Azure DevOps MCP Server
Model Context Protocol

Connect Your Ticketing System to Azure DevOps

MCP server that exposes work items, repositories, pipelines, and wikis from your Azure DevOps on-premises instance. Enable AI-powered analysis and context retrieval.

Available MCP Tools

Work Items
Search, retrieve, and analyze bugs, tasks, and user stories
search_work_itemsget_work_itemanalyze_work_item
Repositories
Access Git repos, commits, branches, and pull requests
list_repositoriesget_commitssearch_code
Pipelines
Monitor builds, analyze failures, and track pipeline status
list_pipelinesget_buildsanalyze_build_failure
Wiki
Search documentation and retrieve wiki page content
search_wikiget_wiki_page

Connect From Your MCP Client

Use the standard MCP SDK to connect your ticketing system or AI application to this server. The server supports Streamable HTTP transport for reliable, stateful communication.

1

Connect to the MCP endpoint

POST requests to /api/mcp with JSON-RPC payloads

2

Call available tools

Search work items, query repositories, analyze builds

3

Use prompts for common tasks

Pre-built prompts for ticket analysis, build investigation

TypeScript Example
import { Client } from "@modelcontextprotocol/sdk/client";
import { StreamableHTTPClientTransport } from 
  "@modelcontextprotocol/sdk/client/streamableHttp";

const client = new Client({
  name: "my-ticketing-system",
  version: "1.0.0"
});

const transport = new StreamableHTTPClientTransport(
  new URL("https://your-server.com/api/mcp")
);

await client.connect(transport);

// Search for related work items
const result = await client.callTool({
  name: "search_work_items",
  arguments: {
    query: "login authentication bug",
    workItemType: "Bug",
    state: "Active"
  }
});