mcp-for-azure-devops-boards
A Model Context Protocol (MCP) server for interacting with Azure DevOps Boards and Work Items, written in Rust.
claude mcp add --transport stdio danielealbano-mcp-for-azure-devops-boards path/to/mcp-for-azure-devops-boards \ --env AZURE_CLI_AUTH_METHOD="default (uses az login) or credentials as configured"
How to use
This MCP server provides a bridge to Azure DevOps Boards and Work Items. It exposes a set of tools that allow you to discover organizations and projects, manage work items, and browse boards and teams. Tools follow a naming convention like azdo_<verb>_<resource> (for example azdo_list_projects or azdo_get_work_item) and are designed to be consumed by MCP clients such as Claude Desktop or Cursor. The server supports both standard discovery (organizations and projects) and full work item operations (create, update, query, and comments), plus board and team related queries. To use, start the server in stdio mode or run it as an HTTP server, then configure your MCP client to point at the server so you can invoke the tools with the required parameters. The output is optimized JSON suitable for large language model consumption, helping reduce token usage while preserving essential data.
How to install
Prerequisites:
- Azure CLI installed and authenticated (az login).
- Rust toolchain (for building from source) or access to the prebuilt binary via Homebrew or Scoop.
Option A: Install via Homebrew (macOS)
- Tap the MCP tools repository and install: brew tap danielealbano/mcp-tools brew install mcp-for-azure-devops-boards
- The binary will be available at /opt/homebrew/bin/mcp-for-azure-devops-boards.
Option B: Install via Scoop (Windows)
- Install the MCP tools bucket and then install the binary: scoop bucket add mcp-tools https://github.com/danielealbano/scoop-mcp-tools scoop install mcp-for-azure-devops-boards
- The binary will be located under your Scoop apps directory.
Option C: Build from source (Rust)
- Install Rust from https://rust-lang.org.
- Clone the repository: git clone https://github.com/danielealbano/mcp-for-azure-devops-boards.git
- Build the project: cd mcp-for-azure-devops-boards cargo build --release
- The binary will be available at: target/release/mcp-for-azure-devops-boards
What to run:
- In stdio mode (default): path/to/mcp-for-azure-devops-boards
- In HTTP server mode (SSE): path/to/mcp-for-azure-devops-boards --server --port 3000
Configuration for MCP clients:
- Claude Desktop example (claude_desktop_config.json): { "mcpServers": { "azure-devops-boards": { "command": "path/to/mcp-for-azure-devops-boards" } } }
Additional notes
Notes and tips:
- Ensure you run az login before using the tools, as authentication relies on the Azure CLI credentials.
- When running in HTTP server mode, the server binds to 0.0.0.0, so ensure appropriate network/firewall rules are in place.
- The toolset is under active development; tool names and parameters may change. Refer to the latest release notes for updates.
- If you encounter issues with authentication, verify that the Azure CLI is installed and reachable from the environment running the MCP server.
- For debugging, start the server in stdio mode and invoke tools directly, capturing the JSON output for inspection.
Related MCP Servers
hyper
📦️ A fast, secure MCP server that extends its capabilities through WebAssembly plugins.
openai -agent-dotnet
Sample to create an AI Agent using OpenAI models with any MCP server running on Azure Container Apps
drawio
A Model Context Protocol (MCP) server for programmatic diagram generation using Draw.io (Diagrams.net). This server generates Draw.io XML directly — no browser extension or Draw.io instance required.
gemini-cli
> Gemini Rust Suite 🦀: A powerful, modular Rust toolkit for interacting with Google Gemini. Features a feature-rich CLI, persistent semantic memory (LanceDB), and extensible tool integration via the Model Context Protocol (MCP).
mcp
✨ MCP Server for Effortless Dependency Updates
ultrafast
High-performance, ergonomic Model Context Protocol (MCP) implementation in Rust