Amidabuddha Unichat Ts MCP Server

🚀 Unichat MCP Server based on TypeScript

There is also a Python version available. -- Send requests to OpenAI, MistralAI, Anthropic, xAI, or Google AI using tools or predefined prompts via the MCP protocol. API keys from each provider are required.

It supports both STDIO and SSE transmission mechanisms, depending on the parameter selection.

✨ Features

Tools

The server implements one tool:

• unichat: Send requests to Unichat.
  • It accepts a required string parameter "messages".
  • Returns a response.

Prompts

• code_review
  • Review code to identify best practices, potential issues, and improvement suggestions.
  • Parameters:
    • code (string, required): The code to be reviewed.
• document_code
  • Generate documentation for the code, including docstrings and comments.
  • Parameters:
    • code (string, required): The code to be commented.
• explain_code
  • Explain in detail how a piece of code works.
  • Parameters:
    • code (string, required): The code to be explained.
• code_rework
  • Modify the provided code according to requirements.
  • Parameters:
    • changes (string, optional): The changes to be applied.
    • code (string, required): The code to be rewritten.

📦 Installation

Installation via Smithery

To automatically install the Unichat MCP Server for Claude Desktop, you can execute the following command via Smithery:

npx -y @smithery/cli install unichat-ts-mcp-server --client claude

Manual Installation

To use it with Claude Desktop, add the server configuration:

• On MacOS: ~/Library/Application Support/Claude/claude_desktop_config.json
• On Windows: %APPDATA%/Claude/claude_desktop_config.json

It runs via STDIO by default or with the --stdio parameter. To run via SSE, add the --sse parameter.

Run locally:

{
  "mcpServers": {
    "unichat-ts-mcp-server": {
      "command": "node",
      "args": [
        "{{/path/to}}/unichat-ts-mcp-server/build/index.js"
      ],
      "env": {
        "UNICHAT_MODEL": "YOUR_PREFERRED_MODEL_NAME",
        "UNICHAT_API_KEY": "YOUR_VENDOR_API_KEY"
      }
    }
  }
}

Run after publishing:

{
  "mcpServers": {
    "unichat-ts-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "unichat-ts-mcp-server"
      ],
      "env": {
        "UNICHAT_MODEL": "YOUR_PREFERRED_MODEL_NAME",
        "UNICHAT_API_KEY": "YOUR_VENDOR_API_KEY"
      }
    }
  }
}

💻 Usage Examples

Development

Install dependencies:

npm install

Build the server:

npm run build

Development with auto-rebuild:

npm run watch

📚 Documentation

Debugging

To debug, visit the Inspector tool, which can help you inspect and debug the MCP server.