Langsmith

v1.0.0Monitoring & Observabilitystable

Enables language models to access LangSmith observability platform features including fetching conversation history, managing prompts, retrieving traces and runs, working with datasets and examples, and analyzing experiments.

langsmithmcpai-integration
Share:
112
Stars
0
Downloads
0
Weekly
0/5

What is Langsmith?

Langsmith is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to enables language models to access langsmith observability platform features including fetching conversation history, managing prompts, retrieving traces and runs, working with datasets and examples, a...

Enables language models to access LangSmith observability platform features including fetching conversation history, managing prompts, retrieving traces and runs, working with datasets and examples, and analyzing experiments.

This server falls under the Monitoring & Observability category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • Enables language models to access LangSmith observability pl

Use Cases

Monitor and analyze language model application performance and behavior.
Access conversation history, prompts, and experiments from LangSmith.
langchain-ai

Maintainer

LicenseMIT
Languagepython
Versionv1.0.0
UpdatedMay 19, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx langsmith

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Langsmith

The LangSmith MCP server gives AI assistants direct access to LangSmith's observability and evaluation platform for LLM applications. It exposes tools to fetch conversation thread history, list and push prompts, query traces and runs with filter expressions, manage datasets and examples, run experiments, and retrieve billing usage data. Teams use it to let AI agents analyze application performance, debug failing traces, compare experiment results, and manage prompt libraries without leaving their AI chat interface.

Prerequisites

  • Python 3.9 or higher with uv package manager installed (https://astral.sh/uv)
  • A LangSmith account and API key from https://smith.langchain.com (Settings > API Keys)
  • An MCP-compatible client such as Claude Desktop
  • Optional: a LangSmith workspace ID if using a multi-workspace API key
1

Install uv package manager

The LangSmith MCP server is run with uv/uvx. Install uv if you do not already have it. This is the recommended way to run the server without managing a separate Python environment.

curl -LsSf https://astral.sh/uv/install.sh | sh
2

Obtain your LangSmith API key

Log in to https://smith.langchain.com, go to Settings, and create a new API key. The key is required for the server to authenticate with the LangSmith platform.

3

Configure your MCP client

Add the LangSmith MCP server to your MCP client configuration using uvx. Set your API key as an environment variable. The workspace ID and endpoint are optional unless you use a multi-workspace setup.

{
  "mcpServers": {
    "langsmith": {
      "command": "uvx",
      "args": ["langsmith-mcp-server"],
      "env": {
        "LANGSMITH_API_KEY": "your_langsmith_api_key",
        "LANGSMITH_WORKSPACE_ID": "optional_workspace_id",
        "LANGSMITH_ENDPOINT": "optional_custom_endpoint"
      }
    }
  }
}
4

Optional: Enable LangSmith tracing for the server itself

To monitor the MCP server's own tool calls within LangSmith, set the monitoring environment variables. This creates traces in LangSmith showing every tool the server executes.

# Add to the env section of your MCP config:
# "LANGSMITH_TRACING": "true"
# "LANGSMITH_MONITORING_API_KEY": "your_key"
# "LANGSMITH_MONITORING_PROJECT": "mcp-server-monitoring"
5

Test the connection

Ask your AI assistant to list projects or fetch recent runs. A successful response confirms the API key is valid and the server has access to your LangSmith workspace.

Langsmith Examples

Client configuration

Claude Desktop configuration using uvx to run the LangSmith MCP server with an API key.

{
  "mcpServers": {
    "langsmith": {
      "command": "uvx",
      "args": ["langsmith-mcp-server"],
      "env": {
        "LANGSMITH_API_KEY": "your_langsmith_api_key"
      }
    }
  }
}

Prompts to try

These prompts use the LangSmith MCP tools to inspect traces, manage prompts, and analyze experiments.

- "Fetch the conversation history from thread ID thread-abc123"
- "List all prompts in my LangSmith workspace"
- "Show me recent runs in the production project that had errors"
- "List all datasets of type chat in my workspace"
- "Get billing usage for my LangSmith account for the past 30 days"
- "Run the experiment named baseline-eval and show me the results"

Troubleshooting Langsmith

Authentication error when the server starts

Verify LANGSMITH_API_KEY is correctly set. The key must not have extra whitespace. If using a multi-workspace key, also set LANGSMITH_WORKSPACE_ID to the target workspace identifier found in your LangSmith workspace settings.

uvx command not found when starting the server

Install uv with `curl -LsSf https://astral.sh/uv/install.sh | sh` and restart your terminal. Then find the full path with `which uvx` and use the absolute path in the MCP config's 'command' field.

Tool calls return empty results even though data exists in LangSmith

Check that your API key has access to the correct workspace. Use LANGSMITH_WORKSPACE_ID to explicitly target the right workspace. Also verify that filters passed to fetch_runs or list_examples use correct LangSmith FQL syntax.

Frequently Asked Questions about Langsmith

What is Langsmith?

Langsmith is a Model Context Protocol (MCP) server that enables language models to access langsmith observability platform features including fetching conversation history, managing prompts, retrieving traces and runs, working with datasets and examples, and analyzing experiments. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Langsmith?

Follow the installation instructions on the Langsmith GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Langsmith?

Langsmith works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Langsmith free to use?

Yes, Langsmith is open source and available under the MIT license. You can use it freely in both personal and commercial projects.

Browse More Monitoring & Observability MCP Servers

Explore all monitoring & observability servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "langsmith": { "command": "npx", "args": ["-y", "langsmith"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Langsmith?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides