How to Use the Azure DevOps MCP in LangChain

Q: How do I use the Azure DevOps MCP Server with LangChain agents?

You'll use MultiServerMCPClient to connect, then call gettools() to get a list of functions. Pass those tools directly into your agent's constructor, like createagent. LangChain handles the rest.

Build autonomous release managers and project auditors in LangChain by chaining together live Azure DevOps data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Azure DevOps MCP to LangChain

Create your Vinkius account to connect Azure DevOps to LangChain and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Azure DevOps with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map Your Entire Azure DevOps Org

Your agent can start with `list_projects` to get a high-level view, then drill down. It can use `list_project_teams` to figure out who owns what, and `list_repositories` to find the code. Each step is a link in a chain. The output from one tool call directly feeds the next, letting your LangChain agent build a complete picture of a project on its own. No manual scripting needed.

Automate CI/CD Monitoring with LangChain

Create an agent that continuously monitors your pipelines. It can use `list_pipelines` to get an inventory, then check on recent activity with `list_builds` for each one. Since it's LangChain, you can chain this with other tools. If a build fails, the agent can automatically check the associated `list_work_items` and then notify the right team via a different MCP tool. This is how you build a real-time DevOps assistant.

Track Work and Sprint Progress

Point your agent at a project and let it pull all the data. It'll use `list_work_items` to see what's in flight, what's blocked, and what's done. You can build chains that generate sprint reports automatically. The agent fetches the work items, categorizes them, and formats a summary without you lifting a finger. It's a simple way to keep tabs on progress with this MCP Server.

Setup guide

Set up Azure DevOps MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Azure DevOps tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "azure-devops-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Azure DevOps transactions"
    })
    print(result["messages"][-1].content)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Azure DevOps. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Azure DevOps now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Azure DevOps MCP in LangChain

You'll use `MultiServerMCPClient` to connect, then call `get_tools()` to get a list of functions. Pass those tools directly into your agent's constructor, like `create_agent`. LangChain handles the rest.

Yes, that's what chains are for. Your agent would first call `list_builds` from this Azure DevOps server. If it finds a failed build, it can use that output to call a tool from another MCP Server to create a Jira issue or GitHub ticket.

If you're using LangSmith, every tool call is automatically traced. You'll see the exact inputs and outputs for tools like `list_repositories` or `list_work_items`, which is great for debugging your agent's reasoning.

Absolutely. LangChain is built for this. You can have one step in your chain call `list_pipelines` on Azure DevOps, and the next step query a database or a vector store for related performance metrics.

This server only reads metadata about your projects, teams, repositories, pipelines, builds, and work items. It never touches your source code or artifact contents. All connections are ephemeral and authenticated through your Vinkius token.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript