# io.github.iris-eval/mcp-server

> Use this tool when you need to evaluate the performance of AI agents, specifically in the context of MCP (Multi-Agent Cooperation and Competition) environments. It scores agent outputs based on quality, safety, and cost, providing a standardized assessment of agent effectiveness. Ideal for use cases where agent performance needs to be measured and optimized in complex, dynamic environments.

Canonical page: https://skillsregistry.net/skills/io-github-iris-eval-mcp-server  
JSON: https://api.skillsregistry.net/v1/skills/io-github-iris-eval-mcp-server

## Description

The agent eval standard for MCP. Score every agent output for quality, safety, and cost.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** unverified

## Facts

- **Version:** 0.1.3
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-04-19

## Source

- **Source listing:** [MCP Registry](https://registry.modelcontextprotocol.io/v0/servers/io.github.iris-eval%2Fmcp-server)
- **Repository:** <https://github.com/iris-eval/mcp-server>

## 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": "io-github-iris-eval-mcp-server"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/io-github-iris-eval-mcp-server` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/io-github-iris-eval-mcp-server/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