Is Iris safe and trustworthy?

tashan scores Iris on public evidence — tashan score 45.0/100, it is currently active. Audit scope: OSV advisories, install-time scripts, build provenance and declared permission surface. We do not review source code or execute the capability.

How do I install Iris?

Configure it from its source repository — it is a remote / registry server.

2 GitHub contributors, source: iris-eval/mcp-server.

‹ The Index

Iris

plugin

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.

Works with: Claude Code (native)
native: this artifact type is that client's own format

Category: Security — see all ranked ›

Work: Model evaluation · Observability

Who it is for: AI engineer · DevOps / SRE

Install (Claude Code):

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

solid

“5 worked examples; short of deep on per-tool docs; read with 1 linked doc(s)”

This grade is wrong ›

tashan score: 45.0
Instruction depth: 64.0 (solid — documents the job properly, with examples you could follow)
Adoption: 1 repos
Upkeep: 75.0
Freshness: 84.0
Evidence coverage: 84% of the inputs this score can use — the rest are unknown, and the score is discounted for it
Health: active
GitHub stars: 8
Contributors: 2
License: MIT

Security audit

Not scanned yet. We audit npm-published capabilities for known advisories, install-time scripts and permission surface; this one has no npm package we can resolve, or has not reached the queue.

You searched for one. Check the rest of your stack:

npx tashan-cli doctor

Reads the config already on your machine and names what is dead, deprecated or running code at install time. No account, nothing uploaded.

tashan Pro$6/mo

Iris scores 45 today. Pro keeps the series, so you can see whether that is a project getting better or one on its way down.

The whole series behind any row, back to the first day we measured it
The replacement, named — not just the news that something died
tashan doctor over your own config, on your own machine

Start a 7-day trial › Everything measured on this page stays free.

Show your score

Measured this well? Put the live badge in your README — it updates as the score does.

[![tashan](https://tashan.sh/badge/plugin-iris-eval-mcp-server-iris.svg)](https://tashan.sh/capability/plugin-iris-eval-mcp-server-iris.html)

source ↗ · plugin:iris-eval/mcp-server/iris

Everything on this page is public evidence and free. What it cannot know is whether you run this — check your whole config, free, in the browser. tashan Pro adds the series behind each row and names a replacement for anything dying.

Already running this? Check your whole config — free, in your browser, nothing installed. Or npx tashan-cli doctor locally, which sends nothing at all.

Measured 2026-09-13 · scorer s5 · how · something wrong here?