How to Use the CircleCI MCP in Pydantic AI

Q: Can I use Pydantic AI to trigger a CircleCI pipeline?

Yes. The agent can call triggerccipipeline with validated arguments. Pydantic AI ensures the parameters match the expected schema before the HTTP request is executed.

Validate CircleCI pipeline schemas and run type-safe workflows using Pydantic AI agents.

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 Pydantic AI

Create your Vinkius account to connect CircleCI 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 CircleCI with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe pipeline execution with Pydantic AI

When your agent calls `trigger_cci_pipeline`, Pydantic AI validates the input parameters against strict Python types before sending the request. This prevents malformed branch names or invalid parameters from hitting the CircleCI API and wasting your API limits. If the API returns unexpected data, the framework raises a validation error immediately. This ensures your agent never operates on corrupted JSON payloads when monitoring active builds.

Strict validation for workflow and job structures

This MCP Server exposes `get_workflow_details` and `list_workflow_jobs` to track the exact state of your test suites. Pydantic AI parses these responses into structured models, making it easy to write assertions about build success in your Python codebase. If a job fails, the agent uses `get_job_details` to inspect the error. Because every field is validated at runtime, your agent can reliably extract the failure step without risking silent errors from unexpected API changes.

Audit shared contexts with model-agnostic agents

Your agent can pull organization secrets metadata using `list_cci_contexts` to verify setup compliance. Pydantic AI works with any LLM provider, meaning you can run these security audits using local models or commercial APIs. You connect the MCP Server using the unified `MCPToolset` class. This setup guarantees that your agent always receives clean, validated data when checking who triggered a pipeline via `get_my_cci_profile`.

Setup guide

Set up CircleCI 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": {
        "circleci-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent CircleCI 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 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 Pydantic AI

Install the MCP extension, then initialize MCPToolset with the Vinkius HTTP URL. Pass this toolset directly to your agent's toolsets list to give it access to tools like list_cci_pipelines.

The framework will raise a validation error instantly. This prevents the agent from making decisions based on malformed data when parsing the output of list_pipeline_workflows.

Yes. The agent can call trigger_cci_pipeline with validated arguments. Pydantic AI ensures the parameters match the expected schema before the HTTP request is executed.

The MCPToolset class is the unified approach for handling an MCP Server. It replaces the deprecated HTTP classes and provides a cleaner interface for running tools like get_my_cci_profile.

Your keys are never stored on disk. Vinkius handles authentication securely by injecting your API token into an ephemeral, zero-trust V8 sandbox that is destroyed as soon as the tool execution completes.

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