AzureDevOps.MCP Server

A Model Context Protocol (MCP) server that provides comprehensive integration with Azure DevOps. This server enables AI assistants like Claude

Local serverstdio

What is the AzureDevOps.MCP MCP server?

A Model Context Protocol (MCP) server that provides comprehensive integration with Azure DevOps. This server enables AI assistants like Claude Desktop and development tools like VS Code to seamlessly interact with Azure DevOps through the. That is what the azuredevops.mcp 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

  • Projects — Browse Azure DevOps projects and team information
  • Repositories — View repositories, files, commits, branches, and pull requests
  • Work Items — Query and manage work items with optional write operations
  • Performance Monitoring — Built-in performance tracking and optimization
  • Production Ready — Comprehensive caching, error handling, and security features
  • Safe Write Operations — Opt-in write capabilities with audit logging

The tools it exposes

The server publishes 14 tools. What each one is for:

  • list_projects — Lists all projects in the Azure DevOps organization
  • list_repositories — Lists repositories in a specific project
  • list_repository_items — Lists files and folders in a repository path
  • get_file_content — Gets the content of a specific file from a repository
  • list_work_items — Lists work items in a specific project
  • get_work_item — Gets detailed information about a specific work item
  • add_pull_request_comment — Adds a comment to a pull request (requires PullRequestComments)
  • create_draft_pull_request — Creates a draft pull request (requires CreateDraftPullRequest)
  • update_work_item_tags — Adds or removes tags from work items (requires UpdateWorkItemTags)
  • batch_get_work_items — Retrieves multiple work items efficiently in parallel
  • batch_get_repositories — Gets multiple repository details in parallel
  • get_test_plans — Gets test plans for a specific Azure DevOps project

What it needs from you

  • .NET 9 SDK (for local development) - Docker (for running the container) - Azure DevOps account with appropriate permissions

Getting it running

Setup follows the usual MCP pattern — install or clone the server, register it in your client's configuration file, restart the client. The configuration blocks on this page cover the common clients.

How it compares

Among the developer tooling options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. AzureDevOps.MCP's toolset — list_projects, list_repositories, list_repository_items and 11 more — is a fair guide to whether it matches your workflow. It is maintained by decriptor; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against AzureDevOps.MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

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.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch AzureDevOps.MCP.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
list_projectsLists all projects in the Azure DevOps organization
list_repositoriesLists repositories in a specific project
list_repository_itemsLists files and folders in a repository path
get_file_contentGets the content of a specific file from a repository
list_work_itemsLists work items in a specific project
get_work_itemGets detailed information about a specific work item
add_pull_request_commentAdds a comment to a pull request (requires PullRequestComments)
create_draft_pull_requestCreates a draft pull request (requires CreateDraftPullRequest)
update_work_item_tagsAdds or removes tags from work items (requires UpdateWorkItemTags)
batch_get_work_itemsRetrieves multiple work items efficiently in parallel
batch_get_repositoriesGets multiple repository details in parallel
get_test_plansGets test plans for a specific Azure DevOps project
get_test_planGets detailed information about a specific test plan
get_test_suitesGets test suites for a specific test plan

How to install the AzureDevOps.MCP MCP server

{
  "mcpServers": {
    "azure-devops": {
      "command": "docker",
      "args": [
        "run", "-i",
        "-e", "AzureDevOps__OrganizationUrl=https://dev.azure.com/your-organization",
        "-e", "AzureDevOps__PersonalAccessToken=your-pat-goes-here",
        "azuredevops-mcp"
      ]
    }
  }
}

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

Configuration

  • .NET 9 SDK (for local development) - Docker (for running the container) - Azure DevOps account with appropriate permissions

Example prompts to try

  • Use AzureDevOps.MCP to list projects.
  • Use AzureDevOps.MCP to list repositories.
  • Use AzureDevOps.MCP to list repository items.

Frequently asked questions

It connects AzureDevOps.MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (list_projects, list_repositories, list_repository_items, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with AzureDevOps.MCP directly.