Azure DevOps MCP Server
The Azure DevOps MCP Server enables AI models to interact with Azure DevOps, providing capabilities for managing work items, pull requests, pipelines, and more.
Overview
The Azure DevOps MCP Server brings Azure DevOps context to your agents, enabling AI models to interact with your Azure DevOps environment. It allows for managing work items, pull requests, test plans, builds, releases, and wiki pages directly from your code editor or AI assistant.
Official Server:
Developed and maintained by Microsoft
Key Features
Work Item Management
Create, update, query, and manage work items like bugs, tasks, and user stories.
Pull Request Operations
List, create, and update pull requests, and manage their comments and threads.
Pipeline & Build Interaction
Query pipeline status and trigger new pipeline runs.
Wiki Management
Create, update, and retrieve content from wiki pages.
Available Tools
Quick Reference
| Tool | Purpose | Category |
|---|---|---|
core_list_projects | List projects in your organization | Core |
wit_work_item | Read work items (get, list, comments, revisions) | Work Items |
wit_work_item_write | Create or update work items | Work Items |
repo_repository | Get or list repositories | Repositories |
repo_pull_request | Get or list pull requests | Repositories |
repo_pull_request_write | Create or update pull requests | Repositories |
wiki_upsert_page | Create or update a wiki page | Wiki |
Detailed Usage
core_list_projects▶
Retrieve a list of projects in your Azure DevOps organization.
use_mcp_tool({
server_name: "azure-devops",
tool_name: "core_list_projects",
arguments: {}
});
wit_work_item_write▶
Create a new work item in a specified project and work item type.
use_mcp_tool({
server_name: "azure-devops",
tool_name: "wit_work_item_write",
arguments: {
action: "create",
project: "MyProject",
workItemType: "Bug",
fields: [
{ name: "System.Title", value: "Fix authentication issue" },
{ name: "System.Description", value: "Users are unable to log in.", format: "Markdown" }
]
}
});
repo_pull_request_write▶
Create a new pull request.
use_mcp_tool({
server_name: "azure-devops",
tool_name: "repo_pull_request_write",
arguments: {
action: "create",
project: "MyProject",
repositoryId: "my-repo-id",
sourceRefName: "refs/heads/feature/new-feature",
targetRefName: "refs/heads/main",
title: "New Feature Implementation"
}
});
wiki_upsert_page▶
Create or update a wiki page with specified content.
use_mcp_tool({
server_name: "azure-devops",
tool_name: "wiki_upsert_page",
arguments: {
project: "MyProject",
wikiIdentifier: "MyWiki",
path: "/NewPage",
content: "# My New Wiki Page\nThis is the content of my new wiki page."
}
});
Installation
Microsoft recommends the hosted remote server. Use the local server only when you need a stdio connection.
{
"mcpServers": {
"azure-devops": {
"type": "http",
"url": "https://mcp.dev.azure.com/your-organization"
}
}
}
Authentication:
Replace your-organization with your Azure DevOps organization name. Sign in with a Microsoft account when your client prompts you.
Sources
Related Articles & Guides
Accessibility Scanner MCP Server
Accessibility Scanner MCP servers enable AI models to perform WCAG compliance checks, capture annotated screenshots, and generate detailed accessibility reports.
Auth0 MCP Server
Auth0 MCP server enables AI models to interact with Auth0 identity and access management, including applications, APIs, actions, logs, and forms.
AWS MCP Server
Interact with Amazon Web Services through your AI assistant using the AWS API MCP Server.