What is langsmith-mcp-server CLAUDE.md?

Project instructions for a LangSmith MCP server. LangSmith is a platform for tracking, testing, and managing applications that use large language models, while MCP connects agents to external tools.

Use them when developing the server or working with its conversation tracking, prompt management, datasets, and trace-analysis integrations.

They document the server’s purpose, architecture, configuration, and the need to keep the instructions updated as tools or dependencies change.

How langchain-ai/langsmith-mcp-server configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to langchain-ai/langsmith-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/langchain-ai/langsmith-mcp-server/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/langchain-ai/langsmith-mcp-server

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/langchain-ai/langsmith-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/langchain-ai/langsmith-mcp-server/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/langchain-ai/langsmith-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/langchain-ai/langsmith-mcp-server/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/langchain-ai/langsmith-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/langchain-ai/langsmith-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 6,401 This file is loaded in full into every session.

When invoked 6,401 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.06401	$0.06401
Opus 5.5	$0.02560	$0.02560
Sonnet 5.5	$0.01280	$0.01280
Haiku 4.5	$0.00640	$0.00640

Measured 2mo ago against content hash 17e4792f502e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

langsmith-mcp-server CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 653 lines

How it starts

The opening of the file, as written. The whole thing — 653 lines — stays where its author put it; the contents beside it link to each section on GitHub.

LangSmith MCP Server - Technical Reference & Development Guide

⚠️ IMPORTANT: Keeping This Document Updated

When you make changes to this codebase, please update this CLAUDE.md file if:

You add or remove MCP tools
You modify the architecture or add new modules
You change configuration requirements or setup procedures
You add new dependencies or change build processes
You discover important patterns or best practices

This document serves as the primary context for AI assistants working on this project. Keeping it accurate ensures efficient development.

Project Overview

The LangSmith MCP Server is a production-ready Model Context Protocol (MCP) server that provides seamless integration with the LangSmith observability platform. This server enables AI language models to programmatically interact with LangSmith's suite of tools for conversation tracking, prompt management, dataset operations, and trace analytics.

What is LangSmith?

LangSmith is LangChain's comprehensive observability and evaluation platform for LLM applications, providing:

Conversation thread tracking and history
Prompt template management and versioning
Dataset creation and management for testing
Trace collection and analysis for debugging
Performance analytics and monitoring
Billing and usage tracking

What is MCP?

The Model Context Protocol (MCP) is an open standard that enables secure connections between AI assistants and external data sources and tools. This server implements the MCP specification to bridge AI models with LangSmith's capabilities.

Architecture Deep Dive

Core Components

1. Server Architecture (server.py)

The server is built on FastMCP, a high-performance MCP framework that provides:

Transport Layer: Uses stdio transport for CLI/desktop integration, HTTP for web-based access
Tool Registration: Modular system for registering LangSmith tools via register_tools()
Middleware Stack: API key authentication and CORS handling
Error Handling: Comprehensive exception handling across all operations

Read the full file on GitHub · 653 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 653 lines · 6,401 tokens per session scan A 17e4792f502e

Subscribe to this mod's changes

langsmith-mcp-server CLAUDE.md is an instructions file published in the GitHub repository langchain-ai/langsmith-mcp-server (130 stars, last pushed 2mo ago), licensed MIT. It adds 6,401 tokens to every session, about $0.0256 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Analytics and metrics Building agents

langsmith-mcp-server CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
langsmith-mcp-server CLAUDE.mdlangchain-ai/langsmith-mcp-server	Instructions file	130	2mo ago	MIT	A	6,401	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	today	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

langsmith-mcp-server: Instructions file for Claude Code