# world-model-mcp

> world-model-mcp — putervision-world-model-mcp. Use this tool when you need to create a persistent and immersive environment for AI agents, solving problems of entity tracking, object permanence, and collision simulation in 3D/2D spaces. It takes in spatial data and outputs simulated views and collision detections via a local SQLite interface. Use it in contexts where AI agents require a realistic and interactive world model to operate effectively.

Canonical page: https://skillsregistry.net/skills/putervision-world-model-mcp  
JSON: https://api.skillsregistry.net/v1/skills/putervision-world-model-mcp

## Description

🌐 Persistent 3D/2D spatial world model MCP server for AI agents. Entity tracking, object permanence, AABB collision simulation & view frustum projection via local SQLite.

## Trust

- **Trust score (0–1):** 0.61
- **Verification tier:** scanned
- **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/putervision/world-model-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": "putervision-world-model-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/putervision-world-model-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/putervision-world-model-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