
azure-devops MCP Server
A TypeScript-based MCP server that implements a simple notes system, allowing users to create, access, and generate summaries of text notes.
README
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
- Install dependencies:
npm install
- 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-repo
- Build the server:
npm run build
Installation
Add the server configuration to your MCP settings:
For VSCode
Add to ~/.vscode/cline_mcp_settings.json
:
{
"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": []
}
}
}
For Claude Desktop
Add to:
- MacOS:
~/Library/Application Support/Claude/claude_desktop_config.json
- Windows:
%APPDATA%/Claude/claude_desktop_config.json
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 dev
Note
Unless explicitly specified in the tool arguments, the project
and repository
parameters will use default values from your environment configuration.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.