shenjingnan/xiaozhi-client

小智AI客户端，目前主要用于MCP的对接

What it solves

Xiaozhi Client provides a bridge between AI servers and Model Context Protocol (MCP) servers. It allows users to connect AI services (like the official Xiaozhi AI servers, ModelScope, Coze, or Dify) to a variety of external tools and data sources via the MCP standard, enabling these AI agents to interact with the real world or specific datasets.

How it works

The project acts as a client that can be configured to connect to multiple AI endpoints. It supports both official RPC communication and standard MCP integration. It includes a web-based visual configuration interface for managing IP and port settings, allowing the client to be deployed on one device (e.g., a NAS) and controlled remotely from another device's browser.

Who it’s for

Developers and users who want to integrate AI agents with external tools using the Model Context Protocol (MCP), specifically those using the Xiaozhi AI ecosystem or other MCP-compatible clients like Cursor or Cherry Studio.

Highlights

  • Broad Compatibility: Supports official Xiaozhi AI servers, ModelScope remote MCP services, Coze, and Dify.
  • MCP Aggregation: Ability to aggregate multiple MCP servers and dynamically control the visibility of tools to prevent server-side errors caused by too many tools.
  • Flexible Deployment: Supports local installation via Node.js, Docker, and Docker Compose, with a background execution mode.
  • Remote Management: Features a web UI for visual configuration and remote control of the deployment device.

Related

  • Project
    IBM/mcp

    A collection of Model Context Protocol (MCP) servers and tools that enable AI agents to securely interact with IBM products and enterprise resources.

  • Project
    microsoft/mcp

    A collection of Model Context Protocol (MCP) servers and core tooling that standardizes how AI agents and LLMs connect to Microsoft services and external data sources.

  • Project
    apify/mcpc

    A universal CLI client for the Model Context Protocol (MCP) that enables AI agents and developers to interact with MCP servers via shell commands.

  • Project
    dbt-labs/dbt-mcp

    An MCP server that provides AI agents with tools to interact with dbt Core, Fusion, and Platform, enabling them to query data, manage lineage, and execute dbt workflows.

  • Project
    sirkirby/unifi-mcp

    A collection of Model Context Protocol (MCP) servers that enable AI agents to manage Ubiquiti UniFi Network, Protect, and Access infrastructure using natural language.