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
hybrid server
The server is able to function both locally and remotely, depending on the configuration or use case.
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.
Related MCP Servers
- -securityAlicense-qualityProvides code manipulation, execution, and version control capabilities. It allows AI assistants to read, write, and execute code while maintaining a history of changes.Last updated -8PythonMIT License
- AsecurityAlicenseAqualityThis server provides a minimal template for creating AI assistant tools using the ModelContextProtocol, featuring a simple 'hello world' tool example and development setups for building custom MCP tools.Last updated -1148TypeScriptThe Unlicense
- -securityFlicense-qualityEnables AI assistants to interact with Metabase databases and dashboards, allowing users to list and execute queries, access data visualizations, and interact with database resources through natural language.Last updated -9JavaScript
- -securityFlicense-qualityA demonstration project that uses Cloudflare Workers MCP to create custom AI tools that can be integrated with Claude, Cursor, and other AI assistants supporting the Model Context Protocol.Last updated -26TypeScript