playbooks
Learn Cursor Rules Windsurf Rules MCPs Modes
Log in

Azure DevOps MCP server

Integrates with Azure DevOps to manage work items, wikis, and project tasks, enabling AI-driven project management and cross-service automation.
Back to servers
Setup instructions
Provider
Daniel Owen van Dommelen
Release date
Feb 17, 2025
Language
Go
Stats
2 stars
View on GitHub

The MCP Server DevOps Bridge acts as a powerful connector between your essential DevOps tools and AI assistants like Claude. It provides a unified natural language interface to work with Azure DevOps, GitHub, Slack, and browser automation while enabling autonomous AI agents to handle tasks on your behalf.

Installation Requirements

Before installing the MCP Server DevOps Bridge, ensure you have:

  • Go 1.23.4 or later
  • Docker (required for agent system)
  • Access tokens for your platforms:
    • Azure DevOps PAT
    • GitHub PAT (optional)
    • Slack Bot Token (optional)
    • OpenAI API Key (for agents)

Installation Steps

Building from Source

git clone https://github.com/theapemachine/mcp-server-devops-bridge
cd mcp-server-devops-bridge
go build

Configuration

Configure your environment by setting the necessary environment variables:

export AZURE_DEVOPS_ORG="your-org"
export AZDO_PAT="your-pat-token"
export AZURE_DEVOPS_PROJECT="your-project"

# Optional integrations
export GITHUB_PAT="your-github-pat"
export SLACK_BOT_TOKEN="your-slack-token"
export DEFAULT_SLACK_CHANNEL="some-slack-channel-id"

# AI and Memory integrations
export OPENAI_API_KEY="your-api-key"
export QDRANT_URL="http://localhost:6333"
export QDRANT_API_KEY="your-qdrant-api-key"
export NEO4J_URL="http://localhost:7474"
export NEO4J_USER="neo4j"
export NEO4J_PASSWORD="your-neo4j-password"

Claude Configuration

Add the MCP Server to Claude's configuration:

{
  "mcpServers": {
    "devops-bridge": {
      "command": "/full/path/to/mcp-server-devops-bridge/mcp-server-devops-bridge",
      "args": [],
      "env": {
        "AZURE_DEVOPS_ORG": "organization",
        "AZDO_PAT": "personal_access_token",
        "AZURE_DEVOPS_PROJECT": "project",
        "SLACK_DEFAULT_CHANNEL": "channel_id",
        "SLACK_BOT_TOKEN": "bot_token",
        "GITHUB_PAT": "personal_access_token",
        "OPENAI_API_KEY": "openaikey",
        "QDRANT_URL": "http://localhost:6333",
        "QDRANT_API_KEY": "yourkey",
        "NEO4J_URL": "yourneo4jinstance",
        "NEO4J_USER": "neo4j",
        "NEO4J_PASSWORD": "neo4jpassword"
      }
    }
  }
}

Alternative Setup with start.sh

If you can't modify environment variables directly, create a start.sh script:

#!/bin/bash

# Azure DevOps Configuration
export AZURE_DEVOPS_ORG="YOUR ORG"
export AZDO_PAT="YOUR PAT"
export AZURE_DEVOPS_PROJECT="YOUR PROJECT"

# GitHub Configuration
export GITHUB_PAT="YOUR PAT"

# Slack Configuration
export SLACK_BOT_TOKEN="YOUR TOKEN"
export DEFAULT_SLACK_CHANNEL="YOUR CHANNEL ID"

# OpenAI Configuration
export OPENAI_API_KEY="YOUR API KEY"

# Qdrant Configuration
export QDRANT_URL="http://localhost:6333"
export QDRANT_API_KEY="your-qdrant-api-key"

# Neo4j Configuration
export NEO4J_URL="http://localhost:7474"
export NEO4J_USER="neo4j"
export NEO4J_PASSWORD="your-neo4j-password"

# Email Configuration (if using email features)
export EMAIL_INBOX_WEBHOOK_URL="YOUR WEBHOOK URL"
export EMAIL_SEARCH_WEBHOOK_URL="YOUR WEBHOOK URL"
export EMAIL_REPLY_WEBHOOK_URL="YOUR WEBHOOK URL"

/path/to/mcp-server-devops-bridge/mcp-server-devops-bridge

Make the script executable with chmod +x start.sh

Usage Examples

Cross-Platform Task Management

"Create a user story for the new authentication feature, link it to the existing GitHub PR #123, and notify the team in Slack"

Code Review Workflow

"Find all work items related to authentication, show their linked PRs, and summarize recent code review comments"

Status Reporting

"Generate a sprint report including:
- Work item status from Azure Boards
- PR review status from GitHub
- Team discussions from Slack"

Documentation Management

"Update the wiki page for authentication and link it to relevant work items and PRs"

Autonomous Agent Workflow

"Create an agent to monitor our authentication PRs, summarize code changes, and post daily updates to Slack"

Key Features

Azure DevOps Integration

  • Work item management (create, update, query)
  • Wiki management
  • Sprint tracking

GitHub Integration

  • Pull request management
  • Code search

Slack Integration

  • Message formatting and posting
  • Message search
  • Threaded replies

Browser Automation

  • Web navigation
  • Form filling
  • Data extraction

Agent System

The MCP Server includes a powerful agent system that enables Claude to create its own long-running agents that can:

  • Execute tasks autonomously in secure Docker containers
  • Communicate with other agents
  • Access system tools and commands
  • Process tasks in the background

Creating and Managing Agents

To create a new agent:

Tool: agent
Arguments: {"id": "researcher", "system_prompt": "You are a research agent...", "task": "Find information about climate change"}

To subscribe an agent to a topic:

Tool: subscribe_agent
Arguments: {"agent_id": "writer", "topic": "research_results"}

To send a message to a specific topic:

Tool: send_agent_message
Arguments: {"topic": "research_results", "content": "Here is the information I found..."}

To send a direct command to an agent:

Tool: send_command
Arguments: {"agent_id": "writer", "command": "Summarize the research in 3 paragraphs"}

Memory System

The bridge implements an intelligent memory system using:

  • Vector Storage (Qdrant) for semantic search
  • Graph Database (Neo4j) for entity relationships

This enables AI assistants to automatically:

  • Retrieve relevant memories before responding
  • Store important context from interactions for future reference

The memory system is configured through the same environment variables used for general setup.

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "devops-bridge" '{"command":"/full/path/to/mcp-server-devops-bridge/mcp-server-devops-bridge","args":[],"env":{"AZURE_DEVOPS_ORG":"organization","AZDO_PAT":"personal_access_token","AZURE_DEVOPS_PROJECT":"project","SLACK_DEFAULT_CHANNEL":"channel_id","SLACK_BOT_TOKEN":"bot_token","GITHUB_PAT":"personal_access_token","OPENAI_API_KEY":"openaikey","QDRANT_URL":"http://localhost:6333","QDRANT_API_KEY":"yourkey","NEO4J_URL":"yourneo4jinstance","NEO4J_USER":"neo4j","NEO4J_PASSWORD":"neo4jpassword"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "devops-bridge": {
            "command": "/full/path/to/mcp-server-devops-bridge/mcp-server-devops-bridge",
            "args": [],
            "env": {
                "AZURE_DEVOPS_ORG": "organization",
                "AZDO_PAT": "personal_access_token",
                "AZURE_DEVOPS_PROJECT": "project",
                "SLACK_DEFAULT_CHANNEL": "channel_id",
                "SLACK_BOT_TOKEN": "bot_token",
                "GITHUB_PAT": "personal_access_token",
                "OPENAI_API_KEY": "openaikey",
                "QDRANT_URL": "http://localhost:6333",
                "QDRANT_API_KEY": "yourkey",
                "NEO4J_URL": "yourneo4jinstance",
                "NEO4J_USER": "neo4j",
                "NEO4J_PASSWORD": "neo4jpassword"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "devops-bridge": {
            "command": "/full/path/to/mcp-server-devops-bridge/mcp-server-devops-bridge",
            "args": [],
            "env": {
                "AZURE_DEVOPS_ORG": "organization",
                "AZDO_PAT": "personal_access_token",
                "AZURE_DEVOPS_PROJECT": "project",
                "SLACK_DEFAULT_CHANNEL": "channel_id",
                "SLACK_BOT_TOKEN": "bot_token",
                "GITHUB_PAT": "personal_access_token",
                "OPENAI_API_KEY": "openaikey",
                "QDRANT_URL": "http://localhost:6333",
                "QDRANT_API_KEY": "yourkey",
                "NEO4J_URL": "yourneo4jinstance",
                "NEO4J_USER": "neo4j",
                "NEO4J_PASSWORD": "neo4jpassword"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later