# Braintrust

> Use this tool when you need to evaluate and observe large language models (LLMs) programmatically, solving problems such as experiment tracking, log analysis, and result sharing. It provides inputs like SQL queries and API keys, and outputs like permalinks, summaries, and schema inferences. Ideal for use cases requiring automated LLM testing, validation, and collaboration in data science and AI development contexts.

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

## Description

Provides programmatic access to Braintrust, an LLM evaluations and observability platform. Supports semantic documentation search, SQL queries against experiments and logs, schema inference, experiment summarization, and resolving Braintrust object names and URLs. Generates permalinks for sharing results. Authenticates via OAuth or API key (Bearer token).

## Trust

- **Trust score (0–1):** 0.30
- **Verification tier:** unverified
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** database
- **Updated:** 2026-09-01

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/braintrust)

## 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": "braintrust"
    }
  }
}
```

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