1. Conduid
  2. AI
  3. core
MCP server · AI

core

by · github.com/shenjingnan/xiaozhi-client

MCP 协议核心实现，提供服务连接和管理功能

Unclaimed devtools
InstallView source
39Low

Scored 4 months ago · breakdown

About core

core is an MCP server published by git+shenjingnan in the AI category: mCP 协议核心实现，提供服务连接和管理功能. It has been installed 0 times through Conduid.

Install

Install
npx @xiaozhi-client/mcp-core
Claude Code
claude mcp add xiaozhi-client -- npx -y @xiaozhi-client/mcp-core
npx
npx -y @xiaozhi-client/mcp-core

This server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.

Ask AI

✦

Ask AI about core

Powered by Claude · Grounded in docs

I know everything about core. Ask me about installation, configuration, usage, or troubleshooting.

Security checks

  • ·README presentNot checked yet.
  • ·License declaredNot checked yet.
  • ·Tests presentNot checked yet.
  • ·Dependencies pinnedNot checked yet.
  • ·No dynamic code executionNot checked yet.
  • !Scoped permissionsDoesn't declare a permission scope. Assume it can do anything its process can.

README

功能特色

  • 支持 小智(xiaozhi.me) 官方服务器接入点
  • 支持 作为普通 MCP Server 集成到 Cursor/Cherry Studio 等客户端
  • 支持 配置多个小智接入点，实现多个小智设备共享一个 MCP 配置
  • 支持 通过标准方式聚合多个 MCP Server
  • 支持 动态控制 MCP Server 工具的可见性，避免由于无用工具过多导致的小智服务端异常
  • 支持 本地化部署的开源服务端集成，你可以使用和小智官方服务端一样的 RPC 通信或直接使用标准 MCP 集成方式
  • 支持 Web 网页可视化配置(允许自定义 IP 和端口，你能将 xiaozhi-client 部署在设备 A，然后在设备 B 通过网页控制 xiaozhi-client)
  • 支持 集成 ModelScope 的远程 MCP 服务
  • 支持 通过模板创建 xiaozhi-client 项目 (xiaozhi create <my-app> --template <template-name>)
  • 支持 后台运行(xiaozhi start -d)

Web UI 配置界面

效果图

快速上手

你可以阅读文档 xiaozhi-client.shenjingnan.com 快速上手！

本地安装

前置条件：请先完成 Node.js >=22（推荐 24）与 pnpm 的安装

# 安装
pnpm install -g xiaozhi-client

# 创建应用
xiaozhi create my-app

# 进入应用目录
cd my-app

# 安装依赖
pnpm install

# 小智AI配置MCP接入点的 [使用说明](https://ccnphfhqs21z.feishu.cn/wiki/HiPEwZ37XiitnwktX13cEM5KnSb)
xiaozhi config set mcpEndpoint "<从小智服务端获取到的接入点地址>"

# 启动服务
xiaozhi start

# 浏览器打开 http://localhost:9999 如果你使用的是NAS部署请使用 http://<部署设备的IP地址>:9999

使用 Docker 运行

我们提供了预配置的 Docker 镜像，可以快速启动 xiaozhi-client 环境。

前置要求

快速启动

方式一：使用启动脚本（推荐）
curl -fsSL https://raw.githubusercontent.com/shenjingnan/xiaozhi-client/main/docker/scripts/start.sh | bash

无法访问 Github 可以使用 Gitee 替代

curl -fsSL https://gitee.com/shenjingnan/xiaozhi-client/raw/main/docker/scripts/start.sh | bash
方式二：使用 Docker Compose

获取 docker-compose.yml 文件：

curl -O https://raw.githubusercontent.com/shenjingnan/xiaozhi-client/main/docker/docker-compose.yml

无法访问 Github 可以使用 Gitee 替代

curl -O https://gitee.com/shenjingnan/xiaozhi-client/raw/main/docker/docker-compose.yml

# 使用 Docker Compose 启动
docker-compose up -d

# 查看日志
docker-compose logs -f

# 停止服务
docker-compose down

贡献者

Contributors

README mirrored from the source repository 4 months ago. The original is authoritative.

Questions

About core

How do I install core?

Run npx @xiaozhi-client/mcp-core, then add the server to your MCP client's configuration. Conduid has recorded 0 installs, so the command is known to work with current clients.

Is core safe to use with an AI agent?

Its trust score is 39 out of 100 (low). It passes 0 of 1 static security checks; the failures are listed above. It has no ConduID identity yet, so agent calls to it are not receipted.

Is core still maintained?

Conduid hasn't recorded a commit date for this repository yet. Check the repository directly for recent activity.