How to Use the Azure DevOps MCP in AutoGen

Q: How do I give my AutoGen agents access to Azure DevOps tools?

Use the mcpservertools function from the autogen-ext library, passing in your server URL. This returns a list of tools that you can provide to your AssistantAgent during initialization. The McpToolAdapter handles the conversion automatically.

Q: Can I use AutoGen to manage Azure DevOps work items?

This specific MCP server provides read-only tools like listworkitems. To create or update work items, you'd need a different MCP server with those specific tools. AutoGen could then use both servers in a single conversation.

Let AutoGen agents debate DevOps strategy, with one agent pulling live Azure DevOps data to ground the conversation in fact.

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 AutoGen

Create your Vinkius account to connect Azure DevOps to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fuel Agent Debates with Live Data

Create an agent whose only job is to provide facts. When a "Planner" agent proposes a new sprint, the "DevOps" agent can use `list_work_items` and `list_builds` to check current capacity and recent failures. This stops the agents from just guessing. The DevOps agent injects real-time data from tools like `list_pipelines` into the conversation, forcing the other agents to adjust their plans based on reality.

Simulate a Release Planning Meeting

Set up a multi-agent conversation. One agent acts as the project manager, another as the lead developer. The developer agent can use this MCP server to pull information. For instance, it can call `list_repositories` to find the right codebase, `list_project_teams` to see who is available, and `list_work_items` to review the backlog. The agents then discuss and agree on a plan, just like a real team.

Create an AutoGen Security Auditor

Design a conversation between a "Developer" agent and a "Security" agent. The Developer proposes a change. The Security agent's job is to check for risks. It can use this MCP server to `list_pipelines` and check their configuration, or `list_repositories` to see if they follow certain naming conventions. The agents go back and forth until they reach a secure consensus.

Setup guide

Set up Azure DevOps MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Azure DevOps tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Azure DevOps_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Azure DevOps data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Azure DevOps_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Azure DevOps data")
    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 AutoGen

Use the `mcp_server_tools` function from the `autogen-ext` library, passing in your server URL. This returns a list of tools that you can provide to your `AssistantAgent` during initialization. The `McpToolAdapter` handles the conversion automatically.

Yes, that's the point of AutoGen. You can have one agent equipped with the Azure DevOps MCP tools and another agent with tools for sending Slack messages. They can then talk to each other to create a full workflow, like "find failed builds and post them to #devops-alerts".

The agent decides based on the conversation history and its goal. If another agent asks "How many active projects do we have?", the agent with the Azure DevOps tools will recognize that `list_projects` is the right tool for the job.

This specific MCP server provides read-only tools like `list_work_items`. To create or update work items, you'd need a different MCP server with those specific tools. AutoGen could then use both servers in a single conversation.

Your agents will be working with metadata from your Azure DevOps organization. This includes lists of projects, teams, repos, build statuses, and work item details. The server doesn't read source code or other sensitive content, and Vinkius ensures each call is isolated and stateless.

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