# PhyMCP

> Use this tool when you need to control and interact with nearby IoT devices, enabling features like device discovery, tool execution, and heartbeat monitoring. PhyMCP solves problems of device management and automation, providing a protocol for predictable and reliable communication. It takes inputs like device discovery requests and tool execution commands, and outputs device information and execution results, ideal for use in IoT environments requiring custom firmware and authorization policies.

Canonical page: https://skillsregistry.net/skills/chensunlai-phymcp  
JSON: https://api.skillsregistry.net/v1/skills/chensunlai-phymcp

## Description

PhyMCP is an ESP-IDF component library defining a physical device control protocol for nearby IoT devices. It enables agent hosts to discover devices via ESP-NOW, retrieve tool lists, execute tools, and send heartbeat requests with predictable timeouts. A Python MCP host interface wrapper translates PhyMCP to standard MCP endpoints. Currently experimental; requires custom firmware, serial bridges, and authorization policies.

## Trust

- **Trust score (0–1):** 0.65
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

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

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/chensunlai-phymcp)
- **Repository:** <https://github.com/chensunlai/phymcp>

## 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": "chensunlai-phymcp"
    }
  }
}
```

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