azdo-mcp
Documentation
Azure DevOps MCP Server
An MCP (Model Context Protocol) server that provides integration with Azure DevOps, allowing AI assistants to interact with Azure DevOps work items, pull requests, and wikis.
Features
- Work Items Management (create, list, get)
- Pull Request Operations (create, list, get, comment, diff)
- Wiki Page Management (create, edit)
Setup
1. Install dependencies:
npm install2. Configure environment variables (create a .env file):
AZURE_DEVOPS_ORG_URL=https://dev.azure.com/your-org
AZURE_DEVOPS_PAT=your-personal-access-token
AZURE_DEVOPS_PROJECT=default-project
AZURE_DEVOPS_REPOSITORY=default-repo3. Build the server:
npm run buildInstallation
Add the server configuration to your MCP settings:
For VSCode
On macOS/Linux
Add to `~/.vscode/cline_mcp_settings.json` or the Cursor/Roo equivalent:
{
"mcpServers": {
"azure-devops": {
"command": "node",
"args": ["/path/to/azure-devops-mcp/build/index.js"],
"env": {
"AZURE_DEVOPS_ORG_URL": "your-org-url",
"AZURE_DEVOPS_PAT": "your-pat",
"AZURE_DEVOPS_PROJECT": "your-project",
"AZURE_DEVOPS_REPOSITORY": "your-repo"
},
"disabled": false,
"autoApprove": []
}
}
}On Windows
Add to `%USERPROFILE%\.vscode\cline_mcp_settings.json` or the Cursor/Roo equivalent:
{
"mcpServers": {
"azure-devops": {
"command": "node",
"args": ["C:/path/to/azure-devops-mcp/build/index.js"],
"env": {
"AZURE_DEVOPS_ORG_URL": "your-org-url",
"AZURE_DEVOPS_PAT": "your-pat",
"AZURE_DEVOPS_PROJECT": "your-project",
"AZURE_DEVOPS_REPOSITORY": "your-repo"
},
"disabled": false,
"autoApprove": []
}
}
}Available Tools
Work Items
list_work_items
Lists work items in a project.
{
"project": string, // Required
"types"?: string[], // Optional: Filter by work item types
"states"?: string[], // Optional: Filter by states
"assignedTo"?: string // Optional: Filter by assigned user
}get_work_item
Get details of a specific work item.
{
"project": string, // Required
"id": number // Required: Work item ID
}create_work_item
Create a new work item.
{
"project": string, // Required
"type": string, // Required: e.g., "Task", "Bug"
"title": string, // Required
"description"?: string, // Optional
"assignedTo"?: string // Optional
}Pull Requests
list_pull_requests
List pull requests in a repository.
{
"status"?: "active" | "completed" | "abandoned" // Optional
}get_pull_request
Get details of a specific pull request.
{
"pullRequestId": number // Required
}create_pull_request
Create a new pull request.
{
"title": string, // Required
"description": string, // Required
"sourceBranch": string, // Required
"targetBranch": string, // Required
"reviewers"?: string[] // Optional: Array of reviewer email addresses
}create_pull_request_comment
Add a comment to a pull request.
{
"pullRequestId": number, // Required
"content": string, // Required
"threadId"?: number, // Optional: For replies
"filePath"?: string, // Optional: For file comments
"lineNumber"?: number, // Optional: For line comments
"status"?: "active"|"fixed"|"pending"|"wontfix"|"closed" // Optional: Thread status
}get_pull_request_diff
Get the diff for a pull request.
{
"pullRequestId": number, // Required
"filePath"?: string, // Optional: Specific file to get diff for
"iterationId"?: number // Optional: Specific iteration to get diff for
}Wiki
create_wiki_page
Create a new wiki page.
{
"project": string, // Required
"wiki": string, // Required
"path": string, // Required
"content": string // Required
}edit_wiki_page
Edit an existing wiki page.
{
"project": string, // Required
"wiki": string, // Required
"path": string, // Required
"content": string, // Required
"etag": string // Required: For concurrency control
}Development
Run in development mode with environment variables:
npm run devNote
Unless explicitly specified in the tool arguments, the `project` and `repository` parameters will use default values from your environment configuration.
Frequently asked questions
What is azdo-mcp?
azdo-mcp is a Model Context Protocol (MCP) server listed in the TrackMCP directory.
How do I install azdo-mcp?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is azdo-mcp open source?
Yes — it is hosted on GitHub at https://github.com/mmruesch12/azdo-mcp and has 3 stars.
Related MCP tools
Connect an MCP Client that only supports local (stdio) servers to a Remote MCP Server, with auth support: TypeScript-based implementation.
- Discover available MCP servers from our curated registry TypeScript-based implementation.
🍒 Cherry Studio is a desktop client that supports for multiple LLM providers. Built for the Model Context Protocol to enhance AI capabilities.
Enhanced ChatGPT Clone: Features Agents, MCP, DeepSeek, Anthropic, AWS, OpenAI, Responses API, Azure, Groq, o1, GPT-5, Mistral, OpenRouter, Vertex AI, Gemini...
FastGPT is a knowledge-based platform built on the LLMs, offers a comprehensive suite of out-of-the-box capabilities such as data processing, RAG retrieval, ...
Composio equips your AI agents & LLMs with 100+ high-quality integrations via function calling for the Model Context Protocol. Enhance AI assistants with powerf
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP