# nethack-mcp

> nethack-mcp — christoph-d-nethack-mcp. Use this tool when you need to enable a Large Language Model (LLM) to play the game of Nethack, providing an interface for the LLM to interact with the game and receive outputs on game state. It solves the problem of integrating LLMs with the classic game of Nethack, allowing for automated gameplay and strategy testing. The tool accepts LLM inputs and generates game-related outputs, ideal for use cases involving AI-driven game exploration and decision-making.

Canonical page: https://skillsregistry.net/skills/christoph-d-nethack-mcp  
JSON: https://api.skillsregistry.net/v1/skills/christoph-d-nethack-mcp

## Description

MCP tool to let an LLM play nethack

## Trust

- **Trust score (0–1):** 0.97
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **License:** AGPL-3.0
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/Christoph-D/nethack-mcp)

## 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": "christoph-d-nethack-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/christoph-d-nethack-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/christoph-d-nethack-mcp/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