How to Use the Metorial MCP in LangChain

Q: Can I monitor Metorial tool execution directly from LangSmith?

Yes. Every time your LangChain agent runs metorialinvokeservertool, the execution details are captured. You can fetch these via metorialgettracedetails and push them into LangSmith for a single, unified view of your pipeline's health.

Build LangChain pipelines that deploy, run, and trace serverless MCP instances on the fly without breaking your budget.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Metorial MCP to LangChain

Create your Vinkius account to connect Metorial 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 Metorial with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Serverless Deploys with LangChain Agents

Your agent uses `metorial_deploy_server` to spin up a fresh, sandboxed MCP Server on the fly. This lets you build chains that provision their own tools dynamically. When the agent finishes its run, it hits `metorial_delete_server` to tear the whole thing down. This keeps your LangChain workflows completely ephemeral and stops idle cloud spend from quietly eating your budget.

Trace Tool Executions inside LangSmith

Your agent pulls raw execution records using `metorial_get_trace_details` to feed them straight into LangSmith. You see exactly which tool call lagged and why. We expose transaction logs through `metorial_list_traces` so your agent can self-correct when a tool returns bad data. No more blind debugging—just clean, traceable pipelines that fix themselves.

Analyze Live Pipeline Costs in Your Chain

By invoking `metorial_get_usage_metrics` mid-run, your agent checks active memory usage and execution times to decide if it needs to throttle requests. This keeps your LangChain pipelines running lean. If the metrics look ugly, the agent queries `metorial_list_servers` to find healthier endpoints. You get direct control over your MCP compute costs without writing complex monitoring scripts.

Setup guide

Set up Metorial 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 Metorial 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({
    "metorial-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 Metorial 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 Metorial. 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 Metorial 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 Metorial MCP in LangChain

We keep a pool of warm sandboxes ready. When your LangChain agent triggers `metorial_deploy_server`, we spin it up in under 1.5 seconds, avoiding the typical multi-second lags that break agentic loops.

Yes. Every time your LangChain agent runs `metorial_invoke_server_tool`, the execution details are captured. You can fetch these via `metorial_get_trace_details` and push them into LangSmith for a single, unified view of your pipeline's health.

You write a cleanup step at the end of your chain. Have your LangChain agent call `metorial_list_servers` to find idle instances, then run `metorial_delete_server` to kill them off instantly.

The platform records the failure details immediately. You can use `metorial_get_server_status` to check if the node is still healthy or if you need to redeploy a fresh instance.

Your execution logs and traces never touch a persistent public database. We isolate each run in an ephemeral V8 sandbox, meaning once your session ends, the trace details are permanently wiped from our active memory.

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