189,"dataGaName":445,"dataGaLocation":407,"icon":446},"back to pricing","GoBack",{"altText":409,"config":448},{"src":411,"dataGaName":412,"dataGaLocation":407},{"altText":409,"config":450},{"src":415,"dataGaName":412,"dataGaLocation":407},{"title":452,"button":453,"config":458},"See how agentic AI transforms software delivery",{"text":454,"config":455},"Watch GitLab Transcend now",{"href":456,"dataGaName":457,"dataGaLocation":47},"/events/transcend/virtual/","transcend event",{"layout":459,"icon":460,"disabled":12},"release","AiStar",{"data":462},{"text":463,"source":464,"edit":470,"contribute":475,"config":480,"items":485,"minimal":691},"Git is a trademark of Software Freedom Conservancy and our use of 'GitLab' is under license",{"text":465,"config":466},"View page source",{"href":467,"dataGaName":468,"dataGaLocation":469},"https://gitlab.com/gitlab-com/marketing/digital-experience/about-gitlab-com/","page source","footer",{"text":471,"config":472},"Edit this page",{"href":473,"dataGaName":474,"dataGaLocation":469},"https://gitlab.com/gitlab-com/marketing/digital-experience/about-gitlab-com/-/blob/main/content/","web ide",{"text":476,"config":477},"Please contribute",{"href":478,"dataGaName":479,"dataGaLocation":469},"https://gitlab.com/gitlab-com/marketing/digital-experience/about-gitlab-com/-/blob/main/CONTRIBUTING.md/","please contribute",{"twitter":481,"facebook":482,"youtube":483,"linkedin":484},"https://twitter.com/gitlab","https://www.facebook.com/gitlab","https://www.youtube.com/channel/UCnMGQ8QHMAnVIsI3xJrihhg","https://www.linkedin.com/company/gitlab-com",[486,533,586,630,657],{"title":187,"links":487,"subMenu":502},[488,492,497],{"text":489,"config":490},"View plans",{"href":189,"dataGaName":491,"dataGaLocation":469},"view plans",{"text":493,"config":494},"Why Premium?",{"href":495,"dataGaName":496,"dataGaLocation":469},"/pricing/premium/","why premium",{"text":498,"config":499},"Why Ultimate?",{"href":500,"dataGaName":501,"dataGaLocation":469},"/pricing/ultimate/","why ultimate",[503],{"title":504,"links":505},"Contact Us",[506,509,511,513,518,523,528],{"text":507,"config":508},"Contact sales",{"href":56,"dataGaName":57,"dataGaLocation":469},{"text":362,"config":510},{"href":364,"dataGaName":365,"dataGaLocation":469},{"text":367,"config":512},{"href":369,"dataGaName":370,"dataGaLocation":469},{"text":514,"config":515},"Status",{"href":516,"dataGaName":517,"dataGaLocation":469},"https://status.gitlab.com/","status",{"text":519,"config":520},"Terms of use",{"href":521,"dataGaName":522,"dataGaLocation":469},"/terms/","terms of use",{"text":524,"config":525},"Privacy statement",{"href":526,"dataGaName":527,"dataGaLocation":469},"/privacy/","privacy statement",{"text":529,"config":530},"Cookie preferences",{"dataGaName":531,"dataGaLocation":469,"id":532,"isOneTrustButton":12},"cookie preferences","ot-sdk-btn",{"title":92,"links":534,"subMenu":542},[535,538],{"text":25,"config":536},{"href":74,"dataGaName":537,"dataGaLocation":469},"devsecops platform",{"text":539,"config":540},"AI-Assisted Development",{"href":81,"dataGaName":541,"dataGaLocation":469},"ai-assisted development",[543],{"title":544,"links":545},"Topics",[546,551,556,561,566,571,576,581],{"text":547,"config":548},"CICD",{"href":549,"dataGaName":550,"dataGaLocation":469},"/topics/ci-cd/","cicd",{"text":552,"config":553},"GitOps",{"href":554,"dataGaName":555,"dataGaLocation":469},"/topics/gitops/","gitops",{"text":557,"config":558},"DevOps",{"href":559,"dataGaName":560,"dataGaLocation":469},"/topics/devops/","devops",{"text":562,"config":563},"Version Control",{"href":564,"dataGaName":565,"dataGaLocation":469},"/topics/version-control/","version control",{"text":567,"config":568},"DevSecOps",{"href":569,"dataGaName":570,"dataGaLocation":469},"/topics/devsecops/","devsecops",{"text":572,"config":573},"Cloud Native",{"href":574,"dataGaName":575,"dataGaLocation":469},"/topics/cloud-native/","cloud native",{"text":577,"config":578},"AI for Coding",{"href":579,"dataGaName":580,"dataGaLocation":469},"/topics/devops/ai-for-coding/","ai for coding",{"text":582,"config":583},"Agentic AI",{"href":584,"dataGaName":585,"dataGaLocation":469},"/topics/agentic-ai/","agentic ai",{"title":587,"links":588},"Solutions",[589,591,593,598,602,605,609,612,614,617,620,625],{"text":134,"config":590},{"href":129,"dataGaName":134,"dataGaLocation":469},{"text":123,"config":592},{"href":106,"dataGaName":107,"dataGaLocation":469},{"text":594,"config":595},"Agile development",{"href":596,"dataGaName":597,"dataGaLocation":469},"/solutions/agile-delivery/","agile delivery",{"text":599,"config":600},"SCM",{"href":119,"dataGaName":601,"dataGaLocation":469},"source code management",{"text":547,"config":603},{"href":112,"dataGaName":604,"dataGaLocation":469},"continuous integration & delivery",{"text":606,"config":607},"Value stream management",{"href":162,"dataGaName":608,"dataGaLocation":469},"value stream management",{"text":552,"config":610},{"href":611,"dataGaName":555,"dataGaLocation":469},"/solutions/gitops/",{"text":172,"config":613},{"href":174,"dataGaName":175,"dataGaLocation":469},{"text":615,"config":616},"Small business",{"href":179,"dataGaName":180,"dataGaLocation":469},{"text":618,"config":619},"Public sector",{"href":184,"dataGaName":185,"dataGaLocation":469},{"text":621,"config":622},"Education",{"href":623,"dataGaName":624,"dataGaLocation":469},"/solutions/education/","education",{"text":626,"config":627},"Financial services",{"href":628,"dataGaName":629,"dataGaLocation":469},"/solutions/finance/","financial services",{"title":192,"links":631},[632,634,636,638,641,643,645,647,649,651,653,655],{"text":204,"config":633},{"href":206,"dataGaName":207,"dataGaLocation":469},{"text":209,"config":635},{"href":211,"dataGaName":212,"dataGaLocation":469},{"text":214,"config":637},{"href":216,"dataGaName":217,"dataGaLocation":469},{"text":219,"config":639},{"href":221,"dataGaName":640,"dataGaLocation":469},"docs",{"text":242,"config":642},{"href":244,"dataGaName":245,"dataGaLocation":469},{"text":237,"config":644},{"href":239,"dataGaName":240,"dataGaLocation":469},{"text":247,"config":646},{"href":249,"dataGaName":250,"dataGaLocation":469},{"text":255,"config":648},{"href":257,"dataGaName":258,"dataGaLocation":469},{"text":260,"config":650},{"href":262,"dataGaName":263,"dataGaLocation":469},{"text":265,"config":652},{"href":267,"dataGaName":268,"dataGaLocation":469},{"text":270,"config":654},{"href":272,"dataGaName":273,"dataGaLocation":469},{"text":275,"config":656},{"href":277,"dataGaName":278,"dataGaLocation":469},{"title":293,"links":658},[659,661,663,665,667,669,671,675,680,682,684,686],{"text":300,"config":660},{"href":302,"dataGaName":295,"dataGaLocation":469},{"text":305,"config":662},{"href":307,"dataGaName":308,"dataGaLocation":469},{"text":313,"config":664},{"href":315,"dataGaName":316,"dataGaLocation":469},{"text":318,"config":666},{"href":320,"dataGaName":321,"dataGaLocation":469},{"text":323,"config":668},{"href":325,"dataGaName":326,"dataGaLocation":469},{"text":328,"config":670},{"href":330,"dataGaName":331,"dataGaLocation":469},{"text":672,"config":673},"Sustainability",{"href":674,"dataGaName":672,"dataGaLocation":469},"/sustainability/",{"text":676,"config":677},"Diversity, inclusion and belonging (DIB)",{"href":678,"dataGaName":679,"dataGaLocation":469},"/diversity-inclusion-belonging/","Diversity, inclusion and belonging",{"text":333,"config":681},{"href":335,"dataGaName":336,"dataGaLocation":469},{"text":343,"config":683},{"href":345,"dataGaName":346,"dataGaLocation":469},{"text":348,"config":685},{"href":350,"dataGaName":351,"dataGaLocation":469},{"text":687,"config":688},"Modern Slavery Transparency Statement",{"href":689,"dataGaName":690,"dataGaLocation":469},"https://handbook.gitlab.com/handbook/legal/modern-slavery-act-transparency-statement/","modern slavery transparency statement",{"items":692},[693,696,699],{"text":694,"config":695},"Terms",{"href":521,"dataGaName":522,"dataGaLocation":469},{"text":697,"config":698},"Cookies",{"dataGaName":531,"dataGaLocation":469,"id":532,"isOneTrustButton":12},{"text":700,"config":701},"Privacy",{"href":526,"dataGaName":527,"dataGaLocation":469},[703],{"id":704,"title":705,"body":8,"config":706,"content":708,"description":8,"extension":28,"meta":712,"navigation":12,"path":713,"seo":714,"stem":715,"__hash__":716},"blogAuthors/en-us/blog/authors/david-oregan.yml","David Oregan",{"template":707},"BlogAuthor",{"name":18,"config":709},{"headshot":710,"ctfId":711},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1749659853/Blog/Author%20Headshots/oregand-headshot.png","oregand",{},"/en-us/blog/authors/david-oregan",{},"en-us/blog/authors/david-oregan","CX5gLc3Gs5FrmvpMNVkBtC5zRi3vj8l3wJGnW0iSa6Y",[718,730,743],{"content":719,"config":728},{"heroImage":720,"title":721,"description":722,"authors":723,"date":725,"category":9,"tags":726,"body":727},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1772643639/sapu29gmlgtwvhggmj6k.png","Extend GitLab Duo Agent Platform: Connect any tool with MCP","Learn how to connect external tools to GitLab Duo Agent Platform using MCP. Step-by-step setup with three practical workflow demos.",[724],"Albert Rabassa","2026-03-05",[9,27,24],"Managing software development often means juggling multiple tools: tracking issues in Jira, writing code in your IDE, and collaborating through GitLab. Context switching between these platforms disrupts focus and slows down delivery.\n\nWith GitLab Duo Agent Platform's [MCP](https://about.gitlab.com/topics/ai/model-context-protocol/) support, you can now connect Jira or any tool that supports MCP directly to your AI-powered development environment. Query issues, update tickets, and sync your workflow — all through natural language, without ever leaving your IDE.\n\n## What you'll learn\n\nIn this tutorial, we'll walk you through:\n\n* **Setting up the Jira/Atlassian OAuth application** for secure authentication\n* **Configuring GitLab Duo Agent Platform** as an MCP client\n* **Three practical use cases** demonstrating real-world workflows\n\n## Prerequisites\n\nBefore getting started, ensure you have the following:\n\n| Requirement | Details |\n| ---- | ----- |\n| **GitLab instance** | GitLab 18.8+ with Duo Agent Platform enabled |\n| **Jira account** | Jira Cloud instance with admin access to create OAuth applications |\n| **IDE** | Visual Studio Code with GitLab Workflow extension installed |\n| **MCP support** | MCP support enabled in GitLab |\n\n\n## Understanding the architecture\n\nGitLab Duo Agent Platform acts as an **MCP client**, connecting to the Atlassian MCP server to access your Jira project management data. Atlassian  MCP server handles authentication, translates natural language requests into API calls, and returns structured data back to GitLab Duo Agent Platform — all while maintaining security and audit controls.\n\n## Part 1: Configure Jira OAuth application\n\nTo securely connect GitLab Duo Agent Platform to your Jira instance, you'll need to create an OAuth 2.0 application in the Atlassian Developer Console. This grants to GitLab the MCP server authorized access to your Jira data.\n\n### Setup steps\n\nIf you prefer to configure manually, follow these steps:\n\n1. **Navigate to the Atlassian Developer Console**\n\n   * Go to [developer.atlassian.com/console/myapps](https://developer.atlassian.com/console/myapps)\n\n   * Sign in with your Atlassian account\n\n2. **Create a new OAuth 2.0 app**\n\n   * Click **Create** → **OAuth 2.0 integration**\n\n   * Enter a name (e.g., \"gitlab-dap-mcp\")\n\n   * Accept the terms and click **Create**\n\n3. **Configure permissions**\n\n   * Navigate to **Permissions** in the left sidebar.\n\n   * Add **Jira API** and configure the following scopes:\n\n     * `read:jira-work` — Read issues, projects, and boards\n\n     * `write:jira-work` — Create and update issues\n\n     * `read:jira-user` — Read user information\n\n4. **Set up authorization**\n\n   * Go to **Authorization** in the left sidebar\n\n   * Add a callback URL for your environment (`https://gitlab.com/oauth/callback`)\n\n   * Save your changes\n\n5. **Retrieve credentials**\n\n   * Navigate to **Settings**\n\n   * Copy your **Client ID** and **Client Secret**\n\n   * Store these securely — you'll need them for the MCP configuration\n\n\n### Interactive walkthrough: Jira OAuth setup\n\nClick on the image below to get started.\n\n\n[![Jira OAuth setup tour](https://res.cloudinary.com/about-gitlab-com/image/upload/v1772644850/wnzfoq43nkkfmgdqldmr.png)](https://gitlab.navattic.com/jira-oauth-setup)\n\n\n## Part 2: Configure GitLab Duo Agent Platform MCP client\n\nWith your OAuth credentials ready, you can now configure GitLab Duo Agent Platform to connect to the Atlassian MCP server.\n\n### Create your MCP configuration file\n\nCreate the MCP configuration file in your GitLab project at `.gitlab/duo/mcp.json`:\n\n\n```json\n{\n  \"mcpServers\": {\n    \"atlassian\": {\n      \"type\": \"http\",\n      \"url\": \"https://mcp.atlassian.com/v1/mcp\",\n      \"auth\": {\n        \"type\": \"oauth2\",\n        \"clientId\": \"YOUR_CLIENT_ID\",\n        \"clientSecret\": \"YOUR_CLIENT_SECRET\",\n        \"authorizationUrl\": \"https://auth.atlassian.com/oauth/authorize\",\n        \"tokenUrl\": \"https://auth.atlassian.com/oauth/token\"\n      },\n      \"approvedTools\": true\n    }\n  }\n}\n```\n\nReplace `YOUR_CLIENT_ID` and `YOUR_CLIENT_SECRET` with the credentials you generated in Part 1.\n\n### Enable MCP in GitLab\n\n1. Navigate to your **Group Settings** → **GitLab Duo** → **Configuration**\n2. Make sure “Allow external MCP tools” is checked\n\n### Verify the connection\n\nOpen your project in VS Code and ask in GitLab Duo Agent Platform chat:\n\n```text\nWhat MCP tools do you have access to?\n```\n\nThen\n\n```text\nTest the MCP JIRA configuration in this project\n```\n\nAt this point you'll be redirected from the IDE to the MCP Atlassian website to approve access:\n\n![Redirect to MCP Atlassian website](https://res.cloudinary.com/about-gitlab-com/image/upload/v1772643461/z5acqjgguh0damnnde9g.png \"Redirect to MCP Atlassian website\")\n\n\u003Cbr>\u003C/br>\n\n![Approve access](https://res.cloudinary.com/about-gitlab-com/image/upload/v1772643461/rwowamm8nsubhpixtn3i.png \"Approve access\")\n\n\u003Cbr>\u003C/br>\n\n![Select your JIRA instance and approve](https://res.cloudinary.com/about-gitlab-com/image/upload/v1772643461/chuzqd0jeptfwvoj7wjr.png \"Select your JIRA instance and approve\")\n\n\u003Cbr>\u003C/br>\n\n![Success!](https://res.cloudinary.com/about-gitlab-com/image/upload/v1772643462/bsgti5iste2bzck19o5y.png \"Success!\")\n\n\u003Cbr>\u003C/br>\n\n### Verify with the MCP Dashboard\n\nGitLab also provides a built-in **MCP Dashboard** directly in your IDE for this.\n\nIn VS Code or VSCodium, open the Command Palette (`Cmd+Shift+P` on macOS, `Ctrl+Shift+P` on Windows/Linux) and search for **\"GitLab: Show MCP Dashboard\"**. The dashboard opens in a new editor tab and gives you:\n\n* **Connection status** for each configured MCP server\n* **Available tools** exposed by the server (e.g., `jira_get_issue`, `jira_create_issue`)\n* **Server logs** so you can see exactly which tools are being called in real time\n\n![MCP servers dashboard and status](https://res.cloudinary.com/about-gitlab-com/image/upload/v1772643462/mmvdfchucacsydivowvn.png \"MCP servers dashboard and status\")\n\n\u003Cbr>\u003C/br>\n\n![Server details and permissions](https://res.cloudinary.com/about-gitlab-com/image/upload/v1772643462/tcocgdvovp2dl42pvfn8.png \"Server details and permissions\")\n\n\u003Cbr>\u003C/br>\n\n\n![MCP Server logs](https://res.cloudinary.com/about-gitlab-com/image/upload/v1772643466/mougvqqk1bozchaufsci.png \"MCP Server logs\")\n\n\u003Cbr>\u003C/br>\n\n### Interactive walkthrough: Testing MCP\n\n\u003Ciframe src=\"https://player.vimeo.com/video/1170005495?badge=0&autopause=0& player_id=0&app_id=58479\" frameborder=\"0\" allow=\"autoplay; fullscreen; picture-in-picture; clipboard-write; encrypted-media; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" style=\"position:absolute;top:0;left:0;width:100%;height:100%;\" title=\"Testing MCP\">\u003C/iframe>\u003Cscript src=\"https://player.vimeo.com/api/player.js\">\u003C/script>\n\n## Part 3: Use cases in action\n\nNow that your integration is configured, let's explore three practical workflows that demonstrate the power of connecting Jira to GitLab Duo Agent Platform.\n\n### Planning assistant\n\n**Scenario:** You're preparing for sprint planning and need to quickly assess the backlog, understand priorities, and identify blockers.\n\nThis demo shows you how to:\n\n* Query the backlog\n* Identify unassigned high-priority issues\n* Get AI-powered sprint recommendations\n\n#### Example prompts\n\nTry these prompts in GitLab Duo Agent Platform Chat:\n\n```text\nList all the unassigned issues in JIRA for project GITLAB\n```\n\n```text\nSuggest the two top issues to prioritize and summarize them. Assign them to me.\n```\n\n### Interactive walkthrough: Project planning\n\n\u003Ciframe src=\"https://player.vimeo.com/video/1170005462?badge=0&autopause=0&player_id=0&app_id=58479\" frameborder=\"0\" allow=\"autoplay; fullscreen; picture-in-picture; clipboard-write; encrypted-media; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" style=\"position:absolute;top:0;left:0;width:100%;height:100%;\" title=\"Project Planning\">\u003C/iframe>\u003Cscript src=\"https://player.vimeo.com/api/player. js\">\u003C/script>\n\n### Issue triage and creation from code\n\n**Scenario:** While reviewing code, you discover a bug and want to create a Jira issue with relevant context — without leaving your IDE.\n\nThis demo walks you through:\n\n* Identifying a bug while coding\n* Creating a detailed Jira issue via natural language\n* Auto-populating issue fields with code context\n* Linking the issue to your current branch\n\n#### Example prompts\n\n```text\nSearch in JIRA for a bug related to: Null pointer exception in PaymentService.processRefund().\nIf it does not exist create it with all the context needed from the code. Find possible blockers that this bug may cause.\n```\n\n```text\nCreate a new branch called issue-gitlab-18, checkout, and link it to the issue we just created. Assign the JIRA issue to me and mark it as in-progress.\n```\n\n### Interactive walkthrough: Bug review and task automation\n\n\u003Ciframe src=\"https://player.vimeo.com/video/1170005368?badge=0&autopause=0& player_id=0&app_id=58479\" frameborder=\"0\" allow=\"autoplay; fullscreen; picture-in-picture; clipboard-write; encrypted-media; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" style=\"position:absolute;top:0;left:0;width:100%;height:100%;\" title=\"Bug Review\">\u003C/iframe>\u003Cscript src=\"https://player.vimeo.com/api/player.js\">\u003C/script>\n\n### Cross-system incident investigation\n\n**Scenario:** A production incident occurs, and you need to correlate information from Jira (incident ticket), GitLab Project Management, your codebase, and merge requests to identify the root cause.\n\nThis demo demonstrates:\n\n* Fetching incident details from Jira\n* Correlating with recent merge requests in GitLab\n* Identifying potentially related code changes\n* Generating an incident timeline\n* Design a remediation plan and create it as a work item in GitLab\n\n#### Example prompts\n\n```text\n\"We have a production incident INC-1 about checkout failures. Can you help me investigate with all available context?\"\n```\n\n```text\nCreate a timeline of events for incident INC-1 including related Jira issues and recent deployments\n```\n\n```text\nPropose a remediation plan\n```\n\n### Interactive walkthrough: Cross-system troubleshooting and remediation\n\n\u003Ciframe src=\"https://player.vimeo.com/video/1170005413?badge=0&autopause=0& player_id=0&app_id=58479\" frameborder=\"0\" allow=\"autoplay; fullscreen; picture-in-picture; clipboard-write; encrypted-media; web-share\" referrerpolicy=\"strict-origin-when-cross-origin\" style=\"position:absolute;top:0;left:0;width:100%;height:100%;\" title=\"Cross System Investigation\">\u003C/iframe>\u003Cscript src=\"https://player.vimeo.com/api/player.js\">\u003C/script>\n\n## Troubleshooting\n\nThese are some common setup issues and quick fixes:\n\n| Issue | Solution |\n| ----- | ----- |\n| \"MCP server not found\" | Verify the `mcp.json` file is in the correct location and properly formatted |\n| \"Authentication failed\" | Re-check your OAuth credentials and ensure scopes are correctly configured in Atlassian |\n| \"No Jira tools available\" | Restart VS Code after updating `mcp.json` and ensure MCP is enabled in GitLab |\n| \"Connection timeout\" | Check your network connectivity to `mcp.atlassian.com` |\n\n\u003Cbr/> For detailed troubleshooting, see the [GitLab MCP clients documentation](https://docs.gitlab.com/user/gitlab_duo/model_context_protocol/mcp_clients/).\n\n\n## Security considerations\n\nWhen integrating Jira with GitLab Duo Agent Platform:\n\n* **OAuth tokens** — Make sure credentials remain secure\n* **Principle of least privilege** — Only grant the minimum required Jira scopes\n* **Token rotation** — Regularly rotate your OAuth credentials as part of security hygiene\n\n\n## Summary\n\nConnecting GitLab Duo Agent Platform to different tools through MCP transforms how you interact with your development lifecycle. In this article, you have learned how to:\n\n* **Query issues naturally** — Ask questions about your backlog, sprints, and incidents in natural language.\n* **Create and update issues on all your DevSecOps environment** — File bugs and update tickets without leaving your IDE.\n* **Correlate across systems** — Combine Jira data with GitLab project management, merge requests, and pipelines for complete visibility.\n* **Reduce context switching** — Keep your focus on code while staying connected to project management.\n\nThis integration exemplifies the power of MCP: standardized, secure access to your tools through AI, enabling developers to work more efficiently without sacrificing governance or security.\n\n\n## Read more\n\n* [GitLab Duo Agent Platform adds support for Model Context Protocol](https://about.gitlab.com/blog/duo-agent-platform-with-mcp/)\n\n* [What is Model Context Protocol?](https://about.gitlab.com/topics/ai/model-context-protocol/)\n\n* [Agentic AI guides and resources](https://about.gitlab.com/blog/agentic-ai-guides-and-resources/)\n\n* [GitLab MCP clients documentation](https://docs.gitlab.com/user/gitlab_duo/model_context_protocol/mcp_clients/)\n\n* [Get started with GitLab Duo Agent Platform: The complete guide](https://about.gitlab.com/blog/gitlab-duo-agent-platform-complete-getting-started-guide/)",{"featured":32,"template":13,"slug":729},"extend-gitlab-duo-agent-platform-connect-any-tool-with-mcp",{"content":731,"config":741},{"title":732,"description":733,"authors":734,"heroImage":736,"date":737,"body":738,"category":9,"tags":739},"10 AI prompts to speed your team’s software delivery","Eliminate review backlogs, security delays, and coordination overhead with ready-to-use AI prompts covering every stage of the software lifecycle.",[735],"Chandler Gibbons","https://res.cloudinary.com/about-gitlab-com/image/upload/v1772632341/duj8vaznbhtyxxhodb17.png","2026-03-04","AI-assisted coding tools are helping developers generate code faster than ever. So why aren’t teams _shipping_ faster?\n\nBecause coding is only 20% of the software delivery lifecycle, the remaining 80% becomes the bottleneck: code review backlogs grow, security scanning can’t keep pace, documentation falls behind, and manual coordination overhead increases.\n\nThe good news is that the same AI capabilities that accelerate individual coding can eliminate these team-level delays. You just need to apply AI across your entire software lifecycle, not only during the coding phase.\n\nBelow are 10 ready-to-use prompts from the [GitLab Duo Agent Platform Prompt Library](https://about.gitlab.com/gitlab-duo/prompt-library/) that help teams overcome common obstacles to faster software delivery. Each prompt addresses a specific slowdown that emerges when individual productivity increases without corresponding improvements in team processes.\n\n## How do you move code review from bottleneck to accelerator?\nDevelopers generate merge requests faster with AI assistance, but human reviewers can quickly become overwhelmed as code review cycles stretch from hours to days. AI can handle routine review tasks, freeing reviewers to focus on architecture and business logic instead of catching basic logical errors and API contract violations.\n\n### Review MR for logical errors\n**Complexity**: Beginner\n\n**Category**: Code Review\n\n**Prompt from library**:\n\n\n```text\nReview this MR for logical errors, edge cases, and potential bugs: [MR URL or paste code]\n```\n\n**Why it helps**: Automated linters catch syntax issues, but logical errors require understanding intent. This prompt catches bugs before human reviewers even look at the code, reducing review cycles from multiple rounds to often just one approval.\n\n### Identify breaking changes in MR\n**Complexity**: Beginner\n\n**Category**: Code Review\n\n**Prompt from library**:\n\n\n```text\nDoes this MR introduce any breaking changes?\n\nChanges:\n[PASTE CODE DIFF]\n\nCheck for:\n1. API signature changes\n2. Removed or renamed public methods\n3. Changed return types\n4. Modified database schemas\n5. Breaking configuration changes\n```\n\n**Why it helps**: Breaking changes discovered during deployment can cause rollbacks and incidents. This prompt shifts that discovery left to the MR stage, when fixes are faster and less expensive.\n\n## How can you shift security left without slowing down?\nSecurity scans generate hundreds of findings. Security teams manually triage each one while developers wait for approval to deploy. Most findings are false positives or low-risk issues, but identifying the real threats requires expertise and time. AI can prioritize findings by actual exploitability and auto-remediate common vulnerabilities, allowing security teams to focus on the threats that matter.\n\n### Analyze security scan results\n**Complexity**: Intermediate\n\n**Category**: Security\n\n**Agent**: Duo Security Analyst\n\n**Prompt from library**:\n\n\n```text\n@security_analyst Analyze these security scan results:\n\n[PASTE SCAN OUTPUT]\n\nFor each finding:\n1. Assess real risk vs false positive\n2. Explain the vulnerability\n3. Suggest remediation\n4. Prioritize by severity\n```\n\n**Why it helps**: Most security scan findings are false positives or low-risk issues. This prompt helps security teams focus on the findings that actually matter, reducing remediation time from weeks to days.\n\n### Review code for security issues\n**Complexity**: Intermediate\n\n**Category**: Security\n\n**Agent**: Duo Security Analyst\n\n**Prompt from library**:\n\n```text\n@security_analyst Review this code for security issues:\n\n[PASTE CODE]\n\nCheck for:\n1. Injection vulnerabilities\n2. Authentication/authorization flaws\n3. Data exposure risks\n4. Insecure dependencies\n5. Cryptographic issues\n```\n\n**Why it helps**: Traditional security reviews happen after code is written. This prompt enables developers to find and fix security issues before creating an MR, eliminating the back and forth that delays deployments.\n\n## How do you keep documentation current as code changes?\nCode changes faster than documentation. Onboarding new developers takes weeks because docs are outdated or missing. Teams know documentation is important, but it always gets deferred when deadlines approach. Automating documentation generation and updates as part of your standard workflow ensures docs stay current without adding manual work.\n\n### Generate release notes from MRs\n**Complexity**: Beginner\n\n**Category**: Documentation\n\n**Prompt from library**:\n\n```text\nGenerate release notes for these merged MRs:\n[LIST MR URLs or paste titles]\n\nGroup by:\n1. New features\n2. Bug fixes\n3. Performance improvements\n4. Breaking changes\n5. Deprecations\n```\n\n**Why it helps**: Manual release note compilation takes hours and often includes errors or omissions. Automated generation ensures every release has comprehensive notes without adding work to your release process.\n\n### Update documentation after code changes\n**Complexity**: Beginner\n\n**Category**: Documentation\n\n**Prompt from library**:\n\n```text\nI changed this code:\n\n[PASTE CODE CHANGES]\n\nWhat documentation needs updating? Check:\n1. README files\n2. API documentation\n3. Architecture diagrams\n4. Onboarding guides\n```\n\n**Why it helps**: Documentation drift happens because teams forget which docs need updates after code changes. This prompt makes documentation maintenance part of your development workflow, not a separate task that gets deferred.\n\n## How do you break down planning complexity?\nLarge features get stuck in planning. Teams spend weeks in meetings trying to scope work and identify dependencies. The complexity feels overwhelming, and it's hard to know where to start. AI can systematically decompose complex work into concrete, implementable tasks with clear dependencies and acceptance criteria, transforming weeks of planning into focused implementation.\n\n### Break down epic into issues\n**Complexity**: Intermediate\n\n**Category**: Documentation\n\n**Agent**: Duo Planner\n\n**Prompt from library**:\n\n```text\nBreak down this epic into implementable issues:\n\n[EPIC DESCRIPTION]\n\nConsider:\n1. Technical dependencies\n2. Reasonable issue sizes\n3. Clear acceptance criteria\n4. Logical implementation order\n```\n\n**Why it helps**: This prompt transforms a week of planning meetings into 30 minutes of AI-assisted decomposition followed by team review. Teams start implementation sooner with clearer direction.\n\n## How can you expand test coverage without expanding effort?\nDevelopers are writing code faster, but if testing doesn't keep pace, test coverage decreases and bugs slip through. Writing comprehensive tests manually is time-consuming, and developers often miss edge cases under deadline pressure. Generating tests automatically means developers can review and refine rather than write from scratch, maintaining quality without sacrificing velocity.\n\n### Generate unit tests\n**Complexity**: Beginner\n\n**Category**: Testing\n\n**Prompt from library**:\n\n```text\nGenerate unit tests for this function:\n\n[PASTE FUNCTION]\n\nInclude tests for:\n1. Happy path\n2. Edge cases\n3. Error conditions\n4. Boundary values\n5. Invalid inputs\n```\n\n**Why it helps**: Writing tests manually is time consuming, and developers often miss edge cases. This prompt generates thorough test suites in seconds, which developers can review and adjust rather than write from scratch.\n\n### Review test coverage gaps\n**Complexity**: Beginner\n\n**Category**: Testing\n\n**Prompt from library**:\n\n```text\nAnalyze test coverage for [MODULE/COMPONENT]:\n\nCurrent coverage: [PERCENTAGE]\n\nIdentify:\n1. Untested functions/methods\n2. Uncovered edge cases\n3. Missing error scenario tests\n4. Integration points without tests\n5. Priority areas to test next\n```\n\n**Why it helps**: This prompt reveals blind spots in your test suite before they cause production incidents. Teams can systematically improve coverage where it matters most.\n\n## How do you reduce mean time to resolution when debugging?\nProduction incidents take hours to diagnose. Developers wade through logs and stack traces while customers experience downtime. Every minute of debugging is a minute of lost productivity and potential revenue. AI can accelerate root cause analysis by parsing complex error messages and suggesting specific fixes, cutting diagnostic time from hours to minutes.\n\n### Debug failing pipeline\n**Complexity**: Beginner\n\n**Category**: Debugging\n\n**Prompt from library**:\n\n```text\nThis pipeline is failing:\n\nJob: [JOB NAME]\nStage: [STAGE]\nError: [PASTE ERROR MESSAGE/LOG]\n\nHelp me:\n1. Identify the root cause\n2. Suggest a fix\n3. Explain why it started failing\n4. Prevent similar issues\n```\n\n**Why it helps**: CI/CD failures block entire teams. This prompt diagnoses failures in seconds instead of the 15-30 minutes developers typically spend investigating, keeping deployment velocity high.\n\n## Moving from individual gains to team acceleration\nThese prompts represent a shift in how teams apply AI to software delivery. Rather than focusing solely on individual developer productivity, they address the coordination, quality, and knowledge-sharing challenges that actually constrain team velocity.\n\nThe [complete prompt library](https://about.gitlab.com/gitlab-duo/prompt-library/) contains more than 100 prompts across all stages of the software lifecycle: planning, development, security, testing, deployment, and operations. Each prompt is tagged by complexity level (Beginner, Intermediate, Advanced) and categorized by use case, making it easy to find the right starting point for your team.\n\nStart with prompts tagged “Beginner” that address your team’s most pressing obstacles. As your team builds confidence, explore intermediate and advanced prompts that enable more sophisticated workflows. The goal is not just faster coding — it's faster, safer, higher-quality software delivery from planning through production.",[23,740],"DevOps platform",{"featured":32,"template":13,"slug":742},"10-ai-prompts-to-speed-your-teams-software-delivery",{"content":744,"config":754},{"title":745,"description":746,"heroImage":747,"authors":748,"date":750,"body":751,"category":9,"tags":752},"AI can detect vulnerabilities, but who governs risk?","AI-assisted vulnerability detection is developing fast, but the harder challenges of enforcement, governance, and supply chain security require a holistic platform.","https://res.cloudinary.com/about-gitlab-com/image/upload/v1772195014/ooezwusxjl1f7ijfmbvj.png",[749],"Omer Azaria","2026-02-27","Anthropic recently announced Claude Code Security, an AI system that detects vulnerabilities and proposes fixes. The market reacted immediately, with security stocks dipping as investors questioned whether AI might replace traditional AppSec tools. The question on everyone's mind: If AI can write code and secure it, is application security about to become obsolete?\n\nIf security only meant scanning code, the answer might be yes. But enterprise security has never been about detection alone.\n\nOrganizations are not asking whether AI can find vulnerabilities. They are asking three much harder questions: \n\n* Is what we are about to ship safe?  \n* Has our risk posture changed as environments evolve and dependencies, third-party services, tools, and infrastructure continuously shift?  \n* How do we govern a codebase that is increasingly assembled by AI and third-party sources, and that we are still accountable for? \n\nThose questions require a platform answer: Detection surfaces risk, but governance determines what happens next. \n\n[GitLab](https://about.gitlab.com/) is the orchestration layer built to govern the software lifecycle end-to-end. It gives teams the enforcement, visibility, and auditability they need to keep pace with the speed of AI-assisted development.\n\n## Trusting AI requires governing risk\n\nAI systems are rapidly getting better at identifying vulnerabilities and suggesting fixes. This is a meaningful and welcome advancement, but analysis is not accountability.\n\nAI cannot enforce company policy or define acceptable risk on its own. Humans must set the boundaries, policies, and guardrails that agents operate within, establishing separation of duties, ensuring audit trails, and maintaining consistent controls across thousands of repositories and teams. Trust in agents comes not from autonomy alone, but from clearly defined governance set by people. \n\nIn an [agentic world](https://about.gitlab.com/topics/agentic-ai/), where software is increasingly written and modified by autonomous systems, governance becomes more important, not less. The more autonomy organizations grant to AI, the stronger the governance must be.\n\nGovernance is not friction. It is the foundation that makes AI-assisted development trustworthy at scale.\n\n## LLMs see code, but platforms see context\n\nA large language model ([LLM](https://about.gitlab.com/blog/what-is-a-large-language-model-llm/)) evaluates code in isolation. An enterprise application security platform understands context. This difference matters because risk decisions are contextual:\n\n* Who authored the change?  \n* How critical is the application to the business?  \n* How does it interact with infrastructure and dependencies?  \n* Does the vulnerability exist in code that is actually reachable in production, or is it buried in a dependency that never executes?  \n* Is it actually exploitable in production, given how the application runs, its APIs, and the environment around it?\n\nSecurity decisions depend on this context. Without it, detection produces noisy alerts that slow down development rather than reducing risk. With it, organizations can triage quickly and manage risk effectively. Context evolves continuously as software changes, which means governance cannot be a one-time decision. \n\n## Static scans can’t keep up with dynamic risk\n\nSoftware risk is dynamic. Dependencies change, environments evolve, and systems interact in ways no single analysis can fully predict. A clean scan at one moment does not guarantee safety at release.\n\nEnterprise security depends on continuous assurance: controls embedded directly into development workflows that evaluate risk as software is built, tested, and deployed.\n\nDetection provides insight. Governance provides trust. Continuous governance is what allows organizations to ship safely at scale.\n\n## Governing the agentic future\n\nAI is reshaping how software is created. The question is no longer whether teams will use AI, but how safely they can scale it.\n\nSoftware today is assembled as much as it is written, from AI-generated code, open-source libraries, and third-party dependencies that span thousands of projects. Governing what ships across all of those sources is the hardest and most consequential part of application security, and it is the part that no developer-side tool is built to address. \n\nAs an intelligent orchestration platform, GitLab is built to address this problem. GitLab Ultimate embeds governance, policy enforcement, security scanning, and auditability directly into the workflows where software is planned, built, and shipped, so security teams can govern at the speed of AI. \n\nAI will accelerate development dramatically. The organizations that benefit most from AI will not be those with the smartest assistants alone, but those that build trust through strong governance.\n\n> To learn how GitLab helps organizations [govern and ship AI-generated code](https://about.gitlab.com/solutions/software-compliance/?utm_medium=blog&utm_campaign=eg_global_x_x_security_en_) safely, [talk to our team today](https://about.gitlab.com/sales/?utm_medium=blog&utm_campaign=eg_global_x_x_security_en_)\n\n\n ## Related reading\n\n - [Integrating AI with DevOps for enhanced security](https://about.gitlab.com/topics/devops/ai-enhanced-security/)\n - [The GitLab AI Security Framework for security leaders](https://about.gitlab.com/blog/the-gitlab-ai-security-framework-for-security-leaders/)\n - [Improve AI security in GitLab with composite identities](https://about.gitlab.com/blog/improve-ai-security-in-gitlab-with-composite-identities/)",[23,753],"security",{"featured":12,"template":13,"slug":755},"ai-can-detect-vulnerabilities-but-who-governs-risk",{"promotions":757},[758,771,782],{"id":759,"categories":760,"header":761,"text":762,"button":763,"image":768},"ai-modernization",[9],"Is AI achieving its promise at scale?","Quiz will take 5 minutes or less",{"text":764,"config":765},"Get your AI maturity score",{"href":766,"dataGaName":767,"dataGaLocation":245},"/assessments/ai-modernization-assessment/","modernization assessment",{"config":769},{"src":770},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1772138786/qix0m7kwnd8x2fh1zq49.png",{"id":772,"categories":773,"header":774,"text":762,"button":775,"image":779},"devops-modernization",[27,570],"Are you just managing tools or shipping innovation?",{"text":776,"config":777},"Get your DevOps maturity score",{"href":778,"dataGaName":767,"dataGaLocation":245},"/assessments/devops-modernization-assessment/",{"config":780},{"src":781},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1772138785/eg818fmakweyuznttgid.png",{"id":783,"categories":784,"header":785,"text":762,"button":786,"image":790},"security-modernization",[753],"Are you trading speed for security?",{"text":787,"config":788},"Get your security maturity score",{"href":789,"dataGaName":767,"dataGaLocation":245},"/assessments/security-modernization-assessment/",{"config":791},{"src":792},"https://res.cloudinary.com/about-gitlab-com/image/upload/v1772138786/p4pbqd9nnjejg5ds6mdk.png",{"header":794,"blurb":795,"button":796,"secondaryButton":801},"Start building faster today","See what your team can do with the intelligent orchestration platform for DevSecOps.\n",{"text":797,"config":798},"Get your free trial",{"href":799,"dataGaName":52,"dataGaLocation":800},"https://gitlab.com/-/trial_registrations/new?glm_content=default-saas-trial&glm_source=about.gitlab.com/","feature",{"text":507,"config":802},{"href":56,"dataGaName":57,"dataGaLocation":800},1777309975515]