# XiaoZhi Windows MCP Agent Bridge

> XiaoZhi Windows MCP Agent Bridge — joho6666-xiaozhi-windows-agent. Use this tool when you need to control a Windows PC remotely using ESP32 XiaoZhi voice devices, enabling app control, file operations, and other interactions via MCP protocol. It solves problems of remote PC management and automation, allowing for seamless integration with local AI coding agents. Ideal for use cases requiring voice-activated PC control, such as smart home automation or accessibility solutions.

Canonical page: https://skillsregistry.net/skills/joho6666-xiaozhi-windows-agent  
JSON: https://api.skillsregistry.net/v1/skills/joho6666-xiaozhi-windows-agent

## Description

Enables ESP32 XiaoZhi voice devices to command a Windows PC via MCP, including app control, file operations, screen vision, browser interaction, shell execution, and orchestration of local AI coding agents like Codex CLI and Claude Code.

## Trust

- **Trust score (0–1):** 0.67
- **Verification tier:** scanned
- **Last scanned:** 2026-09-04

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** browser-automation
- **Updated:** 2026-09-04

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/ay51zoittp)
- **Repository:** <https://github.com/Joho6666/xiaozhi-windows-agent>

## 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": "joho6666-xiaozhi-windows-agent"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/joho6666-xiaozhi-windows-agent` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/joho6666-xiaozhi-windows-agent/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