How to Use the Coolify MCP in LangChain

Q: How does LangChain handle environment variables when configuring Coolify?

The agent reads configuration schemas with getserver, updates variables, and runs restartapplication to cycle container states and apply changes.

Deploy git commits and query database connection strings directly inside your LangChain multi-step reasoning chains.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Coolify MCP to LangChain

Create your Vinkius account to connect Coolify 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 Coolify with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Direct Git-to-Docker Deployments in LangChain

`trigger_deployment` initiates a git fetch, rebuilds Nixpacks images, and replaces the active container with the updated build. LangChain agents coordinate this tool call with `get_application` to check the mapped Traefik FQDN paths before declaring a deployment successful. You get immediate verification through LangSmith tracing when using this MCP integration. This setup means your agent watches the execution state, verifies the new container is running, and acts on errors without human intervention.

Dynamic Database Attachment and State Management

This MCP Server exposes configuration arrays to link newly provisioned web apps to backend datastores using `get_database`. Your agent pulls connection strings via `list_databases` and feeds them straight into down-chain tools. Manual copy-pasting of environment variables is no longer necessary. When configurations change, the agent fires `restart_application` to inject the new `.env` variables into runtime RAM instantly.

Automated Incident Response for Coolify Server Nodes

`stop_application` halts execution algorithms to suspend a mapped application during an active security incident. LangChain ReAct agents check server health using `list_servers` and `get_server` to verify SSH connection statuses. Security playbooks execute autonomously when an anomaly is detected. The agent isolates the compromised node, stops the target container, and logs the entire incident sequence to LangSmith.

Setup guide

Set up Coolify 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 Coolify 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({
    "coolify-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 Coolify 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 Coolify. 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 Coolify 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 Coolify MCP in LangChain

Install langchain-mcp-adapters and use the MultiServerMCPClient pointing to your Vinkius endpoint. Pass the tools directly to your agent executor to run server operations.

Yes. LangChain chains tool calls together, passing the application UUID from list_applications directly into trigger_deployment and verifying the status with get_application.

The agent reads configuration schemas with get_server, updates variables, and runs restart_application to cycle container states and apply changes.

Yes, you configure your agent constructor to only load specific tools like list_applications while omitting destructive ones like stop_application.

This server handles your Coolify API tokens, server IP properties, and database connection strings. Vinkius runs the server inside a zero-trust, ephemeral V8 Isolate sandbox to isolate your credentials.

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