How to Use the Codefresh MCP in OpenAI Agents SDK

Q: Does the OpenAI Agents SDK support caching for Codefresh pipelines?

You can set cacheToolsList=True during initialization to avoid fetching the tool definitions on every turn. This keeps your pipeline queries fast when calling listcodefreshpipelines.

Trigger Codefresh builds and monitor deployments directly inside your OpenAI Agents SDK production workflows using this MCP integration.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Codefresh MCP to OpenAI Agents SDK

Create your Vinkius account to connect Codefresh to OpenAI Agents SDK 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 Codefresh with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Control Codefresh Pipelines via OpenAI Agents SDK

Stop leaving your terminal or console to check on deployment status. This integration lets your Python-based agent call `list_codefresh_pipelines` to see what is running, then inspect configurations with `get_pipeline_configuration` to debug failing steps. Because OpenAI Agents SDK supports strict guardrails, you can intercept these MCP calls before they hit your live clusters. Your agent gets the context it needs, and you keep complete control over execution.

Trigger and Track Builds with Built-In Tracing

Fire off new deployments using `trigger_codefresh_build` when your code checks out. The agent monitors the progress in real-time by polling `get_build_execution_details` to verify if the deployment succeeded or choked. You can trace every single one of these execution steps directly inside your OpenAI developer dashboard. If a build stalls, you will see exactly which tool payload caused the hangup.

Inspect Kubernetes Clusters and Environments

Give your agents eyes on your delivery infrastructure. This MCP Server allows your agent to map out active deployment targets by calling `list_delivery_clusters` and cross-referencing them with secrets retrieved via `list_shared_contexts`. This setup prevents blind deployments to dead clusters. Your agent checks the cluster list first, confirms the environment variables, and only then initiates the release.

Setup guide

Set up Codefresh MCP in OpenAI Agents SDK

Prerequisites

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

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Codefresh tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Codefresh tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Codefresh tools and returns structured results. Copy the full example on the right to get started.

agent.py

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

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Codefresh Agent",
            instructions="You have access to Codefresh tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 Codefresh. 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 Codefresh 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 Codefresh MCP in OpenAI Agents SDK

You install the package, initialize the HTTP MCP stream, and pass it to your agent constructor. The SDK auto-discovers tools like `list_codefresh_builds` without manual mapping.

Yes, by using the SDK's built-in guardrails to inspect the payload before `trigger_codefresh_build` runs. You can set up a human-in-the-loop check to approve production deployments.

You can set `cacheToolsList=True` during initialization to avoid fetching the tool definitions on every turn. This keeps your pipeline queries fast when calling `list_codefresh_pipelines`.

You define one agent to trigger the build and hand off the task to a monitor agent. The monitor agent then polls `get_build_execution_details` until the deployment finishes.

All sensitive environment variables and build configurations are processed through Vinkius's secure sandbox. The SDK only receives the metadata from `list_shared_contexts`, keeping your actual cluster keys isolated.

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