LangSmith MCP Server for Claude
Connect Claude to LangSmith — retrieve conversation threads and traces, fetch and push prompts, browse evaluation datasets and experiments, and access billing usage — with the official LangSmith Model Context Protocol server from LangChain.
Open the source and read safety notes before installing.
Safety notes
- The server runs locally via `uvx` and connects to the LangSmith cloud API using your API key.
- The server provides read access to your traces, prompts, datasets, and experiments; it can also push prompts (write).
- Trace data may contain sensitive LLM inputs and outputs from your production systems — treat retrieved traces as confidential.
Privacy notes
- Conversation threads, prompt content, run inputs/outputs, and dataset examples are surfaced in Claude's context.
- LANGSMITH_API_KEY is a secret — store it in your environment or MCP client config, never in repositories.
Prerequisites
- A LangSmith API key from smith.langchain.com (free tier available).
- Python package manager `uv` installed (for `uvx`).
- An MCP client such as Claude Code or Claude Desktop.
Schema details
- Install type
- cli
- Troubleshooting
- No
- Scope
- Source repo
- Estimated setup
- 5 minutes
- Difficulty
- beginner
- Website
- https://smith.langchain.com
Full copyable content
{
"mcpServers": {
"langsmith": {
"command": "uvx",
"args": ["langsmith-mcp-server"],
"env": {
"LANGSMITH_API_KEY": "your-langsmith-api-key"
}
}
}
}About this resource
Overview
The LangSmith MCP Server is the official Model Context Protocol server from LangChain for
LangSmith. It gives Claude direct access to your LangSmith workspace — retrieving LLM run traces
with FQL filtering, fetching and pushing prompts, browsing evaluation datasets and experiments,
and accessing billing usage — through natural language. It runs locally via uvx and is
MIT-licensed.
Key capabilities
- Conversation threads — retrieve message history from LangSmith conversation threads with pagination.
- Prompts — list, fetch, and push prompts to and from your LangSmith prompt hub.
- Traces & runs — fetch LangSmith runs (traces, chains, tool calls) with FQL filter support.
- Datasets & examples — list and read evaluation datasets and their examples.
- Experiments — list experiment projects with metrics and evaluation results.
- Billing usage — retrieve organization-level billing usage data.
How it compares
| Server | LLM traces | Prompt management | Dataset access | Experiment metrics | Auth |
|---|---|---|---|---|---|
| LangSmith MCP | Yes | Yes (read+write) | Yes | Yes | API key |
| Weights & Biases MCP | Yes | Limited | Yes | Yes | API key |
| MLflow MCP | Yes | Limited | Yes | Yes | Token |
| Arize MCP | Yes | No | Limited | Limited | API key |
LangSmith's MCP is notable for combining trace retrieval with bidirectional prompt management — you can read production traces and push improved prompts back to the hub in the same session.
Installation
Claude Code
claude mcp add langsmith \
-e LANGSMITH_API_KEY=your-key \
-- uvx langsmith-mcp-server
Claude Desktop
{
"mcpServers": {
"langsmith": {
"command": "uvx",
"args": ["langsmith-mcp-server"],
"env": {
"LANGSMITH_API_KEY": "your-langsmith-api-key"
}
}
}
}
Multi-workspace
{
"env": {
"LANGSMITH_API_KEY": "your-key",
"LANGSMITH_WORKSPACE_ID": "your-workspace-id"
}
}
Custom endpoint (self-hosted LangSmith)
Set LANGSMITH_ENDPOINT to your self-hosted LangSmith URL.
Requirements
- A LangSmith API key (free tier available at smith.langchain.com).
uvinstalled (pip install uvorbrew install uv).- An MCP client (Claude Code or Claude Desktop).
Security
- The server only reads (and optionally writes prompts to) your LangSmith workspace.
- Treat
LANGSMITH_API_KEYas a secret. - Trace data may include sensitive LLM inputs and outputs from your applications — use this in trusted environments only.
Source Verification Notes
Verified on 2026-06-18:
- The official repository
github.com/langchain-ai/langsmith-mcp-server(MIT) documents theuvx langsmith-mcp-serverinstall command,LANGSMITH_API_KEYandLANGSMITH_WORKSPACE_IDenv vars, stdio transport, and the six capability areas (threads, prompts, runs, datasets, experiments, billing). - LangChain's LangSmith MCP documentation at
docs.langchain.com/langsmith/langsmith-mcp-serverconfirms the server features and setup instructions. - Claude Code's MCP documentation describes the
-eenv var injection pattern used above.
Source citations
Add this badge to your README
How it compares
LangSmith MCP Server for Claude side by side with 3 alternatives on trust, install, platform support, and disclosed safety notes — all from reviewed registry metadata.
| Field | LangSmith MCP Server for Claude Connect Claude to LangSmith — retrieve conversation threads and traces, fetch and push prompts, browse evaluation datasets and experiments, and access billing usage — with the official LangSmith Model Context Protocol server from LangChain. Open dossier | Arize Phoenix MCP Server for Claude Inspect LLM traces and spans, manage prompts, explore datasets, and review evaluation experiments from Claude — with the official Arize Phoenix MCP server, built into the open-source Phoenix AI observability platform. Open dossier | Opik MCP Server for Claude Debug, evaluate, and monitor LLM applications from Claude — read traces and spans, score outputs, save prompts, run evaluation experiments, and query project metrics — with the official Opik MCP server by Comet. Open dossier | OpenTelemetry MCP Server for Claude Analyze distributed traces and LLM observability data from Claude — search traces and spans, find errors, list services, analyze LLM token usage, identify slow LLM operations, and discover AI model usage patterns — with the OpenTelemetry MCP server supporting Jaeger, Grafana Tempo, and Traceloop backends. Open dossier |
|---|---|---|---|---|
| Trust | ||||
| Install risk | Review first | Review first | Review first | Review first |
| Notes | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ | Safety ✓ Privacy ✓ |
| Category | mcp | mcp | mcp | mcp |
| Source | source-backed | source-backed | source-backed | source-backed |
| Author | LangChain | Arize AI | Comet | Traceloop |
| Added | 2026-06-18 | 2026-06-18 | 2026-06-18 | 2026-06-18 |
| Platforms | Claude CodeCodexCursorClaude Desktop | Claude CodeClaude Desktop | Claude CodeClaude Desktop | Claude CodeClaude Desktop |
| Source repo | — | — | — | — |
| Safety notes | ✓The server runs locally via `uvx` and connects to the LangSmith cloud API using your API key. The server provides read access to your traces, prompts, datasets, and experiments; it can also push prompts (write). Trace data may contain sensitive LLM inputs and outputs from your production systems — treat retrieved traces as confidential. | ✓The `write` and upsert tools can create or modify prompts and add dataset examples — review Claude's proposed changes before confirming. For self-hosted deployments, ensure your Phoenix instance is accessible from the machine running the MCP server. | ✓The `write` tool can create traces, spans, scores, and prompts in your Opik workspace — review any write operations before confirming. The `run_experiment` tool executes evaluation experiments end-to-end, which may incur LLM API costs depending on your experiment configuration. | ✓All tools are read-only — the server queries trace data but does not modify your application or tracing backend. Trace data may contain sensitive information (request parameters, user IDs, SQL queries) — ensure Claude has appropriate access to this data. |
| Privacy notes | ✓Conversation threads, prompt content, run inputs/outputs, and dataset examples are surfaced in Claude's context. LANGSMITH_API_KEY is a secret — store it in your environment or MCP client config, never in repositories. | ✓LLM traces (including prompts and completions), evaluation annotations, session data, datasets, and experiment results from your Phoenix workspace are surfaced in Claude's context. Your `PHOENIX_API_KEY` is passed as an environment variable — store it in a secrets manager rather than plaintext shell config. | ✓LLM traces (including prompts and completions), evaluation scores, experiment results, and prompt library contents from your Opik workspace are surfaced in Claude's context. Your `OPIK_API_KEY` is passed as an environment variable — store it in a secrets manager rather than plaintext shell config. | ✓Distributed trace content including service names, operation names, error messages, HTTP parameters, and LLM prompt/response metadata may be surfaced in Claude's context. For Traceloop backend, `BACKEND_API_KEY` is required and grants access to your Traceloop organization's trace data. |
| Prerequisites |
|
|
|
|
| Install | | | | |
| Config | | | | |
| Citations | ||||
| Claim | Unclaimed | Unclaimed | Unclaimed | Unclaimed |
Signals
Loading live community signals…
A short, calm digest of reviewed Claude resources. Unsubscribe any time.