MCP 小智服务器
About
# MCP 小智服务器 MCP 小智服务器是一个基于 Model Context Protocol (MCP) 的智能体管理工具,可以对小智平台的智能体进行各种操作和配置。 ## 功能特性 - 修改智能体的大语言模型 - 修改智能体的 TTS 模型 - 修改智能体的角色音色 - 修改智能体的角色模板 - 修改智能体的名称 - 获取智能体列表信息 ## 安装 ### 从 PyPI 安装(推荐) ```bash pip install mcp-xiaozhi-server ``` ### 从源码安装 ```bash git clone…
Details
- Author
- 104gogo
- Downloads
- 173
- Categories
- Other
Jump to
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
MCP 小智服务器Command (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
{
"mcpServers": {
"mcp-xiaozhi-server": {
"command": "python",
"args": [
"-m",
"venv",
"venv"
]
}
}
}
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mcp \u5c0f\u667a\u670d\u52a1\u5668": {
"mcp-xiaozhi-server": {
"command": "python",
"args": [
"-m",
"venv",
"venv"
]
}
}
}
}
McpServers
{
"mcp-xiaozhi-server": {
"command": "python",
"args": [
"-m",
"venv",
"venv"
]
}
}
MCP 小智服务器
MCP 小智服务器是一个基于 Model Context Protocol (MCP) 的智能体管理工具,可以对小智平台的智能体进行各种操作和配置。
功能特性
- 修改智能体的大语言模型
- 修改智能体的 TTS 模型
- 修改智能体的角色音色
- 修改智能体的角色模板
- 修改智能体的名称
- 获取智能体列表信息
安装
从 PyPI 安装(推荐)
pip install mcp-xiaozhi-server
从源码安装
git clone https://github.com/yourusername/mcp-xiaozhi-server.git
cd mcp-xiaozhi-server
pip install -e .
使用方法
命令行启动
安装后,可以通过命令行启动服务器:
mcp-xiaozhi-server --host https://api.xiaozhi.com --token your_api_token
参数说明
- --host: 小智 API 主机地址(必填)
- --token: 小智 API 访问令牌(必填)
- --version, -v: 显示版本信息
作为 Python 模块使用
```python
from mcp_xiaozhi_server import XiaoZhiServerController
from mcp_xiaozhi_server.config import Config, set_config
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.



