AI Meta MCP Server
local-only server
The server can only run on the client’s local machine because it depends on local resources.
Integrations
Provides a runtime environment for executing custom tools written in JavaScript code, with appropriate sandboxing for security
Enables installation and execution of the MCP server through npm package management
Offers a runtime environment for executing custom tools implemented in Python, which can be enabled through configuration
AI Meta MCP Server
A dynamic MCP server that allows AI models to create and execute their own custom tools through a meta-function architecture. This server provides a mechanism for AI to extend its own capabilities by defining custom functions at runtime.
Features
- Dynamic Tool Creation: AI can define new tools with custom implementations
- Multiple Runtime Environments: Support for JavaScript, Python, and Shell execution
- Sandboxed Security: Tools run in isolated sandboxes for safety
- Persistence: Store and load custom tool definitions between sessions
- Flexible Tool Registry: Manage, list, update, and delete custom tools
- Human Approval Flow: Requires explicit human approval for tool creation and execution
Security Considerations
⚠️ WARNING: This server allows for dynamic code execution. Use with caution and only in trusted environments.
- All code executes in sandboxed environments
- Human-in-the-loop approval required for tool creation and execution
- Tool execution privileges configurable through environment variables
- Audit logging for all operations
Installation
Usage
Running the server
Configuration
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")
Running with Claude Desktop
Add this to your claude_desktop_config.json
:
Tool Creation Example
In Claude Desktop, you can create a new tool like this:
Claude will use the define_function
meta-tool to create your new tool, which becomes available for immediate use.
Architecture
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.
License
MIT
This server cannot be installed
Enables AI models to dynamically create and execute their own custom tools through a meta-function architecture, supporting JavaScript, Python, and Shell runtimes with sandboxed security and human approval flows.