AI Meta MCP Server
Enables AI models to dynamically create and execute their own custom tools at runtime, supporting JavaScript, Python, and Shell with sandboxed execution and human approval requirements.
8165 views5Local (stdio)
What it does
- Create custom tools dynamically during AI conversations
- Execute JavaScript, Python, and Shell code in sandboxed environments
- Store and load custom tool definitions between sessions
- Manage tool registry with list, update, and delete operations
- Require human approval for tool creation and execution
- Configure execution permissions per runtime environment
Best for
AI researchers developing self-extending AI systemsDevelopers building adaptive AI assistantsAdvanced users needing AI to create specialized tools on-demand
Human-in-the-loop approval flowSandboxed security architecturePersistent tool storage
