Can I trigger a build for a specific branch through the agent?

Yes! Use the `trigger_cci_pipeline` tool. You need to provide the project slug (e.g., `gh/org/repo`) and the branch name. The agent will instruct CircleCI to start the pipeline immediately.

How do I see why a specific job failed?

Use the `get_job_details` tool with the project slug and job number. Your agent will fetch the execution status and metadata, which often points to the cause of failure.

Where do I find my CircleCI API Token?

Log in to CircleCI, go to **User Settings -> Personal API Tokens**. You can generate and copy a new token from there.

CircleCI MCP Server for OpenAI Agents SDK 8 tools — connect in under 2 minutes

Name: CircleCI
Availability: InStock
Author: Vinkius

openai.github.io/openai-agents-python/mcp

Built by Vinkius GDPR 8 Tools SDK

The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect CircleCI through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

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

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    async with MCPServerStreamableHttp(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as mcp_server:

        agent = Agent(
            name="CircleCI Assistant",
            instructions=(
                "You help users interact with CircleCI. "
                "You have access to 8 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from CircleCI"
        )
        print(result.final_output)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About CircleCI MCP Server

Connect your CircleCI account to any AI agent and take full control of your CI/CD pipelines and software delivery through natural conversation. Streamline how you monitor and trigger automated builds.

The OpenAI Agents SDK auto-discovers all 8 tools from CircleCI through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries CircleCI, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.

What you can do

Pipeline Oversight — List and retrieve details for recent CI/CD pipelines across your organizations natively
Trigger Management — Manually trigger new pipeline runs for specific projects and branches flawlessly
Workflow Intelligence — Access detailed information for workflows and their constituent jobs securely
Job Auditing — Retrieve detailed metadata and execution status for specific jobs flawlessly
Context Logistics — List shared environment contexts used for securing sensitive project data flawlessly
Developer Insights — Retrieve your own user profile and organization membership information directly within your workspace

The CircleCI MCP Server exposes 8 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect CircleCI to OpenAI Agents SDK via MCP

Follow these steps to integrate the CircleCI MCP Server with OpenAI Agents SDK.

Install the SDK

Run pip install openai-agents in your Python environment

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com

Run the script

Save the code above and run it: python agent.py

Explore tools

The agent will automatically discover 8 tools from CircleCI

Why Use OpenAI Agents SDK with the CircleCI MCP Server

OpenAI Agents SDK provides unique advantages when paired with CircleCI through the Model Context Protocol.

Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety

Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure

Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate

First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output

CircleCI + OpenAI Agents SDK Use Cases

Practical scenarios where OpenAI Agents SDK combined with the CircleCI MCP Server delivers measurable value.

Automated workflows: build agents that query CircleCI, process the data, and trigger follow-up actions autonomously

Multi-agent orchestration: create specialist agents — one queries CircleCI, another analyzes results, a third generates reports

Data enrichment pipelines: stream data through CircleCI tools and transform it with OpenAI models in a single async loop

Customer support bots: agents query CircleCI to resolve tickets, look up records, and update statuses without human intervention

CircleCI MCP Tools for OpenAI Agents SDK (8)

These 8 tools become available when you connect CircleCI to OpenAI Agents SDK via MCP:

get_job_details

Get detailed information for a specific job

get_my_cci_profile

Retrieve information about the authenticated user

get_workflow_details

Get detailed information for a specific workflow

list_cci_contexts

List shared contexts for an organization

list_cci_pipelines

List recent CI/CD pipelines

list_pipeline_workflows

List all workflows within a specific pipeline

list_workflow_jobs

List all jobs within a specific workflow

trigger_cci_pipeline

Trigger a new pipeline for a project

Example Prompts for CircleCI in OpenAI Agents SDK

Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with CircleCI immediately.

"List my last 5 pipelines in CircleCI."

"Trigger a new pipeline for project 'gh/acme/api' on the 'main' branch."

"Show me the status of all jobs in workflow ID 'wf-12345'."

Troubleshooting CircleCI MCP Server with OpenAI Agents SDK

Common issues when connecting CircleCI to OpenAI Agents SDK through the Vinkius, and how to resolve them.

MCPServerStreamableHttp not found

Ensure you have the latest version: pip install --upgrade openai-agents

Agent not calling tools

Make sure your prompt explicitly references the task the tools can help with.

CircleCI + OpenAI Agents SDK FAQ

Common questions about integrating CircleCI MCP Server with OpenAI Agents SDK.

How does the OpenAI Agents SDK connect to MCP?

Use MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.