How to Use the Laravel Forge MCP in LangChain

Q: Can I trace Laravel Forge tool calls in LangChain using LangSmith?

Yes, every time LangChain invokes a tool like deploysite, the input parameters and response payloads are logged as a node in your trace. You monitor execution speed and pinpoint issues when deployments fail.

Q: How does the Laravel Forge toolset integrate with LangChain agents?

You call client.gettools() on your MCP adapter and pass the resulting tool list directly to createagent. The agent then dynamically decides whether to list servers, check sites, or run deployments based on your prompt.

Run multi-step LangChain pipelines to deploy code and query Laravel Forge server states directly from your agent.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Laravel Forge MCP to LangChain

Create your Vinkius account to connect Laravel Forge 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 Laravel Forge with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain deployments with real-time LangChain telemetry

The `deploy_site` tool triggers a deployment script queue to run on a specific repository site. When you wire this into a LangChain run, your agent kicks off a build and immediately checks the progress in subsequent chain steps. Using LangSmith, you trace the exact latency of the deployment call and inspect the API payload. This setup prevents silent failures because each tool execution is recorded as a trace link.

Inspect server environments in LangChain agent loops

The `list_servers` tool returns the master list of all connected Forge servers in your account. Your agent uses this output to decide which droplet to query next in the execution path. By feeding this server list into a second step using `get_server`, the chain automatically gathers droplet configurations. No manual scripting is required to pass server IDs between API calls.

Manage database states through LangChain MCP Server

The `list_databases` tool lists active databases mounted on a specific Forge server. Your agent inspects this list to verify database names before running migrations or setting up new environments. Integrating this MCP Server with LangChain lets you combine database checks with other tools in your pipeline. You easily construct a chain that checks database existence before executing code updates.

Setup guide

Set up Laravel Forge 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 Laravel Forge 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({
    "laravel-forge-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 Laravel Forge 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 Laravel Forge. 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 Laravel Forge 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 Laravel Forge MCP in LangChain

You use the MultiServerMCPClient from the langchain-mcp-adapters package to aggregate multiple MCP Server endpoints. This allows your LangChain agent to query Laravel Forge alongside other development tools in a single session.

Yes, every time LangChain invokes a tool like `deploy_site`, the input parameters and response payloads are logged as a node in your trace. You monitor execution speed and pinpoint issues when deployments fail.

You call client.get_tools() on your MCP adapter and pass the resulting tool list directly to create_agent. The agent then dynamically decides whether to list servers, check sites, or run deployments based on your prompt.

The error is returned directly to the agent as a tool output, allowing the chain to handle the failure. Your agent then reads the error message and executes a fallback tool, like checking server logs.

The server processes your API token inside a secure V8 Isolate Sandbox on Vinkius, meaning your credentials and server metadata never persist. Only the raw JSON responses, such as database lists and site configurations, are exposed to your local agent.

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