How to Use the Codefresh MCP in LangChain

Run Codefresh pipeline steps and inspect build statuses inside your LangChain reasoning loops.

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 LangChain

Create your Vinkius account to connect Codefresh to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Codefresh pipeline checks with LangChain agents

Your LangChain agent can grab pipeline blueprints using `get_pipeline_configuration` and instantly feed that structural data into the next step of your chain. This lets your agent inspect how a deployment is wired up before making any decisions about running it. Instead of writing custom glue code, you pass the output of `list_codefresh_pipelines` straight into your LLM chain to decide which branch to build. This turns static CI/CD scripts into dynamic, context-aware deployment decisions.

Trace build triggers with LangSmith and this MCP Server

Triggering builds becomes a traceable step when you connect this MCP server to your LangChain setup. Running `trigger_codefresh_build` fires off the workflow, while LangSmith logs the exact input parameters, latency, and token cost of that tool call. If a build fails, your agent catches the error, calls `get_build_execution_details` to find the exact bottleneck, and logs the whole debugging session. You get a clean audit trail of exactly why your agent kicked off a build and how it responded to the logs.

Map environments and clusters in multi-step chains

Manage your Kubernetes setups by letting your agent query `list_delivery_clusters` and `list_shared_contexts` in a single run. The agent grabs the active cluster list, checks the shared environment variables, and configures the environment for the next job. This makes setting up staging environments simple. Your chain inspects the target cluster status, pulls the required secrets, and updates the deployment pipeline without manual intervention.

Setup guide

Set up Codefresh MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes Codefresh tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "codefresh-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent Codefresh transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

Install the adapter packages and use the MultiServerMCPClient to fetch the tools. You then pass client.get_tools() directly into your agent constructor to let it run commands like triggering builds.

Yes, LangSmith tracks every tool call made by this MCP server. You can see the exact execution time for get_build_execution_details and check if API latency is slowing down your agent.

The MultiServerMCPClient aggregates tools from this server alongside other MCP endpoints. Your agent can query database servers and then immediately use trigger_codefresh_build in the same chain.

Yes, the connection is stateless by default. If you need to maintain build history or user context across multiple steps, use client.session() to keep the session alive.

All pipeline definitions, build logs, and cluster metadata stay in your local environment. Vinkius runs this server inside an isolated sandbox, meaning your API tokens and build details are never stored or exposed to third parties.

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