PluginBench
MCP Server
Active
MIT

Azure DevOps (ADO) MCP Server

io.github.PremierInc/azure-devops

Connect AI agents to Azure DevOps for project management, work items, repos, builds, and wikis.

What is the Azure DevOps (ADO) MCP server?

The Azure DevOps MCP Server gives AI agents access to Azure DevOps through the Model Context Protocol. It provides tools to manage projects, work items, repositories, builds, test plans, wikis, and teams. Use the hosted remote server for simplest setup, or run locally for stdio connections.

This server brings Azure DevOps context directly to AI agents like Claude and Cursor. You can list projects, manage work items, query builds and repositories, create and update wiki pages, manage test plans, and handle team operations. It's designed for teams using Azure DevOps who want AI agents to automate and assist with DevOps workflows.

How to install Azure DevOps (ADO)

Copy-paste configuration for popular MCP clients.

transport: http
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • Authorization
    secret

    Authorization header with authentication token (PAT or App token)

~/.cursor/mcp.json
{
  "mcpServers": {
    "azure-devops": {
      "url": "https://mcp.dev.azure.com"
    }
  }
}

Tools & capabilities

Tools this server exposes to the agent.

  • List Projects — Retrieve all Azure DevOps projects in your organization
  • List Work Items — Query work items for a project, optionally filtered by iteration or team
  • List Builds — Retrieve builds for a specified project
  • List Repositories — Get repositories for a project
  • List Test Plans — Retrieve test plans for a project
  • List Teams — Get teams for a project
  • List Iterations — Retrieve iterations for a project
  • List Wikis — Get all wikis in a project
  • Create Wiki Page — Create a new wiki page with specified content
  • Update Wiki Page — Update an existing wiki page with new content
  • Get Wiki Page — Retrieve the content of a specific wiki page

Use cases

  • List and filter work items across projects and iterations to track team progress
  • Create and update wiki pages for documentation, architecture, and onboarding
  • Query builds and repositories to monitor CI/CD pipelines and code changes
  • Manage test plans and retrieve test results for quality assurance workflows
  • Retrieve project, team, and iteration information to provide context for agent decisions

Azure DevOps (ADO) MCP server FAQ

What is the Azure DevOps MCP Server?

It's an MCP server that gives AI agents like Claude and Cursor access to Azure DevOps. You can manage projects, work items, builds, repositories, wikis, test plans, and teams through natural language prompts.

Is it free to use?

Yes, the Azure DevOps MCP Server is open source under the MIT License. The remote server (recommended) is hosted by Microsoft at https://mcp.dev.azure.com. You only need an Azure DevOps account.

How do I install it in Cursor or Claude?

Create a `.vscode/mcp.json` file in your project. For the remote server, add the configuration with your organization URL. For local setup, use `npx @azure-devops/mcp` with your organization name. See the README for detailed instructions for different clients.

What authentication is required?

You need a Microsoft account with access to your Azure DevOps organization. The server supports multiple authentication methods including Azure CLI and interactive sign-in.

Can I use it locally or only as a remote server?

Both. Microsoft recommends the remote server (https://mcp.dev.azure.com) for simplest setup with no installation. A local stdio server is also available if your scenario requires it.

What domains/tools are available?

Tools cover core (projects, teams), work items, builds, repositories, test plans, wikis, pipelines, and advanced security. You can load all tools or filter by domain to keep the tool list manageable.

README (reference)

Source of truth, from the repository.

Azure DevOps MCP Server

[!WARNING] We recently completed a full tool consolidation that includes renaming of existing tools. Please see the Toolset documentation for the complete list of new tool names.

If this is a breaking change for your agents or skills, you can temporarily pin the version to @azure-devops/mcp@2.8.1

This project gives AI agents access to Azure DevOps through the Model Context Protocol (MCP). Use the hosted remote server for the simplest setup, or run the local server when you need a stdio connection.

Table of Contents

[!IMPORTANT] We recommend using the Remote MCP Server instead of this local server. It requires no installation and gets new features first.

Learn more

  1. Overview
  2. Design
  3. Remote MCP Server (Recommended)
  4. Supported Tools
  5. Local MCP Server Installation (Optional)
  6. Using Domains (Local Server)
  7. Project and Team Defaults (Local Server)
  8. Troubleshooting
  9. Examples and Best Practices
  10. Frequently Asked Questions
  11. Contributing

Overview

The Azure DevOps MCP Server brings Azure DevOps context to your agents. Try prompts like:

  • "List my ADO projects"
  • "List ADO Builds for 'Contoso'"
  • "List ADO Repos for 'Contoso'"
  • "List test plans for 'Contoso'"
  • "List teams for project 'Contoso'"
  • "List iterations for project 'Contoso'"
  • "List my work items for project 'Contoso'"
  • "List work items in current iteration for 'Contoso' project and 'Contoso Team'"
  • "List all wikis in the 'Contoso' project"
  • "Create a wiki page '/Architecture/Overview' with content about system design"
  • "Update the wiki page '/Getting Started' with new onboarding instructions"
  • "Get the content of the wiki page '/API/Authentication' from the Documentation wiki"

Design

Each tool handles a focused Azure DevOps task. The server provides a thin layer over the REST APIs, while the AI agent handles higher-level reasoning.

Remote MCP Server (Recommended)

For complete instructions, see the Remote MCP Server onboarding documentation.

The remote server will eventually replace the local server. The local server remains supported, but new development will focus on the remote server. Existing local server users should begin planning their migration.

If you encounter issues with tools, need support, or have a feature request, you can report an issue using the Remote MCP Server issue template. During the preview period, we will track Remote MCP Server issues through this repository.

Quick Start

Create .vscode/mcp.json in your project and add this configuration. Replace {organization} with your Azure DevOps organization name.

{
  "servers": {
    "ado-remote-mcp": {
      "url": "https://mcp.dev.azure.com/{organization}",
      "type": "http"
    }
  },
  "inputs": []
}

See the remote server configuration documentation for more options.

After saving .vscode/mcp.json, start the server from the MCP view in VS Code, then run a prompt like List ADO projects.

Supported Tools

See the Available Tools documentation for the complete list of available remote tools.

For the complete list of local tools, see TOOLSET.md.

Local MCP Server Installation (Optional)

[!IMPORTANT] Start with the Remote MCP Server first. Use the local MCP Server only if your scenario specifically requires a local stdio setup.

These steps use Visual Studio Code and GitHub Copilot. For other supported clients, including Visual Studio 2022, Codex, Claude Code, Cursor, OpenCode, and Kilo Code, see the getting started guide.

Prerequisites

  1. Install VS Code or VS Code Insiders.
  2. Install Node.js 20 or later.
  3. Open your project in VS Code.

Installation

Install from npm

  1. Create .vscode/mcp.json in your project.
  2. Add this configuration:
{
  "inputs": [
    {
      "id": "ado_org",
      "type": "promptString",
      "description": "Azure DevOps organization name  (e.g. 'contoso')"
    }
  ],
  "servers": {
    "ado": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@azure-devops/mcp", "${input:ado_org}"]
    }
  }
}
  1. Save the file, then start the ado server from the MCP view in VS Code.
  2. Open GitHub Copilot Chat and switch to Agent mode.
  3. Select the Azure DevOps tools, then try a prompt such as List ADO projects.
  4. When prompted, sign in with a Microsoft account that has access to the selected Azure DevOps organization.

To use nightly builds, replace @azure-devops/mcp with @azure-devops/mcp@next in the configuration.

For better tool selection, add .github/copilot-instructions.md to your project with this instruction:

This project uses Azure DevOps. Always check whether the Azure DevOps MCP server has a tool relevant to the user's request.

Using Domains (Local Server)

The local server includes many tools. Domains let you load only the tool groups you need, which keeps the tool list manageable and helps clients with tool limits. Available domains are core, work, work-items, search, test-plans, repositories, wiki, pipelines, and advanced-security.

Add -d followed by the domains to the server arguments. For example, this configuration loads only work item-related tools:

{
  "inputs": [
    {
      "id": "ado_org",
      "type": "promptString",
      "description": "Azure DevOps organization name  (e.g. 'contoso')"
    }
  ],
  "servers": {
    "ado_with_filtered_domains": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@azure-devops/mcp", "${input:ado_org}", "-d", "core", "work", "work-items"]
    }
  }
}

Always include core so the agent can retrieve project information.

If you omit -d, the server loads all domains.

Project and Team Defaults (Local Server)

Set default Azure DevOps project and team values in .vscode/mcp.json so tools can skip selection prompts.

Example .vscode/mcp.json

{
  "servers": {
    "ado": {
      "type": "stdio",
      "command": "npx",
      "args": ["-y", "@azure-devops/mcp", "myorg", "--authentication", "azcli"],
      "env": {
        "ado_mcp_project": "Contoso",
        "ado_mcp_team": "Fabrikam Team"
      }
    }
  }
}

Troubleshooting

See the Troubleshooting guide for help with common issues and logging.

Examples

See the examples for sample prompts.

Frequently Asked Questions

For answers to common questions about the Azure DevOps MCP Server, see the Frequently Asked Questions.

Contributing

We welcome contributions. During preview, file issues for bugs, enhancements, or documentation improvements.

See our Contributions Guide for:

  • Development setup
  • Adding new tools
  • Code style and testing
  • Pull request process

Read the Contributions Guide before creating a pull request.

Code of Conduct

This project follows the Microsoft Open Source Code of Conduct. For questions, see the FAQ or contact open@microsoft.com.

Hall of Fame

Thanks to all contributors who make this project awesome! ❤️

Contributors

Generated with contrib.rocks

License

Licensed under the MIT License.


Trademarks: This project may include trademarks or logos for Microsoft or third parties. Use of Microsoft trademarks or logos must follow Microsoft’s Trademark & Brand Guidelines. Third-party trademarks are subject to their respective policies.

<!-- version: 2023-04-07 [Do not delete this line, it is used for analytics that drive template improvements] -->

Related MCP servers

DBdbt-plan logo

dbt-plan

Active

Predicts the DDL a dbt change will execute, before you run it. Reads files, not the warehouse.

2
Python
Apache-2.0
View repository →
FRFreshContext logo

Context integrity for AI agents: evaluate freshness, confidence, and provenance before reasoning.

9
TypeScript
MIT
View repository →

An MCP server to send personalised direct mail.

View repository →

Let AI agents create, discover, and track tokens across chains via Printr.

3
TypeScript
View repository →
SISignet MCP Tools logo

Cryptographic signing and verification for AI agent tool calls — tamper-evident receipts, offline-verifiable.

37
Rust
Apache-2.0
View repository →

Real-time status for 75+ AI services (OpenAI, Anthropic, Cursor). No auth, CORS-enabled.

0
TypeScript
MIT
View repository →