mcpField
A
Azure DevOps MCP Server

Azure DevOps MCP Server

Local
github.com/aymenfurterCloud & Infra1Updated 68w ago
Repository

About Azure DevOps MCP Server

Azure DevOps MCP Server is a sample server for managing Azure DevOps work items. It supports searching, creating, and updating items, and retrieving their states.

Key features

  1. 01Search work items
  2. 02Create work items
  3. 03Update work items
  4. 04Get work item states
  5. 05Test with a simple CLI

Use cases

  1. 01Find work items in an Azure DevOps project
  2. 02Create a work item
  3. 03Update an existing work item
  4. 04Check work item states

MCP support

Exposes Azure DevOps work item search, creation, updates, and state retrieval to MCP clients.

#ado-mcp-server#azure-devops#work-item-management

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "ado-mcp-server-python": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "build"
      ]
    }
  }
}
Run commanddocker run -i --rm build

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
ocibuild

Tools

No tool list yet

Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.

Details

From the project README

Important


Please consider using the official MCP server:
https://github.com/microsoft/azure-devops-mcp

Azure DevOps MCP Server

This is a Model Context Protocol (MCP) server for Azure DevOps that provides work item management capabilities.

Prerequisites

  • Docker
  • Azure DevOps Personal Access Token (PAT) with appropriate permissions
  • Azure DevOps Organization and Project details

Quick Start

  1. Build the Docker image:
docker build -t ado-mcp-server .
  1. Run the server with environment variables:
docker run -i --rm \
  -e ADO_PERSONAL_ACCESS_TOKEN="your_pat_here" \
  -e ADO_ORGANIZATION_URL="https://dev.azure.com/your_org" \
  -e ADO_PROJECT_NAME="your_project" \
  ado-mcp-server

Configuration

The server requires the following environment variables:

  • ADO_PERSONAL_ACCESS_TOKEN: Your Azure DevOps Personal Access Token
  • ADO_ORGANIZATION_URL: Your Azure DevOps organization URL
  • ADO_PROJECT_NAME: Your Azure DevOps project name

VS Code Integration

Add this configuration to your VS Code settings to integrate with the MCP server:

{
    "inputs": [
      {
        "type": "promptString",
        "id": "ado_pat",
        "description": "Azure DevOps Personal Access Token",
        "password": true
      },
      {
        "type": "promptString",
        "id": "ado_org",
        "description": "Azure DevOps Organization URL"
      },
      {
        "type": "promptString",
        "id": "ado_project",
        "description": "Azure DevOps Project Name"
      }
    ],
    "servers": {
      "azuredevops": {
        "command": "docker",
        "args": [
          "run",
          "-i",
          "--rm",
          "-e",
          "ADO_PERSONAL_ACCESS_TOKEN",
          "-e",
          "ADO_ORGANIZATION_URL",
          "-e",
          "ADO_PROJECT_NAME",
          "ado-mcp-server"
        ],
        "env": {
          "ADO_PERSONAL_ACCESS_TOKEN": "${input:ado_pat}",
          "ADO_ORGANIZATION_URL": "${input:ado_org}",
          "ADO_PROJECT_NAME": "${input:ado_project}"
        }
      }
    }
}

Features

  • Search work items
  • Create new work items
  • Update existing work items
  • Get work item states
  • Simple command-line interface for testing

Development

To build and run locally for development:

  1. Clone the repository
  2. Build the Docker image: docker build -t ado-mcp-server .
  3. Run the server with your environment variables

Testing

Run the tests using:

docker run -i --rm \
  -e ADO_PERSONAL_ACCESS_TOKEN="your_pat_here" \
  -e ADO_ORGANIZATION_URL="https://dev.azure.com/your_org" \
  -e ADO_PROJECT_NAME="your_project" \
  ado-mcp-server python -m pytest

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.