# ConduitMCP

> ConduitMCP — advik-b-conduitmcp. Use this tool when you need to integrate AI agents with the Godot game engine, enabling undo-safe scene editing, gameplay, input injection, frame capture, and debugging. ConduitMCP provides a native in-process MCP server for seamless interaction between AI agents and Godot scenes. Ideal for AI-powered game development, testing, and debugging workflows.

Canonical page: https://skillsregistry.net/skills/advik-b-conduitmcp  
JSON: https://api.skillsregistry.net/v1/skills/advik-b-conduitmcp

## Description

Native in-process MCP server for Godot: AI agents edit scenes undo-safely, play the game, inject input, capture frames, and debug.

## Trust

- **Trust score (0–1):** 0.74
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/Advik-B/ConduitMCP)

## 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": "advik-b-conduitmcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/advik-b-conduitmcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/advik-b-conduitmcp/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