How to Use the LangSmith (LLM Observability & Hub) MCP in Claude

Q: How do I see production logs using LangSmith (LLM Observability & Hub) in Claude Desktop?

You configure the server in your config file and use the listruns tool. This lets you pull recent invocation data into your conversation for immediate analysis. It turns your chat into a live observability dashboard.

Q: Can LangSmith (LLM Observability & Hub) help me debug prompt drift inside Claude Desktop?

Yes, you use listprompts to check your current templates against production history. You can then spot deviations in how models are being prompted. This allows for quick corrections before issues compound.

Q: How do I list my evaluation datasets in Claude Desktop using the LangSmith (LLM Observability & Hub) server?

Simply invoke the listdatasets tool. It returns a list of all current evaluation and fine-tuning sets. You can then pick the right dataset to validate your latest prompt changes.

Monitor your LLM production performance directly inside Claude Desktop by connecting the LangSmith (LLM Observability & Hub) 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 (LLM Observability & Hub) MCP to Claude Desktop

Create your Vinkius account to connect LangSmith (LLM Observability & Hub) 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 (LLM Observability & Hub) with Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trace every LLM interaction

Stop guessing why your prompts fail. Use `list_runs` to pull raw request and response data into your chat so you can inspect exactly what happened during a specific inference cycle. Once you find a problematic trace, call `get_run` to grab the precise telemetry. This gives you the full context you need to debug latency issues or unexpected model behaviors without leaving the app.

Audit prompt templates in real-time

Keep your prompts synced with what is actually running in production. Use `list_prompts` to view the templates stored in your hub and verify if your current configuration matches the deployed version. This keeps your experiments honest. You can compare production inputs against your stored templates to ensure your logic remains consistent as you iterate on new versions.

Manage your evaluation datasets

Organize your testing workflow by querying your current evaluation sets directly. The `list_datasets` tool exposes every testing suite you have built, making it easy to decide which batch to run against your latest changes. When you need human feedback, use `list_annotation_queues` to see what is waiting for review. You can quickly see which items require your eyes, ensuring you never miss a critical model evaluation.

Setup guide

Set up LangSmith (LLM Observability & Hub) 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 (LLM Observability & Hub) 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 (LLM Observability & Hub) 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-llm-observability-hub-mcp.

json

{
  "mcpServers": {
    "langsmith-llm-observability-hub-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 (LLM Observability & Hub) 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 (LLM Observability & Hub) MCP in Claude Desktop

You configure the server in your config file and use the `list_runs` tool. This lets you pull recent invocation data into your conversation for immediate analysis. It turns your chat into a live observability dashboard.

Yes, you use `list_prompts` to check your current templates against production history. You can then spot deviations in how models are being prompted. This allows for quick corrections before issues compound.

Your traces contain sensitive prompt and completion text. The server transmits this data directly to the LangSmith API endpoint you provide. Ensure your API key is scoped strictly to the projects you need to monitor.

Simply invoke the `list_datasets` tool. It returns a list of all current evaluation and fine-tuning sets. You can then pick the right dataset to validate your latest prompt changes.

The server processes raw run traces that may contain user-provided input. You should sanitize any PII locally before these traces reach the backend. Security depends on your implementation of client-side masking.

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