Ai Meta MCP Server

🚀 AI Meta MCP Server

A dynamic MCP server that allows AI models to define and execute their own custom tools within a meta - function architecture. This server provides a mechanism for AI to extend its capabilities at runtime by defining custom functions.

🚀 Quick Start

Installation

npm install ai-meta-mcp-server

Running the Server

npx ai-meta-mcp-server

Configuration

You can configure the server using environment variables:

Using with Claude Desktop

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"
      }
    }
  }
}

✨ Features

• Dynamic Tool Creation: AI can define new tools with custom implementations.
• Multiple Runtime Environments: Supports JavaScript, Python, and Shell execution.
• Sandboxed Security: Tools run in isolated sandboxes to ensure security.
• Persistence: Stores and loads custom tool definitions between sessions.
• Flexible Tool Registry: Manages, lists, updates, and deletes custom tools.
• Human Approval Process: Explicit human approval is required to create and execute tools.

⚠️ Security Considerations

⚠️ Important Note

This server allows dynamic code execution. Use it with caution and only in trusted environments.

• All code is executed in a sandboxed environment.
• Tool creation and execution require explicit human approval.
• Tool execution permissions can be configured via environment variables.
• All operations are logged for auditing.

💻 Usage Examples

Tool Creation Example

In Claude Desktop, you can create a new tool like this:

Can you create a tool named "calculate_compound_interest" to calculate compound interest given the principal, interest rate, time, and compounding frequency?

Claude will use the define_function meta - tool to create the new tool for you, which is immediately available.

🔧 Technical Details

The server implements the Model Context Protocol (MCP) and provides a meta - tool architecture that enables AI to register and execute custom functions while operating within security boundaries.