# Braintrust

> Use this tool when you need to evaluate and observe AI experiments, logs, datasets, and prompts in a unified platform. Braintrust solves problems of AI model transparency and reproducibility by providing a query-based interface to access and analyze experiment data. It takes in experiment logs, datasets, and prompts as inputs and outputs actionable insights and visualizations to inform AI model development and optimization.

Canonical page: https://skillsregistry.net/skills/io-github-braintrustdata-braintrust  
JSON: https://api.skillsregistry.net/v1/skills/io-github-braintrustdata-braintrust

## Description

AI evaluation and observability platform — query experiments, logs, datasets, and prompts.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-05-03

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/io.github.braintrustdata%2Fbraintrust)

## Use it

MCP endpoint published by the skill: `https://api{region}.braintrust.dev/mcp`

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": "io-github-braintrustdata-braintrust"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/io-github-braintrustdata-braintrust` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/io-github-braintrustdata-braintrust/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