Neosapience Typecast Api MCP Server Sample

🚀 Type Conversion API - MCP Server Sample

Implement an MCP (Model Context Protocol) server for the Typecast API, enabling seamless integration with MCP clients. This project offers a standardized approach to interact with the Typecast API through the Model Context Protocol.

🚀 Quick Start

This project implements the server - side of the Model Context Protocol for the Typecast API, allowing MCP clients to interact with the Typecast API in a unified manner.

✨ Features

Function Implementation Status

📦 Installation

Clone the Repository with Git

git clone https://github.com/hyunseung/typecast-api-mcp-server-sample.git
cd typecast-api-mcp-server-sample

Dependencies

This project requires Python 3.10 or higher and uses uv for package management.

Install Packages

# Create a virtual environment and install dependencies
uv venv
uv pip install -e .

Set Environment Variables

Set the following environment variables:

TYPECAST_API_HOST=https://api.typecast.ai
TYPECAST_API_KEY=<your-api-key>
TYPECAST_OUTPUT_DIR=<your-output-directory> # Default: ~/Downloads/typecast_output

Configuration in Claude Desktop

You can add the following content to claude_desktop_config.json:

Basic Configuration:

{
  "mcpServers": {
    "typecast-api-mcp-server": {
      "command": "uv",
      "args": [
        "--directory",
        "/PATH/TO/YOUR/PROJECT",
        "run",
        "typecast-api-mcp-server"
      ],
      "env": {
        "TYPECAST_API_HOST": "https://api.typecast.ai",
        "TYPECAST_API_KEY": "YOUR_API_KEY",
        "TYPECAST_OUTPUT_DIR": "PATH/TO/YOUR/OUTPUT/DIR"
      }
    }
  }
}

Replace /PATH/TO/YOUR/PROJECT with the actual path of your project.

Manual Operation

You can also run the server manually:

uv run python app/main.py

🤝 Contribution

All forms of contributions are welcome! Please feel free to submit a Pull Request.

📄 License

MIT License