How to Use the LangSmith MCP in Claude Code

Q: How do I add the LangSmith MCP Server to Claude Code?

Run claude mcp add --transport http -- in your terminal. Make sure all flags come before the server name so the config saves correctly to /.claude.json.

Pipe LangSmith MCP Server observability data directly into your terminal with Claude Code for headless trace debugging.

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 Code

Create your Vinkius account to connect LangSmith to Claude Code 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 Code

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Monitor Projects from the CLI

The `langsmith_list_projects` tool outputs your high-level tracing metrics straight to standard out. Claude Code fetches your project list, grabbing aggregate run counts, latency stats, and feedback scores. This fits perfectly into a morning SRE routine. You run a quick terminal command to check system health, and the agent pulls the latency metrics across all environments without you ever opening a browser tab.

Query Execution Runs Headless

The `langsmith_list_runs` tool extracts recent LLM executions for a specific project. Claude Code pulls the run names, execution statuses, token usage, and timing data. You can script this into a CI/CD pipeline. Have your GitHub Action trigger Claude Code to check the staging project for any failed runs after a deployment, automatically failing the build if the error rate spikes.

Debug Deep MCP Server Traces

The `langsmith_get_run` tool isolates a single trace ID and pulls the granular execution data. Claude Code retrieves the exact inputs, outputs, and intermediate tool calls of that specific run. When an alert fires at 2 AM, you just pipe the trace ID into your terminal. The agent reads the payload, identifies the timeout in the chain execution, and prints the root cause directly to your shell.

Setup guide

Set up LangSmith MCP in Claude Code

Prerequisites

Claude Code CLI installed (npm install -g @anthropic-ai/claude-code)
Active Vinkius subscription with a valid endpoint token

1

Run the add command

Open your terminal and run the command shown on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com. Use --scope user to make it available across all projects.
2

Verify the connection

Start a Claude Code session and type /mcp to list connected servers. You should see langsmith-mcp with a green status indicator.
3

Start using tools

Ask Claude Code something like "Check my latest LangSmith transactions." It will automatically discover and invoke the available LangSmith tools.

Terminal

claude mcp add --transport http langsmith-mcp https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

Get your connection token →

Prerequisites

Claude Code CLI installed
Active Vinkius subscription with a valid endpoint token

1

Open the config file

Create or edit .mcp.json in your project root for project-level scope, or ~/.claude.json for user-level scope.
2

Add the LangSmith MCP

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

Restart Claude Code

Start a new Claude Code session. Type /mcp to confirm the server is connected. The tools will be automatically available in your conversation.

.mcp.json

{
  "mcpServers": {
    "langsmith-mcp": {
      "type": "url",
      "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 Code

Run `claude mcp add --transport http -- ` in your terminal. Make sure all flags come before the server name so the config saves correctly to `~/.claude.json`.

Yes, if you script it. You can set up a cron job that triggers the agent to run the list projects tool and check the median latency stats against your SLAs.

That is exactly what it is built for. You can run it headless in a Docker container to validate that your integration tests didn't generate any failed LLM runs.

You instruct the agent on how you want the data. Tell it to output the trace inputs and token counts as a JSON object, and it formats standard out accordingly.

Your execution metadata, including raw token usage and model inputs, is routed through an ephemeral V8 Isolate Sandbox. Vinkius strips all state after the terminal session closes, guaranteeing strict data isolation.

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