How to Use the CircleCI MCP in CrewAI

Q: How do I configure the CircleCI MCP Server in my CrewAI setup?

Pass the Vinkius endpoint URL directly into the mcps array of your Agent definition. For granular control, import MCPServerHTTP from crewai.mcp and define explicit tool filters.

Deploy a team of autonomous agents to manage your builds. CrewAI delegates CircleCI monitoring, debugging, and deployment across specialized roles.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CircleCI MCP to CrewAI

Create your Vinkius account to connect CircleCI 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 CircleCI with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Assign CircleCI tasks to specialized agents

Stop forcing one script to do everything. CrewAI lets you build a dedicated DevOps team in code. You can assign a Monitor Agent to poll `list_cci_pipelines` continuously, looking for stalled builds or sudden failures. When the monitor finds a problem, it hands the context to a Debugger Agent. This second agent pulls the exact logs using `get_job_details` and analyzes the failure. Because the crew shares memory, the debugger knows exactly which commit caused the issue without asking for redundant information.

Resolve build errors with CrewAI teams

True autonomy means handling the unexpected. If a critical deployment fails, your hierarchical crew can execute a predefined escalation path. A Moderator Agent reviews the failure from `get_workflow_details` and decides whether to rollback or push a hotfix. Connecting this MCP Server gives your agents actual execution power. Instead of just writing a Slack message about a broken build, the Action Agent uses `trigger_cci_pipeline` to start the recovery process. You define the boundaries, and the framework handles the coordination.

Filter MCP Server access by agent role

Security requires principle of least privilege. You do not want your research agent accidentally starting a production build. The Python framework lets you restrict which tools each specific persona can access. Use the `MCPServerHTTP` class with a `tool_filter` to lock down permissions. Give your reporting agent access to `list_workflow_jobs` and `get_my_cci_profile`, while reserving the trigger commands strictly for the deployment manager. Your infrastructure stays safe from hallucinated commands.

Setup guide

Set up CircleCI 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 CircleCI tools as needed.

crew.py

from crewai import Agent, Task, Crew

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

task = Task(
    description="List recent CircleCI 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="CircleCI Analyst",
        goal="Access and analyze CircleCI data via MCP.",
        backstory="Expert analyst with direct CircleCI access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent CircleCI 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 CircleCI. 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 CircleCI 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 CircleCI MCP in CrewAI

Pass the Vinkius endpoint URL directly into the `mcps` array of your Agent definition. For granular control, import `MCPServerHTTP` from `crewai.mcp` and define explicit tool filters.

Yes, they collaborate using shared memory. If one persona fetches a failed run using `list_pipeline_workflows`, the next agent in the sequence can read that context without making another API call.

Apply a strict tool filter when defining the integration. Explicitly exclude the `trigger_cci_pipeline` tool from any agent that only needs read-only access to your build logs.

The framework supports stdio, SSE, and Streamable HTTP. Vinkius provides HTTP endpoints, which the Python client handles natively without complex networking configuration.

Not at all. Vinkius isolates your CI/CD credentials and pipeline execution histories inside a temporary sandbox. Once your multi-agent session terminates, all traces of your organization contexts and job details vanish.

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