How to Use the Azure DevOps MCP in CrewAI

Q: How do I assign Azure DevOps tools to specific agents in CrewAI?

Pass the Vinkius MCP URL in the agent's mcps list. You can use a toolfilter to ensure an agent only gets access to listworkitems or listbuilds.

Q: How do I connect a CrewAI framework to the Azure DevOps MCP Server?

Install crewaitools via pip and define your connection using MCPServerHTTP pointing to your Vinkius endpoint. This exposes the tools to your entire agent crew over a secure MCP connection.

Deploy a specialized crew of CrewAI agents to coordinate Azure DevOps builds, track repositories, and assign work items.

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 CrewAI

Create your Vinkius account to connect Azure DevOps to CrewAI 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 CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate Azure DevOps tasks using specialized CrewAI agent teams

Managing complex Azure DevOps projects requires multiple perspectives. CrewAI lets you set up one agent to analyze codebases using `list_repositories` while a second agent monitors active deployments with `list_pipelines`. These CrewAI agents share memory, allowing them to collaborate on issues. If the pipeline agent notices a broken Azure DevOps build, it alerts the repo agent to find the commit that broke it, mimicking a human engineering team.

Automate backlog triage without human intervention

Keeping your Azure DevOps backlog clean is a constant battle. By giving a CrewAI agent access to `list_work_items` and `list_projects`, you can let it run autonomous triage cycles to flag stale tickets. The CrewAI agent scans your active Azure DevOps boards, evaluates item descriptions, and organizes them sequentially. It matches tasks against existing `list_project_teams` to make sure nothing falls through the cracks on your Azure DevOps team.

Limit tool exposure for sensitive CrewAI operations

You might not want every agent in your CrewAI team to have unrestricted access to your Azure DevOps codebase. Using the `MCPServerHTTP` class with a `tool_filter`, you can restrict specific agents to harmless operations. For example, you can allow your CrewAI project manager agent to run `list_builds` while completely blocking its access to your Azure DevOps repositories. This keeps your security posture tight on this MCP Server.

Setup guide

Set up Azure DevOps MCP in CrewAI

Prerequisites

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

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke Azure DevOps tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="Azure DevOps Analyst",
    goal="Access and analyze Azure DevOps data via MCP.",
    backstory="Expert analyst with direct Azure DevOps access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent Azure DevOps transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

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

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="Azure DevOps Analyst",
        goal="Access and analyze Azure DevOps data via MCP.",
        backstory="Expert analyst with direct Azure DevOps access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent Azure DevOps transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

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 CrewAI

Pass the Vinkius MCP URL in the agent's `mcps` list. You can use a `tool_filter` to ensure an agent only gets access to `list_work_items` or `list_builds`.

Yes, CrewAI's shared memory allows a monitoring agent using `list_pipelines` to pass pipeline data to a developer agent, which can then inspect `list_repositories`.

Install `crewai[tools]` via pip and define your connection using `MCPServerHTTP` pointing to your Vinkius endpoint. This exposes the tools to your entire agent crew over a secure MCP connection.

You can run your crew in either sequential or hierarchical modes, meaning agents can pass build statuses down a chain or report to a manager agent.

Your pipeline metrics, repository lists, and project structures are processed strictly within memory during the execution of your crew's tasks. No data is written to persistent storage, and all connections to your Azure DevOps organization are fully encrypted.

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