How to Use the LangSmith MCP in LangChain

Use LangSmith with LangChain to track your agent's reasoning chains and debug every step of your multi-step pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LangSmith MCP to LangChain

Create your Vinkius account to connect LangSmith 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 LangSmith with LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trace your LangChain agent execution paths

The `langsmith_list_runs` tool pulls recent execution history directly into your chain. You see exactly where your agent took a detour or hit a wall. This visibility turns your black-box agents into transparent sequences. You catch errors in the logic before they reach your end users.

Monitor LangChain project performance metrics

Call `langsmith_list_projects` to view aggregate latency and token usage across your entire workspace. It shows you which chains are hogging resources. Data-driven optimization starts here. You identify the bottlenecks in your pipeline and adjust your agent logic to keep response times within your SLA.

Debug specific LangChain agent decisions

Use `langsmith_get_run` to inspect the raw input and output of any single tool call. It gives you a granular look at what your agent actually processed. Stop guessing why a chain failed. You get the full context of the failure, including the specific prompt and tool response that caused the issue.

Setup guide

Set up LangSmith 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 LangSmith 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({
    "langsmith-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 LangSmith 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 LangSmith. 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 LangSmith 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 LangSmith MCP in LangChain

You start by listing your recent runs to identify the failing trace ID. Once you have the ID, you pull the full details to inspect the chain execution. This workflow pinpoints exactly where your LangChain logic deviated from the expected path.

Yes. Each run retrieved via this MCP Server includes token counts for every step of your LangChain process. You see the consumption for both prompt and completion, allowing for precise cost tracking.

Tracing happens asynchronously, so your core agent logic stays fast. You only pull the telemetry when you need to inspect the data during debugging or post-process evaluation.

It does. You use the project listing tool to switch between different environments and track performance across your entire development lifecycle.

The server only touches your trace metadata, such as latency, token counts, and tool execution history. Your proprietary source code and raw API keys remain entirely outside of this observability loop.

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