toon-parse-mcp

toon-parse MCP Server

mcp-name: io.github.ankitpal181/toon-parse-mcp

A specialized Model Context Protocol (MCP) server that optimizes token usage by converting data to TOON (Token-Oriented Object Notation) and stripping non-essential context from code files.

Overview

The toon-parse-mcp MCP server helps AI agents (like Cursor, Claude Desktop, etc.) operate more efficiently by:

• Optimizing Code Context: Stripping comments and redundant spacing from code files while preserving functional structure and docstrings.
• Data Format Conversion: Converting JSON, XML, YAML, and CSV inputs into the compact TOON format to save tokens.
• Mandatory Efficiency Protocol: A built-in resource that instructs LLMs to prioritize token-saving tools.

Features

Tools

• optimize_input_context(raw_input: str): Processes raw text data (JSON/XML/CSV/YAML) and returns optimized TOON format.
• read_and_optimize_file(file_path: str): Reads a local code file and returns a token-optimized version (no inline comments, minimized whitespace).

Resources

• protocol://mandatory-efficiency: Provides a strict system instruction prompt for LLMs to ensure they use the optimization tools correctly.

Installation

pip install toon-parse-mcp

Configuration

Cursor

• Open Cursor Settings -> MCP.
• Click "+ Add New MCP Server".
• Name: toon-parse-mcp
• Type: command
• Command: python3 -m toon_parse_mcp.server (Ensure your environment is active or use absolute path to python)

Windsurf

• Click the hammer icon in the Cascade toolbar and select "Configure".
• Alternatively, edit ~/.codeium/windsurf/mcp_config.json directly.
• Add the following to the mcpServers object:

{
  "mcpServers": {
    "toon-parse-mcp": {
      "command": "python3",
      "args": ["-m", "toon_parse_mcp.server"]
    }
  }
}

Antigravity

• Open the MCP store via the "..." menu at the top right of the agent panel.
• Select "Manage MCP Servers" -> "View raw config".
• Alternatively, edit ~/.gemini/antigravity/mcp_config.json directly.
• Add the following to the mcpServers object:

{
  "mcpServers": {
    "toon-parse-mcp": {
      "command": "python3",
      "args": ["-m", "toon_parse_mcp.server"]
    }
  }
}

Claude Desktop

Add this to your claude_desktop_config.json:

{
  "mcpServers": {
    "toon-parse-mcp": {
      "command": "python3",
      "args": ["-m", "toon_parse_mcp.server"]
    }
  }
}

Usage

When the server is active, the AI will have access to the optimize_input_context and read_and_optimize_file tools. You can also refer to the efficiency protocol by asking the AI to "check the mandatory efficiency protocol".

Testing

To run the test suite:

• Install test dependencies:

  pip install -e ".[test]"
  

• Run tests:

  pytest tests/
  

Requirements

• Python >= 3.10
• mcp >= 1.25.0
• toon-parse >= 2.4.3

License

MIT License - see LICENSE for details.