Can I trigger a pipeline run for a specific branch?

Yes! Use the `trigger_codefresh_build` tool. You can provide the pipeline ID and specify the branch name in the payload. The agent will instruct Codefresh to start the build immediately.

How do I see the status of all my Kubernetes clusters in Codefresh?

Use the `list_delivery_clusters` tool. Your agent will fetch all connected clusters, showing you which targets are available for deployment and their current health status.

Where do I find my Codefresh API Key?

Log in to Codefresh, click on your profile icon, go to **User Settings**, and select **API Keys**. You can generate and copy a new token from that section.

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

Name: Codefresh
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 Codefresh through 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="Codefresh Assistant",
            instructions=(
                "You help users interact with Codefresh. "
                "You have access to 8 tools."
            ),
            mcp_servers=[mcp_server],
        )

        result = await Runner.run(
            agent, "List all available tools from Codefresh"
        )
        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 Codefresh MCP Server

Connect your Codefresh account to any AI agent and take full control of your CI/CD and cloud-native delivery through natural conversation. Streamline how you automate and monitor software deployments natively.

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

What you can do

Pipeline Oversight — List and retrieve details for all CI/CD pipelines including their configurations natively
Build Management — Trigger new builds for specific pipelines and specify branches or variables flawlessly
Workflow Intelligence — Access detailed status and execution info for recent builds (workflows) flawlessly
Cluster Logistics — Monitor all connected Kubernetes and delivery clusters to verify deployment targets securely
Environment Auditing — List shared contexts, including secrets and variables, used in your workflows securely
integrated Visibility — Retrieve detailed build metadata and user profile information directly within your workspace

The Codefresh 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 Codefresh to OpenAI Agents SDK via MCP

Follow these steps to integrate the Codefresh 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 Codefresh

Why Use OpenAI Agents SDK with the Codefresh MCP Server

OpenAI Agents SDK provides unique advantages when paired with Codefresh 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

Codefresh + OpenAI Agents SDK Use Cases

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

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

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

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

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

Codefresh MCP Tools for OpenAI Agents SDK (8)

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

get_build_execution_details

Get detailed status and execution info for a specific build

get_my_codefresh_profile

Retrieve information about the authenticated user and account

get_pipeline_configuration

Get detailed information for a specific pipeline

list_codefresh_builds

List all recent builds (workflows) in the account

list_codefresh_pipelines

List all CI/CD pipelines in the account

list_delivery_clusters

List all connected Kubernetes/Delivery clusters

list_shared_contexts

List all shared environment contexts (secrets, variables)

trigger_codefresh_build

Trigger a new build for a specific pipeline

Example Prompts for Codefresh in OpenAI Agents SDK

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

"List all my Codefresh pipelines."

"Trigger the 'api-service-ci' pipeline on the 'develop' branch."

"Show me the status of my recent builds."

Troubleshooting Codefresh MCP Server with OpenAI Agents SDK

Common issues when connecting Codefresh 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.

Codefresh + OpenAI Agents SDK FAQ

Common questions about integrating Codefresh 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.