iris
Iris v0.4.4
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 thr...
From the developer
License
MIT
Works with
Claude Code
Description
From the marketplace listing
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.
What changed
No changes recorded yet. Follow this plugin to keep track of future changes.
Similar plugins
Find competitors to follow as you develop your plugin.
-
Russian text quality plugin. Auto-activates on Russian text output and applies ~1,040 rules across typography, information style, editori...
Shared terms: output, quality, rule, standard
-
Safety for Agents - Agent Detection & Response (ADR) for AI agents
Shared terms: detection, safety, agent
-
The MCP-native AI API gateway for developers building with LLMs. Every app using AI needs API keys, cost control, and provider flexibilit...
Shared terms: cost, mcp, open, track
-
Generate ready-to-paste Claude Code prompts with the right agent, orchestration pattern, and safety rails. Orchestrator synthesises patte...
Shared terms: safety, agent, hierarchical, open
-
Output.ai workflow development toolkit for Claude Code. Adds 5 specialist agents (planner, builder, debugger, prompt writer, quality revi...
Shared terms: output, quality, agent, sdk
Keywords
Files & skills
iris · catalog manifest
Saved declaration
{}
iris · catalog manifest
Saved declaration
{
"name": "iris",
"source": {
"sha": "b83394823c50242779dd16729e2866e32a1af044",
"url": "https://github.com/iris-eval/mcp-server.git",
"source": "url"
},
"homepage": "https://iris-eval.com",
"description": "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."
}
iris · catalog manifest
Saved declaration
{
"name": "iris",
"author": {
"url": "https://github.com/iris-eval",
"name": "Iris",
"email": "hello@iris-eval.com"
},
"license": "MIT",
"version": "0.4.4",
"homepage": "https://iris-eval.com",
"keywords": [
"eval",
"evaluation",
"mcp",
"quality",
"safety",
"cost",
"agent",
"scoring"
],
"repository": "https://github.com/iris-eval/mcp-server",
"description": "The agent eval standard for MCP. Score every agent output for quality, safety, and cost."
}
plugin.json observed Nov 6, 2026 · 10:45 UTC. Manifest source ↗
Catalog declarations and available plugin.json metadata are saved. Referenced skills and executable source files are not downloaded or tested. Missing components in a manifest do not prove that the plugin has none.
Installation instructions
Community
/plugin marketplace add anthropics/claude-plugins-community
/plugin install iris@claude-communityTechnical details
- Sources
- Community
- First seen
- Oct 3, 2026 · 22:13 UTC
- Last seen
- Nov 7, 2026 · 18:00 UTC
- Latest observed change
- Oct 3, 2026 · 22:13 UTC
- Collection status
- Listed
- Reported installs
- Not provided
Installation counts are source-reported, not independently verified active users. Observation dates are not release dates.
Download plugin data (JSON)Plugin history: freshly prepared. Prepared . Refreshed when catalog data changes or after 6 hours. Your account and Follow status are live.