# Evals

> GitHub Action for evaluating MCP server tool calls using LLM-based scoring

## Facts
- Page: https://tashan.sh/capability/pkg-mcp-evals
- tashan id: pkg:mcp-evals
- Source: https://github.com/mclenhard/mcp-evals
- npm: https://www.npmjs.com/package/mcp-evals
- Type: npm
- Category: ai
- tashan score: 35.0 / 100
- Adoption: 68.0
- Upkeep: 44.0
- Freshness: 23.0
- Evidence coverage: 100% of the inputs this score can use
- Health: abandoned
- Instruction depth: not yet graded
- npm downloads: 68,731/week
- Official: no

## Install

```sh
claude mcp add evals -- npx -y mcp-evals
```

## Security audit
Not scanned. We audit npm-published capabilities; this one has no npm package we can resolve, or has not reached the queue. This is not a clean bill of health.

---
Measured 2026-08-08 by tashan (https://tashan.sh) from public evidence. Scorer s5.