MCP Server for Azure DevOps
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@MCP Server for Azure DevOps list recent pull requests in the e-commerce project"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP Server for Azure DevOps
A comprehensive Model Context Protocol (MCP) server that provides AI assistants with full access to Azure DevOps services.
π Quick Install
# Clone the repository
git clone https://github.com/sepal7/mcp-ado.git
cd mcp-ado
# Install dependencies
npm install
# Create .env file
cp .env.example .env
# Edit .env with your Azure DevOps credentials
# Test the connection
npm run test-connectionThen configure your IDE (see Installation section below).
Related MCP server: Azure DevOps MCP Server
π¦ Available Tools (25+)
Wiki (3 tools)
get_wiki_page- Retrieve wiki page by ID or pathlist_wiki_pages- List all wiki pages in a projectsearch_wiki_pages- Search wiki pages by content or title
Repositories (5 tools)
list_repos- List all repositoriesget_repo- Get repository detailsget_repo_file- Get file content from repositorylist_repo_branches- List branches in a repositorysearch_code- Search code across repositories
Work Items (5 tools)
get_work_item- Get work item by IDget_work_items- Get multiple work itemsquery_work_items- Query work items using WIQLcreate_work_item- Create new work itemupdate_work_item- Update existing work item
Pull Requests (3 tools)
list_pull_requests- List pull requestsget_pull_request- Get pull request detailsget_pr_comments- Get PR review comments
Builds & Pipelines (4 tools)
list_builds- List recent buildsget_build- Get build detailslist_pipelines- List pipelinesget_pipeline_run- Get pipeline run details
Releases (2 tools)
list_releases- List releasesget_release- Get release details
Test Plans (2 tools)
list_test_plans- List test plansget_test_plan- Get test plan details
Generic (1 tool)
ado_api_call- Make any Azure DevOps REST API call
π Comparison with Similar Projects
Feature | This Project | Other MCP ADO Servers |
Total Tools | 25+ | 5-15 |
Wiki Support | β Yes (3 tools) | β Limited/None |
Multi-Project | β Built-in | β Single project |
WIQL Queries | β Yes | β No |
Generic API Tool | β Yes | β No |
Helper Scripts | β PAT management | β No |
Documentation | β Comprehensive | β οΈ Basic |
Key Differentiators:
Most comprehensive tool coverage (25+ vs 5-15)
Multi-project support without reconfiguration
Advanced features (WIQL queries, generic API tool)
Better developer experience (helper scripts, comprehensive docs)
β¨ Features
25+ MCP Tools covering all major Azure DevOps services
Multi-Project Support - Access any project in your organization without reconfiguration
WIQL Query Support - Advanced work item querying using Work Item Query Language
Generic API Tool - Make any Azure DevOps REST API call for future-proof extensibility
Helper Scripts - Automated PAT token management and connection testing
Comprehensive Documentation - Step-by-step guides for Cursor, VS Code, and deployment
π Quick Start
Prerequisites
Node.js 18+ installed
Azure DevOps Personal Access Token (PAT) with appropriate permissions
VS Code with GitHub Copilot Chat extension, VS Code Insiders, or Cursor IDE
Installation
π¦ Install from Source
# Clone the repository
git clone https://github.com/sepal7/mcp-ado.git
cd mcp-ado
# Install dependencies
npm install
# Create .env file
cp .env.example .env
# Edit .env with your values:
# AZURE_DEVOPS_ORG=YourOrganization
# AZURE_DEVOPS_PROJECT=YourProject
# AZURE_DEVOPS_PAT=your_pat_token_here
# Test the connection
npm run test-connectionThen configure manually (see detailed guides below).
For detailed setup instructions, see:
π― Usage Examples
Once configured, use natural language to interact with Azure DevOps:
Default Project:
"List all repositories"
"Get work item #12345"
"Show me pull requests"
Other Projects:
"List repositories in the [ProjectName] project"
"Get work items from the [ProjectName] project"
All tools support an optional project parameter to access any project in your organization.
βοΈ Configuration
Environment Variables
Variable | Required | Description |
| Yes | Your Azure DevOps organization name |
| Yes | Default project name |
| Yes | Personal Access Token |
| No | Optional telemetry connection string |
Multi-Project Support
All MCP tools support an optional project parameter. When using Cursor or VS Code, mention the project name in your request:
"List repositories in the [ProjectName] project"The AI assistant automatically extracts the project name and passes it to the MCP tool.
π Project Structure
mcp-ado/
βββ server.js # Main MCP server implementation
βββ package.json # Node.js dependencies and scripts
βββ .env.example # Environment variables template
βββ README.md # This file
β
βββ docs/ # Documentation
β βββ 01-SETUP.md # General setup guide
β βββ 02-CURSOR-SETUP.md # Cursor IDE setup
β βββ 03-VSCODE-SETUP.md # VS Code setup
β βββ 04-PAT-MANAGEMENT.md # PAT token management
β βββ 05-RESTART-SERVER.md # How to restart server
β βββ 07-CHANGELOG.md # Version history
β βββ 08-ONPREMISE-WINDOWS-IIS.md # On-premise deployment
β
βββ scripts/ # Utility scripts
β βββ test.js # Basic server tests
β βββ test-connection.js # Azure DevOps connection tester
β βββ update-pat.ps1 # PAT token updater script
β
βββ azure/ # Azure deployment files
βββ README.md # Azure deployment guide
βββ Dockerfile # Container image definition
βββ azure-deploy.bicep # Infrastructure as codeπ Documentation
Setup Guide - General setup and configuration
Cursor Setup - Cursor IDE configuration
VS Code Setup - VS Code + GitHub Copilot setup
PAT Management - Managing Personal Access Tokens
Changelog - Version history
π€ Contributing
Contributions are welcome! Please feel free to submit a Pull Request.
π License
MIT License - see LICENSE file for details
π Credits
Enhanced with features from Microsoft's official Azure DevOps MCP Server
Made with β€οΈ for the MCP community
Available Tools
25 toolsado_api_callC
Make a generic Azure DevOps REST API call
Inputs: endpoint (required), project, method, params, +1 more.
create_work_itemC
Create a new work item
Inputs: type (required), title (required), project, description, +1 more.
get_buildC
Get build details by ID
Inputs: buildId (required), project.
get_pipeline_runC
Get pipeline run details
Inputs: pipelineId (required), runId (required), project.
get_pr_commentsC
Get pull request review comments
Inputs: repo (required), pullRequestId (required), project, $top.
get_pull_requestC
Get pull request details
Inputs: repo (required), pullRequestId (required), project, includeCommits, +1 more.
get_releaseC
Get release details
Inputs: releaseId (required), project.
get_repoB
Get repository details by name
Inputs: repo (required), project.
get_repo_fileC
Get file content from a repository
Inputs: repo (required), path (required), project, branch, +1 more.
get_test_planC
Get test plan details
Inputs: planId (required), project.
get_wiki_pageC
Retrieve a specific Azure DevOps wiki page by ID or path
Inputs: project, wiki, pageId, path, +1 more.
get_work_itemC
Get work item details by ID
Inputs: workItemId (required), project, fields, expand.
get_work_itemsC
Get multiple work items by IDs
Inputs: workItemIds (required), project, fields, expand.
list_buildsC
List recent builds
Inputs: project, definitionId, status, result, +1 more.
list_pipelinesC
List pipelines in the project
Inputs: project, $top.
list_pull_requestsC
List pull requests in a repository
Inputs: repo (required), project, status, $top.
list_releasesD
List releases
Inputs: project, definitionId, status, $top.
list_repo_branchesC
List branches in a repository
Inputs: repo (required), project, includeLinks.
list_reposC
List all repositories in the project
Inputs: project, includeLinks.
list_test_plansC
List test plans
Inputs: project, $top.
list_wiki_pagesC
List all pages in a wiki
Inputs: project, wiki, recursive.
query_work_itemsC
Query work items using WIQL (Work Item Query Language)
Inputs: wiql (required), project, $top.
search_codeC
Search code across repositories
Inputs: searchText (required), project, repo, $top.
search_wiki_pagesC
Search wiki pages by content or title
Inputs: query (required), project, wiki.
update_work_itemC
Update an existing work item
Inputs: workItemId (required), project, fields, links, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
TDQS
Scored across 25 tools
Most tools have distinct purposes targeting specific Azure DevOps resources (e.g., work items, builds, pipelines, repos, wikis), with clear separation between get/list/query/search operations. However, some potential confusion exists between get_work_item and get_work_items (both retrieve work items, differing only in single vs. multiple items), and between list_wiki_pages and search_wiki_pages (both operate on wiki pages with overlapping retrieval functions).
Tool names follow a highly consistent verb_noun pattern throughout, using snake_case uniformly. Verbs are standardized (get, list, create, update, query, search) paired with specific nouns (work_item, build, pipeline, repo, wiki_page, etc.), making the naming predictable and easy to understand. No deviations or mixed conventions are present.
With 25 tools, the count is borderline high for a single server, potentially overwhelming for agents. While Azure DevOps is a broad platform, the toolset covers multiple domains (work items, CI/CD, repos, wikis, testing), which might be better split into focused servers. However, the tools are well-organized within this scope, avoiding extreme bloat.
The toolset provides comprehensive coverage for core Azure DevOps operations, including CRUD for work items (create, get, update, query), listing and retrieving builds, pipelines, releases, repos, and wikis, and search capabilities for code and wiki pages. Minor gaps include missing update/delete operations for non-work-item resources (e.g., no update_build or delete_repo) and limited pull request management (only get and list, no create or merge), but agents can work around these with the generic ado_api_call.
Maintenance
Related MCP Connectors
Your org's AI agents, tasks, runs, search, and brain files as MCP tools and resources.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Governed app access for AI agents: 1,000+ apps & 12,000+ tools via Code Mode MCP.
AgentPMT is the AI agent marketplace that turns any MCP-compatible AI assistant into an autonomous employee. Connect once and your agents gain access to a growing ecosystem of tools, workflows, and skills spanning communication, data analytics, development, file management, search, and more. AgentPMT dynamically discovers and orchestrates tools from across the MCP ecosystem, so your agents can independently find the right tool for any task without manual configuration.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to interact with Azure DevOps APIs for managing projects, work items, repositories, pull requests, and pipelines through natural language.29 npm1MIT
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to interact with Azure DevOps APIs for managing projects, work items, repositories, pull requests, pipelines, and more through natural language.5,492 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to interact with Azure DevOps through an MCP server with 34 tools for PRs, work items, repos, and branches, optimized for token efficiency and agent-first workflows.4 npmMIT
- AlicenseCqualityDmaintenanceEnables AI agents to interact with Azure DevOps through natural language, supporting work items, pull requests, sprints, boards, teams, repositories, and wiki pages.30MIT