@azure-devops/mcp
Connects Claude directly to Azure DevOps work items, pipelines, and repositories, eliminating manual context-switching and reducing time spent on status upda…
Official Microsoft MCP server (npm: @azure-devops/mcp) that brings Azure DevOps context to agents — work items, builds, repos, test plans, wikis, teams, and iterations. Runs locally via npx with your organization name; a hosted Remote MCP Server is now in public preview and is Microsoft's recommended path going forward.
- Query work item status across sprints without opening Azure DevOps portal
- Auto-generate release notes from commit history and linked items
- Check pipeline build status and logs during incident response
Connects Claude directly to Azure DevOps work items, pipelines, and repositories, eliminating manual context-switching and reducing time spent on status updates or ticket queries.
Teams running development workflows in Azure DevOps who want Claude to retrieve work items, pipeline status, or commit history without leaving their chat interface.
https://github.com/microsoft/azure-devops-mcp
By antonatms
How to Get It
npx -y @azure-devops/mcp <your-ado-organization>
Tip: Paste this into a Claude Code conversation. Verify command matches your Claude Code version.
Once it’s connected, paste this into Claude:
Help me query work item status across sprints without opening Azure DevOps portal
Trust Signals Auto-scanned
Data & Access
Community Pulse Growing
Discussed on Hacker News
- AzureFunBytes – Azure Virtual Networks with Abel Wang – Azure DevOps Blog — Hacker News · 2 pts
- Azure DevOps Blog: What Is DevOps? With Donovan Brown — Hacker News · 2 pts
- Ask HN: How to track tickets across DevOps — Hacker News · 2 pts
3 mentions across 1 sources
Reviewer notes
Auto-scanned review. These are observations, not a security certification.
catalog_hygiene stale-eval refresh: Scored from trust signals (evidence-eval-v1): 1,958 GitHub stars; 62 contributors; last commit 6d ago; license MIT.
Things to check
- Scanned, not hands-on tested — this entry was auto-scanned from public metadata (GitHub metrics, license, security flags). No reviewer has run it, and no tool-specific limitations have been documented yet.
How to evaluate tools before deploying →
Data shown here comes from public APIs and automated scanning. Reviewer notes reflect one person's experience. This is not a security certification or legal recommendation. Always evaluate tools according to your own organization's policies.
Evaluation
catalog_hygiene stale-eval refresh: Scored from trust signals (evidence-eval-v1): 1,958 GitHub stars; 62 contributors; last commit 6d ago; license MIT.