How to Use the LangSmith MCP in Claude

Q: How do I view my LangSmith project metrics inside Claude Desktop?

Run langsmithlistprojects through the chat interface to pull your workspace stats. Claude Desktop displays the run counts and median latency directly in your conversation.

Q: Can Claude Desktop find a specific failing run in LangSmith?

Yes, you can ask your agent to search your projects using langsmithlistruns. Once it identifies the failed run, it uses langsmithgetrun to pull the exact error trace.

Debug LLM latency and token drift directly inside Claude Desktop using this LangSmith MCP Server.

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 Claude Desktop

Create your Vinkius account to connect LangSmith to Claude Desktop 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 Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit Project Health in Claude Desktop

`langsmith_list_projects` pulls aggregate metrics for your tracing environments right into your local chat interface. Your agent scans run counts and median latency across different workspaces to pinpoint where your LLM pipeline is slowing down. You don't have to keep a browser tab open to check if your production runs are spiking.

Pinpoint Latency Spikes Instantly

`langsmith_list_runs` retrieves recent execution data so you can check token consumption and execution status. Your desktop client parses these runs to find the exact step where an agentic loop stalled or failed. This makes debugging complex chains with your MCP client a matter of asking Claude Desktop to find the slowest run.

Inspect Trace Details and JSON Payloads

`langsmith_get_run` extracts the exact inputs, outputs, and metadata of any failing step. Your agent pulls these details directly into your workspace to reconstruct the failure state. You see the precise JSON payload without leaving your terminal or desktop app.

Setup guide

Set up LangSmith MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The LangSmith MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the LangSmith MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under langsmith-mcp.

json

{
  "mcpServers": {
    "langsmith-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Claude Desktop

Run `langsmith_list_projects` through the chat interface to pull your workspace stats. Claude Desktop displays the run counts and median latency directly in your conversation.

Yes, you can ask your agent to search your projects using `langsmith_list_runs`. Once it identifies the failed run, it uses `langsmith_get_run` to pull the exact error trace.

You only need to add the server configuration to your local `claude_desktop_config.json` file. The desktop app manages the stdio connection to execute the tools locally.

The server retrieves individual run IDs and nested steps using `langsmith_get_run`. Your desktop client maps the execution hierarchy so you can see where the chain broke.

Your API keys and tracing payloads remain inside the local V8 sandbox environment. Claude Desktop only communicates with the LangSmith endpoint to fetch trace data, keeping your telemetry private.

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