# pymcp

> pymcp — activeinferenceinstitute-pymcp. Use this tool when you need to build and interact with generative models, infer states and policies, or simulate agents in environments. It solves problems in active inference and decision-making by providing a REST API and Model Context Protocol interface for inputs and outputs. This tool is ideal for AI agents and applications requiring model-based reasoning and simulation capabilities.

Canonical page: https://skillsregistry.net/skills/activeinferenceinstitute-pymcp  
JSON: https://api.skillsregistry.net/v1/skills/activeinferenceinstitute-pymcp

## Description

Exposes the PyMDP active-inference library to AI agents and applications over the Model Context Protocol and a plain REST API: build generative models, infer states and policies, and simulate agents in environments

## Trust

- **Trust score (0–1):** 0.07
- **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/ActiveInferenceInstitute/pymcp)

## 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": "activeinferenceinstitute-pymcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/activeinferenceinstitute-pymcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/activeinferenceinstitute-pymcp/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