# LangSmith

> Use this tool when you need to retrieve and analyze conversation data, experiment metrics, and billing usage from the LangSmith observatory platform. It solves problems related to conversation history tracking, experiment analysis, and organization-level billing management by providing inputs such as query filters and pagination options, and outputs like datasets, metrics, and usage reports. Ideal for use cases requiring in-depth conversation and experiment insights, LangSmith streamlines data retrieval and analysis to inform decision-making and optimization efforts.

Canonical page: https://skillsregistry.net/skills/langsmith  
JSON: https://api.skillsregistry.net/v1/skills/langsmith

## Description

Connects to the LangSmith observability platform to retrieve conversation history, prompts, traces and runs, datasets with examples, experiment metrics, and organization-level billing usage. Supports thread-based message retrieval with pagination, filtered run queries, and experiment analysis with latency, cost, and feedback metrics.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-04-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/langsmith)
- **Repository:** <https://github.com/langchain-ai/langsmith-mcp-server>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "langsmith"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/langsmith` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/langsmith/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt