How to Use the Azure DevOps MCP in OpenAI Agents SDK

Q: How do I get my OpenAI Agent to list Azure DevOps pipelines?

Your agent automatically discovers the listpipelines tool from this MCP Server. Just ask it to 'list the pipelines for project X'. The OpenAI Agents SDK handles the tool-calling and response parsing for you.

Q: What's the setup for connecting the OpenAI Agents SDK to this Azure DevOps MCP Server?

It's one MCPServerStreamableHttp object. You pass your Vinkius endpoint URL to it, then add that server object to your Agent's mcpservers list. The tools are discovered automatically.

Build production-ready agents with the OpenAI Agents SDK that manage your Azure DevOps lifecycle, from work items to deployments.

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 OpenAI Agents SDK

Create your Vinkius account to connect Azure DevOps to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Map Out Your Entire Organization

This MCP Server gives your agent tools to build a complete picture of your Azure DevOps organization. It can start with `list_projects`, then dig into each one to `list_repositories` and `list_project_teams`. You get a full, queryable map of your engineering world. This is where the OpenAI Agents SDK proves its worth. You can build a 'discovery' agent that maps out the repos, then hands that list off to a specialized 'security' agent for analysis. The SDK's guardrails ensure the second agent only acts on valid repository data from the first, and the whole process is visible in your OpenAI tracing dashboard.

Monitor CI/CD with Your OpenAI Agent

Your agent can finally keep an eye on build health for you. It uses `list_pipelines` to find the critical deployment pipelines, then polls `list_builds` to check the status of recent runs. No more refreshing the builds page manually. When a build fails, an agent's response is more than just a simple script. The SDK's built-in guardrails can validate the agent's plan—like notifying a team—before it executes the action. This creates a monitored, safe operation, not just a blind notification bot.

Assign Work and Track Progress

Give your agent the ability to interact with your development workflow. It can pull project members with `list_project_teams` and then check on their assigned tasks by calling `list_work_items`. You can build a specialized agent for sprint planning that uses these tools. The OpenAI Agents SDK makes this reliable. If the agent tries to act on a corrupted or invalid work item, the framework can catch it. This is how you build an autonomous project manager that you can actually trust.

Setup guide

Set up Azure DevOps MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Azure DevOps tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Azure DevOps tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Azure DevOps tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Azure DevOps Agent",
            instructions="You have access to Azure DevOps tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Your agent automatically discovers the `list_pipelines` tool from this MCP Server. Just ask it to 'list the pipelines for project X'. The OpenAI Agents SDK handles the tool-calling and response parsing for you.

Yes. While the MCP Server exposes all tools, you can configure your agent in the SDK to only use a specific subset, like `list_work_items` and `list_builds`. This is a standard safety pattern for production agents.

It's one `MCPServerStreamableHttp` object. You pass your Vinkius endpoint URL to it, then add that server object to your Agent's `mcp_servers` list. The tools are discovered automatically.

It's not about speed, it's about context. Your agent understands what `list_repositories` means without you writing the HTTP requests, auth, or parsing logic. You just tell the agent what you want done.

The server only reads metadata like project names, repository lists, build statuses, and work item titles. It never accesses your source code. Vinkius runs each request in a sandboxed, ephemeral environment, and your connection is secured by your unique endpoint 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