Azure DevOps MCP Server
Enables AI assistants to search, create, update, and manage work items in Azure DevOps using natural language.
README
Azure DevOps MCP Server
MCP (Model Context Protocol) server for Azure DevOps Work Item Tracking integration. Enables AI assistants like Claude to search, create, update, and manage work items in Azure DevOps.
Features
- Search Work Items: Query using WIQL (Work Item Query Language)
- Get Work Item: Retrieve detailed work item information by ID
- Create Work Item: Create Bugs, Tasks, User Stories, Features, etc.
- Update Work Item: Modify fields, change state, update assignments
- Add Comments: Add discussion comments to work items
Installation
npm install @bugzy-ai/azure-devops-mcp-server
Or run directly with npx:
npx @bugzy-ai/azure-devops-mcp-server
Configuration
Environment Variables
| Variable | Required | Description |
|---|---|---|
AZURE_DEVOPS_ORG_URL |
Yes | Organization URL (e.g., https://dev.azure.com/myorg) |
AZURE_DEVOPS_PAT |
Yes | Personal Access Token |
AZURE_DEVOPS_MCP_DEBUG |
No | Enable debug logging to .azure-devops-mcp/mcp.log |
Note: Project name is specified per-request, not via environment variable. The AI agent discovers the project from context (e.g.,
.bugzy/runtime/project-context.md) or usesazuredevops_list_projectsto find available projects.
Creating a Personal Access Token (PAT)
- Go to Azure DevOps → User Settings → Personal Access Tokens
- Click "New Token"
- Set the required scopes:
vso.work- Read work itemsvso.work_write- Create and update work items
- Copy the token and set it as
AZURE_DEVOPS_PAT
MCP Configuration
Add to your MCP configuration file (e.g., claude_desktop_config.json):
{
"mcpServers": {
"azure-devops": {
"command": "npx",
"args": ["@bugzy-ai/azure-devops-mcp-server"],
"env": {
"AZURE_DEVOPS_ORG_URL": "https://dev.azure.com/your-org",
"AZURE_DEVOPS_PAT": "your-pat-token"
}
}
}
}
Tools
azuredevops_list_projects
List all projects in the Azure DevOps organization. Use this to discover available projects.
{
top?: number, // Max projects to return (default: 100, max: 100)
skip?: number // Number to skip for pagination (default: 0)
}
azuredevops_search_work_items
Search for work items using WIQL queries.
{
project: string, // Azure DevOps project name (required)
wiql: string, // WIQL query
maxResults?: number // Max results (default: 50, max: 200)
}
Example WIQL queries:
-- Find open bugs
SELECT [System.Id], [System.Title], [System.State]
FROM WorkItems
WHERE [System.WorkItemType] = 'Bug'
AND [System.State] <> 'Closed'
ORDER BY [System.CreatedDate] DESC
-- Find work items assigned to me
SELECT [System.Id], [System.Title]
FROM WorkItems
WHERE [System.AssignedTo] = @Me
AND [System.State] = 'Active'
-- Find recent items in a specific area
SELECT [System.Id], [System.Title], [System.WorkItemType]
FROM WorkItems
WHERE [System.AreaPath] UNDER 'Project\Team'
AND [System.CreatedDate] >= @Today - 7
azuredevops_get_work_item
Get detailed information about a work item.
{
project: string, // Azure DevOps project name (required)
id: number, // Work item ID
fields?: string[], // Specific fields to retrieve
expand?: "None" | "Relations" | "Fields" | "Links" | "All"
}
azuredevops_create_work_item
Create a new work item.
{
project: string, // Azure DevOps project name (required)
type: string, // "Bug", "Task", "User Story", etc.
title: string, // Work item title
description?: string, // Description (HTML supported)
areaPath?: string, // Area path
iterationPath?: string,// Iteration/sprint path
assignedTo?: string, // User email or display name
priority?: number, // 1-4 (1=Critical, 4=Low)
severity?: string, // For bugs: "1 - Critical", "2 - High", etc.
tags?: string, // Semicolon-separated tags
parentId?: number // Parent work item ID
}
azuredevops_update_work_item
Update an existing work item using JSON Patch operations.
{
project: string, // Azure DevOps project name (required)
id: number,
operations: Array<{
op: "add" | "remove" | "replace",
path: string, // e.g., "/fields/System.State"
value?: any
}>
}
Example - Change state to Active:
{
"id": 123,
"operations": [
{ "op": "replace", "path": "/fields/System.State", "value": "Active" }
]
}
azuredevops_add_comment
Add a comment to a work item.
{
project: string, // Azure DevOps project name (required)
id: number, // Work item ID
text: string // Comment text (HTML supported)
}
Development
# Install dependencies
npm install
# Build
npm run build
# Run with MCP Inspector (for testing)
npm run dev
# Watch mode
npm run build:watch
Debugging
Enable debug logging by setting AZURE_DEVOPS_MCP_DEBUG=true. Logs are written to .azure-devops-mcp/mcp.log.
License
MIT
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.