arcade-azure-devops-mcp
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., "@arcade-azure-devops-mcp list my active work items for this week"
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.
arcade-azure-devops-mcp
An MCP server for Azure DevOps built with Arcade.dev. Enables AI assistants to interact with Azure DevOps projects, work items, repositories, pipelines, wikis, and more.
Features
21 tools covering:
Core: List projects, teams, search identities
Work Items: Get, create, update, query work items; add comments
Repositories: List repos, branches, pull requests; create PRs
Pipelines: List definitions, builds; queue builds; run pipelines
Wikis: List wikis, get wiki pages
Search: Search code across repositories
Related MCP server: Azure DevOps MCP Server
Quick Start
1. Install dependencies
uv sync2. Configure credentials
You have two options for providing Azure DevOps credentials:
Option A: Environment Variables (.env file)
Copy the example environment file and add your credentials:
cp .env.example .envEdit .env:
AZURE_DEVOPS_ORG=your-organization-name
AZURE_DEVOPS_PAT=your-personal-access-tokenOption B: Arcade Secrets (recommended for production)
If no .env file or environment variables are found, the server automatically falls back to Arcade Secrets. This is ideal for:
Publishing to the Arcade marketplace
Sharing the toolkit without exposing credentials
Production deployments via Arcade Deploy
Configure secrets in Arcade:
# Login to Arcade
arcade login
# Set your secrets
arcade secrets set AZURE_DEVOPS_ORG "your-organization-name"
arcade secrets set AZURE_DEVOPS_PAT "your-personal-access-token"Or configure via the Arcade Dashboard.
How it works:
Server checks for environment variables first
If not found, requests secrets from Arcade Cloud via
context.get_secret()Arcade prompts user to authorize secret access (first time only)
3. Create a Personal Access Token (PAT)
Go to
https://dev.azure.com/{your-org}/_usersSettings/tokensClick "New Token"
Select scopes: Code (Read/Write), Work Items (Read/Write), Build (Read/Execute), Wiki (Read/Write)
Copy the token
4. Run the MCP Server
# stdio transport (default) - for Claude Desktop, CLI tools
uv run server.py stdio
# http transport - for Cursor, VS Code
uv run server.py httpFor HTTP transport, view the API docs at http://127.0.0.1:8000/docs
Configure MCP Clients
Cursor IDE
arcade configure cursorOr manually add to .cursor/mcp.json:
With environment variables:
{
"mcpServers": {
"azure-devops": {
"command": "uv",
"args": ["run", "server.py", "stdio"],
"cwd": "/path/to/arcade-azure-devops-mcp",
"env": {
"AZURE_DEVOPS_ORG": "your-org",
"AZURE_DEVOPS_PAT": "your-pat"
}
}
}
}With Arcade Secrets (no local credentials):
{
"mcpServers": {
"azure-devops": {
"command": "uv",
"args": ["run", "server.py", "stdio"],
"cwd": "/path/to/arcade-azure-devops-mcp"
}
}
}VS Code
arcade configure vscodeClaude Desktop
arcade configure claudeAvailable Tools
Category | Tool | Description |
Core |
| List all projects in the organization |
| Get project details | |
| List teams in a project | |
| Search for users/groups | |
Work Items |
| Get a work item by ID |
| Create a new work item | |
| Update an existing work item | |
| Run a WIQL query | |
| Get work items assigned to you | |
| Add a comment to a work item | |
Repos |
| List Git repositories |
| List branches in a repository | |
| List pull requests | |
| Create a new PR | |
Pipelines |
| List pipeline definitions |
| List builds | |
| Queue a new build | |
| Start a pipeline run | |
Wikis |
| List wikis |
| Get wiki page content | |
Search |
| Search code across repositories |
Architecture
Request Flow
┌────────────┐ ┌────────────┐ ┌──────────────┐ ┌─────────────┐
│ MCP Client │ │ MCP Server │ │ Arcade Cloud │ │ Azure DevOps│
└─────┬──────┘ └─────┬──────┘ └──────┬───────┘ └──────┬──────┘
│ │ │ │
│ Call tool │ │ │
│──────────────────>│ │ │
│ │ │ │
│ │ Check env vars │ │
│ │◄──────────────────►│ │
│ │ │ │
│ │ [If env vars missing - paid tier] │
│ │ get_secret() │ │
│ │───────────────────>│ │
│ │<───────────────────│ │
│ │ │ │
│ │ API Request (Basic Auth) │
│ │─────────────────────────────────────────>│
│ │<─────────────────────────────────────────│
│ │ │ │
│ Tool result │ │ │
│<──────────────────│ │ │
│ │ │ │sequenceDiagram
participant C as MCP Client
participant S as MCP Server
participant A as Arcade Cloud
participant D as Azure DevOps
C->>S: Call tool (e.g., list_projects)
Note over S: Resolve Credentials
S->>S: Check env: AZURE_DEVOPS_ORG
S->>S: Check env: AZURE_DEVOPS_PAT
alt Environment variables exist
S->>S: Use local credentials
else Environment variables missing (paid tier)
S->>A: context.get_secret("AZURE_DEVOPS_ORG")
A-->>S: Return organization name
S->>A: context.get_secret("AZURE_DEVOPS_PAT")
A-->>S: Return PAT token
end
Note over S,D: API Request
S->>D: GET /{org}/_apis/projects?api-version=7.1
D-->>S: JSON response
S-->>C: Tool resultComponent Overview
┌─────────────────────────────────────────────────────────────────────────────┐
│ MCP CLIENT │
│ (Cursor / Claude Desktop) │
└─────────────────────────────────┬───────────────────────────────────────────┘
│ MCP Protocol (stdio/http)
▼
┌─────────────────────────────────────────────────────────────────────────────┐
│ MCP SERVER │
│ ┌─────────────────┐ ┌──────────────────┐ ┌─────────────────────────┐ │
│ │ MCPApp │ │ Azure DevOps │ │ AuthManager │ │
│ │ Framework │──│ Tools (21) │──│ (credential resolver) │ │
│ └─────────────────┘ └──────────────────┘ └───────────┬─────────────┘ │
└─────────────────────────────────────────────────────────┼───────────────────┘
│
┌─────────────────────────────────┼─────────────────┐
│ │ │
▼ [Priority 1] ▼ [Priority 2] │
┌─────────────────────────┐ ┌───────────────────────┐ │
│ Local .env / │ │ Arcade Cloud │ │
│ Environment Variables │ │ (Secrets API) │ │
└─────────────────────────┘ │ [Paid tier only] │ │
└───────────────────────┘ │
│
┌─────────────────┘
▼
┌───────────────────────┐
│ Azure DevOps │
│ REST API v7.1 │
└───────────────────────┘flowchart TB
subgraph MCPClient [MCP Client]
Cursor[Cursor / Claude Desktop]
end
subgraph MCPServer [MCP Server]
App[MCPApp Framework]
Tools[Azure DevOps Tools]
Auth[AuthManager]
end
subgraph External [External Services]
Arcade[Arcade Cloud - Secrets API]
ADO[Azure DevOps REST API v7.1]
end
subgraph Local [Local Config]
Env[.env file / Environment Variables]
end
Cursor -->|MCP Protocol| App
App --> Tools
Tools --> Auth
Auth -->|Priority 1| Env
Auth -.->|Priority 2 - Paid Tier| Arcade
Auth -->|Basic Auth| ADOCredential Resolution Priority
Environment variables (
.envfile or system env) - checked firstArcade Cloud secrets - fallback if env vars not found (requires paid Arcade tier)
Project Structure
arcade-azure-devops-mcp/
├── server.py # MCP server entry point with all tools
├── arcade_azure_devops_mcp/ # Azure DevOps client library
│ ├── __init__.py
│ ├── client.py # REST API client (httpx)
│ ├── models.py # Pydantic models
│ └── auth/ # Authentication
│ ├── __init__.py
│ ├── manager.py # Credential management (env + Arcade secrets)
│ └── oauth.py # OAuth/Azure AD (optional)
├── pyproject.toml # Dependencies & entry points
├── .env.example # Environment template
└── README.mdDevelopment
# Install with dev dependencies
uv sync --all-extras
# Run tests
uv run pytestPublishing to Arcade
To publish this toolkit to the Arcade marketplace:
# Ensure pyproject.toml has correct entry points
arcade publishUsers can then install via:
arcade install arcade-azure-devops-mcpLicense
MIT
Links
Available Tools
21 toolsAzureDevops_AddWorkItemCommentAzureDevops_AddWorkItemCommentB
Add a comment to a work item.
Inputs: text (required), project (required), work_item_id (required).
AzureDevops_CreatePullRequestAzureDevops_CreatePullRequestC
Create a new pull request.
Inputs: title (required), project (required), repository_id (required), source_ref_name (required), +3 more.
AzureDevops_CreateWorkItemAzureDevops_CreateWorkItemC
Create a new work item.
Inputs: title (required), project (required), work_item_type (required), state, +5 more.
AzureDevops_GetProjectAzureDevops_GetProjectC
Get details of a specific Azure DevOps project.
Inputs: project (required).
AzureDevops_GetWikiPageAzureDevops_GetWikiPageC
Get a specific wiki page.
Inputs: path (required), project (required), wiki_identifier (required), include_content.
AzureDevops_GetWorkItemAzureDevops_GetWorkItemB
Get a work item by ID.
Inputs: project (required), work_item_id (required), expand.
AzureDevops_ListBranchesAzureDevops_ListBranchesB
List branches in a repository.
Inputs: project (required), repository_id (required), top, filter_contains.
AzureDevops_ListBuildDefinitionsAzureDevops_ListBuildDefinitionsA
List build/pipeline definitions in a project.
Inputs: project (required), top, name.
AzureDevops_ListBuildsAzureDevops_ListBuildsA
List builds in a project.
Inputs: project (required), top, result, status.
AzureDevops_ListProjectsAzureDevops_ListProjectsB
List all projects in the Azure DevOps organization.
Inputs: top, skip, state_filter.
AzureDevops_ListPullRequestsAzureDevops_ListPullRequestsA
List pull requests in a repository.
Inputs: project (required), repository_id (required), top, status.
AzureDevops_ListRepositoriesAzureDevops_ListRepositoriesA
List all Git repositories in a project.
Inputs: project (required).
AzureDevops_ListTeamsAzureDevops_ListTeamsB
List all teams in a project.
Inputs: project (required), top, skip.
AzureDevops_ListWikisAzureDevops_ListWikisA
List wikis in a project or organization.
Inputs: project.
AzureDevops_MyWorkItemsAzureDevops_MyWorkItemsA
Get work items assigned to the current user.
Inputs: project (required), top, include_completed.
AzureDevops_QueueBuildAzureDevops_QueueBuildC
Queue a new build.
Inputs: project (required), definition_id (required), source_branch.
AzureDevops_RunPipelineAzureDevops_RunPipelineC
Start a new pipeline run.
Inputs: project (required), pipeline_id (required), branch.
AzureDevops_RunWorkItemQueryAzureDevops_RunWorkItemQueryC
Run a WIQL (Work Item Query Language) query.
Inputs: query (required), project (required), top.
AzureDevops_SearchCodeAzureDevops_SearchCodeB
Search for code across repositories.
Inputs: search_text (required), top, project, repository.
AzureDevops_SearchIdentitiesAzureDevops_SearchIdentitiesA
Search for identities (users/groups) in Azure DevOps.
Inputs: filter_value (required), search_filter (required).
AzureDevops_UpdateWorkItemAzureDevops_UpdateWorkItemB
Update an existing work item.
Inputs: project (required), work_item_id (required), state, title, +3 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 21 tools
Most tools target distinct Azure DevOps resources and actions. The only potential confusion is between QueueBuild and RunPipeline, which both trigger pipeline executions but on different pipeline types.
Tools follow an AzureDevops_VerbNoun pattern consistently. One deviation is MyWorkItems, which lacks a verb, but all other names are predictable.
With 21 tools, the server leans toward the heavy side, covering many Azure DevOps areas from projects to wikis. Each tool serves a distinct purpose, but the count is above the typical 3-15 well-scoped range.
The tool surface covers core read and create operations for work items, PRs, and builds, but lacks important lifecycle actions such as updating or merging pull requests, creating projects/repositories, and managing teams. These gaps will require agents to work around missing operations.
Maintenance
Related MCP Connectors
The MCP server for Azure DevOps, bringing the power of Azure DevOps directly to your agents.
One MCP server for the services your AI needs: memory, files, Microsoft 365, kanban and more.
MCP server that lets your AI assistant build and deploy apps, hosting each one at a live URL.
MCP server for your apps' tools and custom tools, plus hosted AI agents and approval-gated workflows
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceAn MCP server that provides Azure DevOps integration for AI assistants, enabling them to list projects, run pipelines, analyze failures, view logs, and troubleshoot builds directly from chat interfaces.37 PyPIMIT
- AlicenseAqualityDmaintenanceAn MCP server that exposes 41 Azure DevOps tools to AI assistants, enabling management of pipelines, repositories, pull requests, releases, work items, test management, and wikis through natural language.4147 PyPIMIT
- AlicenseNot gradedqualityCmaintenanceMCP server that enables AI assistants to manage Azure DevOps resources including Work Items, Git repositories, pipelines, and user identities.25 npmMIT
- AlicenseCqualityDmaintenanceA Model Context Protocol server that enables AI assistants to interact with Azure DevOps work items, projects, wikis, and boards through natural language.4194 npm4MIT