# MCP-Atlas

> MCP-Atlas — anigg-eth-mcp-atlas-rl. Use this tool when you need to assess AI agents' ability to utilize tools effectively in real-world scenarios. The MCP-Atlas benchmark evaluates competency across 36 MCP servers, providing a comprehensive and reproducible testing environment with Docker sandbox and LLM-as-judge scoring. Ideal for use cases requiring evaluation of AI tool-use proficiency, such as testing AI agents' problem-solving capabilities in complex, dynamic environments.

Canonical page: https://skillsregistry.net/skills/anigg-eth-mcp-atlas-rl  
JSON: https://api.skillsregistry.net/v1/skills/anigg-eth-mcp-atlas-rl

## Description

A large-scale benchmark that evaluates AI agents' tool-use competency across 36 real MCP servers using a reproducible Docker sandbox and LLM-as-judge scoring.

## Trust

- **Trust score (0–1):** 0.24
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** cloud-infra
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/j5y7dptpc5)
- **Repository:** <https://github.com/AniGG-Eth/mcp-atlas-rl>

## 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": "anigg-eth-mcp-atlas-rl"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/anigg-eth-mcp-atlas-rl` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/anigg-eth-mcp-atlas-rl/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