The project was inspired by the mcp-atlassian server, which provides similar functionality for Jira and Confluence, though this MCP doesn't directly integrate with Atlassian services.
Enables read-only repository management including listing repositories, files, and retrieving file content from Azure DevOps Git repositories.
mcp-azure-devops
An open-source Model Context Protocol (MCP) server for seamless integration with Azure DevOps.
Mission
To create a robust, open-source Model Context Protocol (MCP) server that provides seamless integration with Azure DevOps. This server will empower AI agents to interact with Azure DevOps projects, managing work items, wikis, and repositories, thereby streamlining development workflows.
License
This project is licensed under the MIT License. See the LICENSE file for details.
Core Features
The MCP server will expose a set of tools to interact with Azure DevOps, categorized by area.
Implemented Features
Work Item Management (CRUD)
create_work_item
(supports Epic, User Story, Task, Bug, and work item linking)get_work_item
(by ID)update_work_item
(by ID, supports work item linking)delete_work_item
(by ID)search_work_items
(using WIQL - Work Item Query Language)
Wiki Management (CRUD)
create_wiki_page
get_wiki_page
(by path)update_wiki_page
(by path)delete_wiki_page
(by path)list_wiki_pages
get_wikis
create_wiki
Repository Management (Read-only)
list_repositories
list_files
(in a repository)get_file_content
Project Scoping
set_project_context
: A special tool to set the active project for subsequent commands.clear_project_context
: To revert to the organization-level scope.get_projects
: To list all projects in the organization.
Server Documentation
list_available_tools
: Lists all available tools.get_tool_documentation
: Gets the documentation for a specific tool.
Planned Features
- Repository Management (Write operations):
create_repository
create_pull_request
manage_branches
- Pipeline Management:
trigger_build
get_build_status
list_pipelines
Getting Started
This guide will walk you through setting up the mcp-azure-devops
server.
Prerequisites
- Python 3.10 or higher
pip
andvenv
for managing Python packages
Installation Steps
- Clone the Repository:
- Create and Activate a Virtual Environment:
It's highly recommended to use a virtual environment to manage the project's dependencies.
- Install Dependencies:
Install the project and its dependencies in editable mode.
Configuration
- Generate an Azure DevOps Personal Access Token (PAT):
- Navigate to your Azure DevOps organization.
- Go to User settings > Personal Access Tokens.
- Click + New Token.
- Give your token a name (e.g.,
mcp-server-token
). - Select the organization.
- Set the expiration date.
- For the scopes, you will need to grant the following permissions at a minimum:
- Work Items: Read & write
- Wiki: Read & write
- Code: Read
- Click Create and copy the token immediately. You will not be able to see it again.
- Configure the MCP Server in Cline:
- Open your
cline_mcp_settings.json
file. Note: The location of this file can vary. A common location on Windows is
C:\Users\<YourUsername>\AppData\Roaming\Code\User\globalStorage\saoudrizwan.claude-dev\settings\cline_mcp_settings.json
. If you can't find it, you can search your user's home directory for the file.- Add a new entry for the
mcp-azure-devops
server. The command should bemcp-azure-devops
.
Here is an example configuration. You must use the full, absolute path to the
mcp-azure-devops.exe
executable created inside your virtual environment.- Replace
your-organization
with your Azure DevOps organization name andyour-personal-access-token
with the PAT you generated.
- Open your
- Restart Cline: Restart your Cline application to load the new MCP server.
Acknowledgements
This project was inspired by the mcp-atlassian
server, which provides similar functionality for Jira and Confluence. You can find it here: https://github.com/pashpashpash/mcp-atlassian.
This server cannot be installed
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
An open-source server that enables AI agents to interact with Azure DevOps projects through the Model Context Protocol, providing tools for managing work items, wikis, and repositories to streamline development workflows.
Related MCP Servers
- AsecurityAlicenseAqualityThis server provides a convenient API for interacting with Azure DevOps services, enabling AI assistants and other tools to manage work items, code repositories, boards, sprints, and more. Built with the Model Context Protocol, it provides a standardized interface for communicating with Azure DevOpsLast updated -962843TypeScriptMIT License
- AsecurityAlicenseAqualityA Model Context Protocol server that enables AI assistants to interact with Azure DevOps resources including projects, work items, repositories, pull requests, branches, and pipelines through a standardized protocol.Last updated -15622279TypeScriptMIT License
- -securityFlicense-qualityA reference server implementation for the Model Context Protocol that enables AI assistants to interact with Azure DevOps resources and perform operations such as project management, work item tracking, repository operations, and code search programmatically.Last updated -7TypeScript
- AsecurityAlicenseAqualityA Model Context Protocol server that enables AI assistants to interact with Azure DevOps services, allowing users to query work items with plans to support creating/updating items, managing pipelines, handling pull requests, and administering sprints and branch policies.Last updated -971PythonMIT License