The AI Meta MCP Server is a dynamic server that enables AI models to create and execute custom tools through a meta-function architecture. This implementation allows AI to extend its capabilities by defining and running custom functions at runtime, providing flexibility and adaptability for various use cases.
⚠️ WARNING: This server allows dynamic code execution. Use with caution and only in trusted environments.
npm install ai-meta-mcp-server
npx ai-meta-mcp-server
Environment variables:
- ALLOW_JS_EXECUTION
: Enable JavaScript execution (default: true
).
- ALLOW_PYTHON_EXECUTION
: Enable Python execution (default: false
).
- ALLOW_SHELL_EXECUTION
: Enable Shell execution (default: false
).
- PERSIST_TOOLS
: Save tools between sessions (default: true
).
- TOOLS_DB_PATH
: Path to store tools database (default: "./tools.json"
).
Add the following to your claude_desktop_config.json
:
{
"mcpServers": {
"ai-meta-mcp": {
"command": "npx",
"args": ["-y", "ai-meta-mcp-server"],
"env": {
"ALLOW_JS_EXECUTION": "true",
"ALLOW_PYTHON_EXECUTION": "false",
"ALLOW_SHELL_EXECUTION": "false"
}
}
}
}
In Claude Desktop, you can create a new tool like this:
Can you create a tool called "calculate_compound_interest" that computes compound interest given principal, rate, time, and compounding frequency?
Claude will use the define_function
meta-tool to create your new tool, which becomes available for immediate use.
The server implements the Model Context Protocol (MCP) and provides a meta-tool architecture that enables AI-driven function registration and execution within safe boundaries.
MIT