Azure MCP Server

MCP server for Azure DevOps Server 2022 / TFS - READ-ONLY access to builds, work items, releases, git, pipelines, and test results

Local serverstdioGo

What is the Azure MCP server?

MCP server for Azure DevOps Server 2022 / TFS - READ-ONLY access to builds, work items, releases, git, pipelines, and test results. That is what the azure mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

A READ-ONLY MCP (Model Context Protocol) server that connects AI assistants to Azure DevOps Server (on-premises). Works with Claude Code CLI, VS Code AI extensions (Continue, Cline), Cursor, and any MCP-compatible client.

  • Projects — List and explore projects
  • Git/Repos — Browse repositories, commits, branches, pull requests, diffs, and code search
  • Builds — List builds, view logs, analyze errors
  • Work Items — Query work items, find linked commits/PRs
  • Releases — View releases and deployment status
  • Pipelines — List YAML pipelines, view runs, get pipeline configuration

The tools it exposes

The server publishes 4 tools. What each one is for:

  • Projects — The Projects tool exposed by this server
  • Builds — The Builds tool exposed by this server
  • Releases — The Releases tool exposed by this server
  • Pipelines — The Pipelines tool exposed by this server

What it needs from you

Configuration is passed through the environment: AZURE_DEVOPS_URL, AZURE_DEVOPS_PAT, AZURE_DEVOPS_COLLECTION, AZURE_DEVOPS_PROJECT. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

  • Node.js 18 or higher - Azure DevOps Server 2020 or 2022 (on-premises) - Personal Access Token (PAT) with read scopes

Getting it running

azure-devops-mcp on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.

How it compares

This sits in the developer tooling group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Azure's toolset — Projects, Builds, Releases and 1 more — is a fair guide to whether it matches your workflow. It is maintained by GitHub Actions; worth a glance at recent repository activity before you build anything load-bearing on it.

We check each listing at SyncDev against the project's documentation before it goes live — if something here drifts out of date, it is a bug worth reporting.

Things to watch

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
ProjectsThe Projects tool exposed by this server.
BuildsThe Builds tool exposed by this server.
ReleasesThe Releases tool exposed by this server.
PipelinesThe Pipelines tool exposed by this server.

How to install the Azure MCP server

{
  "mcpServers": {
    "azure-devops": {
      "command": "cmd",
      "args": ["/c", "npx", "azure-devops-mcp"],
      "env": {
        "AZURE_DEVOPS_URL": "http://your-tfs-server:8080/tfs",
        "AZURE_DEVOPS_PAT": "your-personal-access-token",
        "AZURE_DEVOPS_COLLECTION": "YourCollection",
        "AZURE_DEVOPS_PROJECT": "YourDefaultProject"
      }
    }
  }
}

Configuration as documented by the project. Restart the client after saving.

Configuration

  • Node.js 18 or higher - Azure DevOps Server 2020 or 2022 (on-premises) - Personal Access Token (PAT) with read scopes
VariableDescriptionRequired
AZURE_DEVOPS_URLEndpoint or connection string the server talks to.Yes
AZURE_DEVOPS_PATConfiguration value read at startup.Optional
AZURE_DEVOPS_COLLECTIONConfiguration value read at startup.Optional
AZURE_DEVOPS_PROJECTConfiguration value read at startup.Optional

Example prompts to try

  • Use Azure to Projects.
  • Use Azure to Builds.
  • Use Azure to Releases.

Frequently asked questions

It connects Azure to MCP-compatible AI assistants such as Claude and Cursor, exposing 4 tools (Projects, Builds, Releases, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Azure directly.