Get the FREE Ultimate OpenClaw Setup Guide →

baichuan s

百川智能官方mcp server集合

Installation
Run this command in your terminal to add the MCP server to Claude Code.
Run in terminal:
Command
claude mcp add --transport stdio baichuan-inc-baichuan-mcp-servers node packages/baixiaoying-mcp-server/index.js \
  --env LOG_LEVEL="info" \
  --env BAICHUAN_API_KEY="your-baichuan-api-key" \
  --env BAICHUAN_API_HOST="https://api.baichuan-ai.com"

How to use

Baichuan MCP Servers provide medical AI capabilities via the MCP APPs protocol. The server bundle exposes professional medical question answering, medical document QA, and six-source evidence with traceable reasoning. Once deployed, you can interact with the MCP Apps-enabled endpoints to generate visualization-rich responses, view referenced sources, and audit the model's reasoning steps. This server focuses on medical dialogs powered by Baichuan-M3-Plus and Baichuan-M2-Plus models, delivering structured, evidence-backed answers suitable for clinical-style interactions.

How to install

Prerequisites:

  • Node.js (LTS version recommended, e.g., v16+)
  • npm or pnpm
  • Access to a Baichuan API key if required by the server

Installation steps:

  1. Clone the repository or install the npm package directly:

    • git clone <repository-url>
    • cd <repo-directory>
    • npm install
  2. Alternatively, install the MCP server package from npm:

    • npm install @baichuan-ai/baixiaoying-mcp-server
  3. Create a configuration file or use environment variables to configure the server (see mcp_config example below).

  4. Start the server:

    • node packages/baixiaoying-mcp-server/index.js
  5. Verify the server is running by sending a test request to the MCP Apps endpoint and checking the response.

Additional notes

Environment variables:

  • BAICHUAN_API_KEY: Your API key for accessing Baichuan services.
  • BAICHUAN_API_HOST: Base URL for the Baichuan API (default: https://api.baichuan-ai.com).
  • LOG_LEVEL: Logging verbosity (e.g., info, warn, error). Configuration considerations:
  • Ensure network access to Baichuan endpoints if required by the model provider.
  • When using MCP Apps visualization, ensure frontend clients are compatible with the MCP Apps protocol version supported by this server.
  • Regularly update the MCP server package to get the latest models and fixes.

Common issues:

  • If the server fails to start, check environment variable availability and that the specified index.js path exists.
  • If API requests fail due to authentication, verify BAICHUAN_API_KEY and host are correct.
  • For visualization features, confirm the MCP Apps protocol compatibility between client and server.

Related MCP Servers

Sponsor this space

Reach thousands of developers