# Iris

> The agent eval standard for MCP. Score every agent output for quality, safety, and cost. 12 built-in eval rules cover completeness, relevance, safety (PII detection, prompt injection), and cost thresholds. Log traces with hierarchical spans, evaluate outputs inline, and track costs across all your agents. No SDK, no code changes — add one line to your MCP config. Open source, MIT licensed.

## Facts
- Page: https://tashan.sh/capability/plugin-iris-eval-mcp-server-iris
- tashan id: plugin:iris-eval/mcp-server/iris
- Source: https://github.com/iris-eval/mcp-server
- Type: plugin
- Category: security
- tashan score: 45.0 / 100
- Adoption: 19.0
- Upkeep: 75.0
- Freshness: 84.0
- Evidence coverage: 84% of the inputs this score can use
- Health: active
- Instruction depth: solid
- GitHub stars: 8
- License: MIT
- Official: no

## Install

```sh
/plugin marketplace add anthropics/claude-plugins-community
/plugin install iris@claude-community
```

## 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 2026-09-13 by tashan (https://tashan.sh) from public evidence. Scorer s5.