mcp-azure-devops
Health Warn
- License — License: MIT
- Description — Repository has a description
- Active repo — Last push 0 days ago
- Low visibility — Only 7 GitHub stars
Code Pass
- Code scan — Scanned 7 files during light audit, no dangerous patterns found
Permissions Pass
- Permissions — No dangerous permissions requested
This is a Model Context Protocol (MCP) server that allows AI assistants to interact with Azure DevOps. It enables querying and managing work items, git repositories, pull requests, and pipelines.
Security Assessment
Overall Risk: Medium. The tool inherently requires access to highly sensitive data—specifically your Azure DevOps Personal Access Token (PAT). No hardcoded secrets or dangerous execution patterns were found in the scanned code, and it does not request unnecessary system permissions. However, because it handles authentication credentials and interacts with internal developer infrastructure, it should be treated with care. Additionally, the README suggests downloading and running an automated PowerShell script directly from the internet, which is a common vector for supply-chain attacks. Always review such scripts thoroughly before executing them.
Quality Assessment
The project is actively maintained, with recent updates pushed within the last few days. It utilizes a continuous integration pipeline and is protected by a permissive MIT license. However, community trust and visibility are currently very low. With only 7 GitHub stars, the tool has not yet been widely adopted or extensively reviewed by the broader open-source community.
Verdict
Use with caution—the codebase is clean and maintained, but handling Personal Access Tokens requires strict security practices, and the project's low community adoption means it carries a higher inherent trust risk.
Azure DevOps MCP for querying repositories, pipelines, work items, and delivery metadata via HTTP
MCP Azure DevOps Server
A Model Context Protocol (MCP) server for Azure DevOps integration, enabling AI assistants to interact with Azure DevOps Work Items, Git Repositories, Pull Requests, and Pipelines.
Note: Flow metrics, WIP analysis, and other analytics features were removed. With
ActivatedDateandClosedDatenow exposed on all work item queries, Claude can derive cycle time, lead time, aging, and throughput directly from the data — no pre-built analytics tools needed.
Quick Start
Get up and running in 3 steps:
1. Clone and configure
git clone https://github.com/viamus/mcp-azure-devops.git
cd mcp-azure-devops
Option A — .env file (recommended for Docker):
cp .env.example .env
# Edit .env with your Azure DevOps credentials
Option B — appsettings.json (for .NET CLI):
Edit src/Viamus.Azure.Devops.Mcp.Server/appsettings.json with your Azure DevOps credentials:
{
"AzureDevOps": {
"OrganizationUrl": "https://dev.azure.com/your-organization",
"PersonalAccessToken": "your-personal-access-token",
"DefaultProject": "your-project-name"
}
}
Need a PAT? See Creating a Personal Access Token below.
2. Run the server
Option A - Docker (recommended):
docker compose up -d
# Server runs at http://localhost:8080 (use reverse proxy for HTTPS in production)
Option B - .NET CLI:
dotnet run --project src/Viamus.Azure.Devops.Mcp.Server
# Server runs at http://localhost:5000
3. Verify it's working
# Docker
curl http://localhost:8080/health
# .NET CLI
curl http://localhost:5000/health
You should see: Healthy
Automated Installation (Windows)
For Windows users, a PowerShell script is available that automates the entire setup process:
# Download and run the installer (as Administrator)
irm https://raw.githubusercontent.com/viamus/mcp-azure-devops/main/install-mcp-azure-devops.ps1 -OutFile install-mcp-azure-devops.ps1
.\install-mcp-azure-devops.ps1 `
-OrganizationUrl "https://dev.azure.com/your-organization" `
-PersonalAccessToken "your-pat-token" `
-DefaultProject "your-project-name" `
-ApiKey "your-secure-api-key" # Optional: enables API key authentication
The script will automatically:
- Install .NET 10 SDK (if not present)
- Install Node.js (if not present)
- Install Claude Code CLI (if not present)
- Clone the repository
- Configure your Azure DevOps credentials
- Register the MCP server with Claude Code (HTTPS transport)
After installation, start the server:
cd $env:USERPROFILE\mcp-azure-devops
dotnet run --project src/Viamus.Azure.Devops.Mcp.Server
About
This project implements an MCP server that exposes tools for querying and managing Work Items and Git Repositories in Azure DevOps. It can be used with any compatible MCP client, such as Claude Desktop, Claude Code, or other assistants that support the protocol.
Available Tools
Work Item Tools
| Tool | Description |
|---|---|
get_work_item |
Gets details of a specific work item by ID |
get_work_items |
Gets multiple work items by IDs (batch retrieval) |
query_work_items |
Queries work items using WIQL (Work Item Query Language) |
get_work_items_by_state |
Filters work items by state (Active, New, Closed, etc.) |
get_work_items_assigned_to |
Gets work items assigned to a specific user |
get_child_work_items |
Gets child work items of a parent work item |
get_recent_work_items |
Gets recently changed work items |
search_work_items |
Searches work items by title text |
add_work_item_comment |
Adds a comment to a specific work item |
create_work_item |
Creates a new work item (Bug, Task, User Story, etc.) with support for all standard fields, parent linking, and custom fields |
update_work_item |
Updates an existing work item. Only specified fields are changed; omitted fields remain unchanged |
Git Repository Tools
| Tool | Description |
|---|---|
get_repositories |
Lists all Git repositories in a project |
get_repository |
Gets details of a specific repository by name or ID |
get_branches |
Lists all branches in a repository |
get_repository_items |
Browses files and folders at a specific path in a repository |
get_file_content |
Gets the content of a specific file in a repository |
search_repository_files |
Searches for files by path pattern in a repository |
Pull Request Tools
| Tool | Description |
|---|---|
get_pull_requests |
Lists pull requests with optional filters (status, creator, reviewer, branches) |
get_pull_request |
Gets details of a specific pull request by ID within a repository |
get_pull_request_by_id |
Gets details of a pull request by ID only, searching across all repositories in the project |
get_pull_request_threads |
Gets comment threads for a pull request |
search_pull_requests |
Searches pull requests by text in title or description |
query_pull_requests |
Advanced query with multiple combined filters |
create_pull_request |
Creates a new pull request with title, description, source/target branches, draft flag, reviewers, and linked work items |
Pipeline/Build Tools
| Tool | Description |
|---|---|
get_pipelines |
Lists all pipelines (build definitions) in a project |
get_pipeline |
Gets details of a specific pipeline by ID |
get_pipeline_runs |
Gets recent runs (builds) for a specific pipeline |
get_build |
Gets details of a specific build by ID |
get_builds |
Lists builds with optional filters (status, result, branch, requester) |
get_build_logs |
Gets the list of log files for a build |
get_build_log_content |
Gets the content of a specific build log |
get_build_timeline |
Gets the timeline (stages, jobs, tasks) for a build |
query_builds |
Advanced query with multiple combined filters |
Prerequisites
| Requirement | Version | Notes |
|---|---|---|
| .NET SDK | 10.0+ | Required for local development |
| Docker | Latest | Recommended for running |
| Azure DevOps Account | - | With Personal Access Token |
Creating a Personal Access Token (PAT)
- Go to your Azure DevOps organization:
https://dev.azure.com/{your-org} - Click on User Settings (gear icon) > Personal Access Tokens
- Click + New Token
- Configure:
- Name:
MCP Server(or any name you prefer) - Expiration: Choose based on your needs
- Scopes: Select the following permissions:
- Name:
| Scope | Permission | Required for |
|---|---|---|
| Work Items | Read & Write | Get, query, create, update work items and add comments |
| Code | Read & Write | Git repositories, branches, files, and pull requests (Write required to create PRs) |
| Build | Read | Pipelines and builds |
- Click Create and copy the token immediately (you won't see it again!)
Running Options
Option 1: Docker Compose (Recommended)
Best for: Production use, quick setup without .NET installed
Create your
.envfile from the template:cp .env.example .env # Edit .env with your Azure DevOps credentialsStart the server:
docker compose up -d
Server URL: http://localhost:8080 (internal)
Important: For production, use a reverse proxy (nginx, traefik, or a cloud load balancer) in front of the container to provide HTTPS/TLS termination.
Useful commands:
docker compose logs -f # View logs
docker compose down # Stop the server
docker compose up -d --build # Rebuild and start
Option 2: .NET CLI
Best for: Development, debugging
dotnet run --project src/Viamus.Azure.Devops.Mcp.Server
Server URL: http://localhost:5000
HTTPS Support: The server can also run with HTTPS on port 5001, but this may cause certificate validation issues with some MCP clients (e.g., Claude Code). If you need HTTPS locally, configure the development certificate properly:
# Trust the development certificate (first time only) dotnet dev-certs https --trust # Run with HTTPS dotnet run --project src/Viamus.Azure.Devops.Mcp.Server --urls "https://localhost:5001"For production environments, use a reverse proxy with properly configured TLS certificates instead.
Option 3: Self-Contained Executable
Best for: Deployment without .NET runtime
# Windows
dotnet publish src/Viamus.Azure.Devops.Mcp.Server -c Release -r win-x64 -o ./publish/win-x64
# Linux
dotnet publish src/Viamus.Azure.Devops.Mcp.Server -c Release -r linux-x64 -o ./publish/linux-x64
# macOS (Intel)
dotnet publish src/Viamus.Azure.Devops.Mcp.Server -c Release -r osx-x64 -o ./publish/osx-x64
# macOS (Apple Silicon)
dotnet publish src/Viamus.Azure.Devops.Mcp.Server -c Release -r osx-arm64 -o ./publish/osx-arm64
Then run the executable directly:
# Windows
./publish/win-x64/Viamus.Azure.Devops.Mcp.Server.exe
# Linux/macOS
./publish/linux-x64/Viamus.Azure.Devops.Mcp.Server
Note: For production, use a reverse proxy (nginx, traefik) or Application Gateway to handle TLS termination with your own certificates.
Security
API Key Authentication
The server supports optional API key authentication to protect your MCP endpoints.
Configuration
Add to appsettings.json:
{
"ServerSecurity": {
"ApiKey": "your-secret-api-key",
"RequireApiKey": true
}
}
Or via environment variables:
# .NET CLI
ServerSecurity__ApiKey=your-secret-key ServerSecurity__RequireApiKey=true dotnet run
# Docker — configure in .env file (see .env.example)
docker compose up -d
For Docker, add to your .env file (see .env.example for the full template):
MCP_API_KEY=your-secret-api-key
MCP_REQUIRE_API_KEY=true
How It Works
- When
RequireApiKeyisfalse(default): No authentication required - When
RequireApiKeyistrue: All requests (except/health) require a valid API key - The
/healthendpoint is always accessible without authentication
Providing the API Key
Clients can provide the API key one way:
Option 1 - X-API-Key Header (recommended):
curl -H "X-API-Key: your-secret-key" https://localhost:5001
Generating a Secure API Key
# Using OpenSSL
openssl rand -base64 32
# Using PowerShell
[Convert]::ToBase64String([Security.Cryptography.RandomNumberGenerator]::GetBytes(32))
Client Configuration
Claude Code
Without API Key authentication:
claude mcp add azure-devops --transport http http://localhost:5000
With API Key authentication:
claude mcp add azure-devops --transport http http://localhost:5000 --header "X-API-Key: your-secret-api-key"
Note: Use port
5000(HTTP) if running with .NET CLI, or8080(HTTP) if running with Docker locally. For production deployments, configure a reverse proxy with HTTPS.
Usage Examples
After configuring the MCP client, you can ask questions like:
Work Items
- "List the active work items in project X"
- "What bugs are assigned to me?"
- "Show me the details of work item #1234"
- "What work items were changed in the last 7 days?"
- "Search for work items with 'login' in the title"
- "Add a comment to work item #1234 saying the bug was fixed"
- "Create a new Bug in project X titled 'Login page crashes on submit'"
- "Create a User Story assigned to John with priority 2 under parent #100"
- "Update work item #1234 to change state to 'Resolved' and assign to Jane"
- "Set the iteration path of work item #567 to 'Project\Sprint 3'"
Git Repositories
- "List all repositories in project X"
- "Show me the branches in the 'my-app' repository"
- "What files are in the /src folder of the 'backend' repository?"
- "Get the content of the README.md file from the 'frontend' repository"
- "Search for all .cs files in the 'api' repository"
- "Show me the content of /src/Program.cs from the 'main' branch"
Pull Requests
- "Show me all active pull requests in the 'my-repo' repository"
- "Get details of pull request #123"
- "Find pull request #456 anywhere in the project"
- "What comments are on PR #456?"
- "Search for pull requests related to 'authentication'"
- "Show me PRs targeting the 'main' branch"
- "List PRs created by [email protected]"
- "Create a pull request from 'feature/login' to 'main' titled 'Add login page'"
- "Open a draft PR from my branch to main with a description of the changes"
- "Create a PR and link it to work items #123 and #456"
Pipelines and Builds
- "List all pipelines in the project"
- "Show me the recent builds for pipeline 'CI-Build'"
- "What's the status of build #789?"
- "Show me failed builds from the last week"
- "Get the logs for build #456"
- "Show me the timeline of build #123"
- "What builds are currently in progress?"
Troubleshooting
Common Issues
Health check returns error or connection refusedVerify the server is running:
# Docker docker compose ps # Check if port is in use netstat -an | grep 8080 # Docker netstat -an | grep 5000 # .NET CLICheck logs for errors:
# Docker docker compose logs # .NET CLI - errors appear in terminal
- Verify your PAT is correct in
appsettings.json - Check PAT hasn't expired in Azure DevOps
- Ensure PAT has required scopes (Work Items, Code, Build)
- Verify the organization URL is correct (no trailing slash)
If API key authentication is enabled (RequireApiKey: true):
- Verify the API key is correctly set in your client configuration
- Check the
X-API-Keyheader is being sent with requests - Ensure the API key matches exactly (case-sensitive)
- The
/healthendpoint should still work without authentication
# Test health endpoint (should work without API key)
curl http://localhost:5000/health
# Test with API key
curl -H "X-API-Key: your-key" http://localhost:5000
Project not found
- Verify
AZURE_DEVOPS_DEFAULT_PROJECTmatches exact project name - Or pass the project name explicitly in your queries
- Check PAT has access to the project
- Check if
appsettings.jsonhas the required Azure DevOps configuration - View logs:
docker compose logs - Ensure port 8080 is not in use by another application
- Verify .NET 10 SDK is installed:
dotnet --version - Restore packages:
dotnet restore - Check if
appsettings.jsonhas the correct Azure DevOps settings
Project Structure
mcp-azure-devops/
├── src/
│ └── Viamus.Azure.Devops.Mcp.Server/
│ ├── Configuration/ # App configuration classes
│ ├── Middleware/ # HTTP middleware (authentication, etc.)
│ ├── Models/ # DTOs and data models
│ │ ├── WorkItemDto.cs # Work item models
│ │ ├── RepositoryDto.cs # Git repository models
│ │ ├── PullRequestDto.cs # Pull request models
│ │ └── PipelineDto.cs # Pipeline/build models
│ ├── Services/ # Azure DevOps SDK integration
│ ├── Tools/ # MCP tool implementations
│ │ ├── WorkItemTools.cs # Work item operations
│ │ ├── GitTools.cs # Git repository operations
│ │ ├── PullRequestTools.cs # Pull request operations
│ │ └── PipelineTools.cs # Pipeline/build operations
│ ├── Program.cs # Entry point
│ ├── appsettings.json # App settings
│ └── Dockerfile # Container definition
├── tests/
│ └── Viamus.Azure.Devops.Mcp.Server.Tests/
│ ├── Configuration/ # Configuration tests
│ ├── Middleware/ # Middleware tests
│ ├── Models/ # DTO tests
│ └── Tools/ # Tool behavior tests
├── .github/ # GitHub templates and workflows
├── .env.example # Environment variable template (copy to .env)
├── docker-compose.yml # Docker orchestration
├── install-mcp-azure-devops.ps1 # Windows automated installer
├── CONTRIBUTING.md # Contributor guide
├── CODE_OF_CONDUCT.md # Community guidelines
├── SECURITY.md # Security policy
└── LICENSE # MIT License
API Reference
Work Item DTOs
WorkItemDto
Complete work item details including all standard fields and custom fields.
WorkItemSummaryDto
Lightweight representation with essential fields (Id, Title, Type, State, Priority) for list views.
WorkItemCommentDto
Represents a comment on a work item with author and timestamp.
Git DTOs
RepositoryDto
Repository details including Id, Name, DefaultBranch, URLs, Size, and project information.
BranchDto
Branch information including Name, ObjectId (commit), and creator details.
GitItemDto
Represents a file or folder in a repository with Path, ObjectId, GitObjectType, and IsFolder flag.
GitFileContentDto
File content with Path, Content (text), IsBinary flag, Encoding, and Size.
Pull Request DTOs
PullRequestDto
Complete pull request details including:
- PullRequestId, Title, Description
- SourceBranch, TargetBranch
- Status (Active, Abandoned, Completed)
- CreatedBy, CreationDate, ClosedDate
- Reviewers list, MergeStatus, IsDraft
- Repository and Project information
PullRequestReviewerDto
Reviewer information including DisplayName, Vote (-10 to 10), IsRequired, and HasDeclined status.
PullRequestThreadDto
Comment thread with Id, Status (Active, Fixed, etc.), FilePath, LineNumber, and Comments list.
PullRequestCommentDto
Individual comment with Id, Content, Author, timestamps, and CommentType.
Pipeline/Build DTOs
PipelineDto
Pipeline (build definition) details including Id, Name, Folder, ConfigurationType, and QueueStatus.
BuildDto
Comprehensive build information including:
- Id, BuildNumber, Status, Result
- SourceBranch, SourceVersion
- RequestedBy, RequestedFor
- QueueTime, StartTime, FinishTime
- Definition details, LogsUrl, Reason, Priority
BuildLogDto
Build log metadata with Id, Type, Url, LineCount, and timestamps.
BuildTimelineRecordDto
Timeline record (stage, job, or task) with Id, ParentId, Type, Name, State, Result, timing information, and error/warning counts.
Development
Running Tests
# Run all tests
dotnet test
# Run specific test class
dotnet test --filter "FullyQualifiedName~WorkItemToolsTests"
# Run with coverage
dotnet test --collect:"XPlat Code Coverage"
Building
# Debug build
dotnet build
# Release build
dotnet build -c Release
Contributing
We welcome contributions! Please see CONTRIBUTING.md for:
- Development setup
- Coding standards
- How to add new MCP tools
- Pull request guidelines
License
This project is licensed under the MIT License.
Links
Reviews (0)
Sign in to leave a review.
Leave a reviewNo results found