How to Use the Azure DevOps MCP in Pydantic AI

Q: What's the setup for Pydantic AI and the Azure DevOps MCP Server?

Install pydantic-ai-slimmcp, then instantiate an MCPToolset with your Vinkius server URL. Pass this toolset into the Agent constructor's toolsets list. The framework handles discovery and validation.

Build brutally reliable agents for Azure DevOps with Pydantic AI, where every API response is validated against a strict schema.

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 Pydantic AI

Create your Vinkius account to connect Azure DevOps to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Monitor Pipelines with Zero Guesswork

This toolset provides functions to check on your pipelines and builds. Your agent can call `list_pipelines` and `list_builds` to get the current state of your CI/CD. Here's the Pydantic AI difference: the response is guaranteed to match the Pydantic model you define. If the Azure DevOps API ever changes, your agent won't silently fail or hallucinate data. It will raise a `ValidationError` immediately, so you know exactly what broke and why. This is how you build reliable automation.

Manage Work Items with Confidence

Give your agent the tools to interact with your backlog. It can use `list_projects` to find the right project, then `list_work_items` to see what's on the board. With Pydantic AI, you're not just getting a list of strings; you're getting a list of `WorkItem` objects validated at runtime. This means your agent's logic can trust the data structure it's working with. No more defensive coding against missing keys or wrong data types. This MCP Server provides the data, and Pydantic AI ensures it's correct.

Use Any LLM with this MCP Server

This MCP server exposes core Azure DevOps functions like `list_repositories` and `list_project_teams`. Your agent gets a clear, functional view of your organization's structure. Because Pydantic AI is model-agnostic, you can swap between OpenAI, Anthropic, or a local LLM without changing your tool-calling logic. The framework handles the model-specific boilerplate. Your focus stays on defining the correct Pydantic models for the tool outputs, ensuring your DevOps agent works predictably no matter which brain is powering it.

Setup guide

Set up Azure DevOps MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "azure-devops-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Azure DevOps tools.",
)

result = await agent.run("List recent Azure DevOps transactions")
print(result.output)

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 Pydantic AI

If the Azure DevOps API returns data that doesn't match the Pydantic model for a tool, Pydantic AI will raise a `ValidationError`. This prevents your agent from acting on corrupted or unexpected data, making your automation much safer.

Absolutely. Pydantic AI is model-agnostic. You can point it at a local LLM, connect it to this MCP Server, and your agent can use tools like `list_projects` and `list_repositories` on your Azure DevOps instance.

Install `pydantic-ai-slim[mcp]`, then instantiate an `MCPToolset` with your Vinkius server URL. Pass this toolset into the `Agent` constructor's `toolsets` list. The framework handles discovery and validation.

By default, Pydantic ignores extra fields, so your agent won't break. If you want stricter validation, you can configure your models to forbid extra fields, which would cause a `ValidationError`. You have full control.

The server accesses read-only metadata: project and repo names, build statuses, team rosters, and work item details. Your source code and other sensitive content are never touched. Security is handled by Vinkius; your API key authenticates you, and every request runs in a completely separate, throwaway sandbox.

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