AI Meta Tool Creator
About
Enables AI to dynamically create, execute, and manage custom tools in a secure sandbox environment for JavaScript, Python, or shell code with persistent storage capabilities.
Details
- Author
- alxspiker
- Repository
- alxspiker/ai-meta-mcp-server
- GitHub stars
- 5
- Downloads
- 463
- License
- MIT License
- Categories
- AI, Design, Developer Tools, File Management, Database, Security, Frontend, Infrastructure, Other
Jump to
- 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
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
AI Meta Tool CreatorCommand (node, npx, python, etc.)npxArguments-
Argument 1
-y -
Argument 2
ai-meta-mcp-server
Environment-
ALLOW_JS_EXECUTION
true -
ALLOW_SHELL_EXECUTION
false -
ALLOW_PYTHON_EXECUTION
false
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
-
Argument 1
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
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")
npx ai-meta-mcp-server
docker run --rm -i \
-e ALLOW_PYTHON_EXECUTION=true \
-e ALLOW_SHELL_EXECUTION=false \
-v $(pwd)/data:/app/data \
ai-meta-mcp-server
Add this 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"
}
}
}
}
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"ai meta tool creator": {
"env": {
"ALLOW_JS_EXECUTION": "true",
"ALLOW_SHELL_EXECUTION": "false",
"ALLOW_PYTHON_EXECUTION": "false"
},
"args": [
"-y",
"ai-meta-mcp-server"
],
"command": "npx"
}
}
}Linux
{
"env": {
"ALLOW_JS_EXECUTION": "true",
"ALLOW_SHELL_EXECUTION": "false",
"ALLOW_PYTHON_EXECUTION": "false"
},
"args": [
"-y",
"ai-meta-mcp-server"
],
"command": "npx"
}Macos
{
"env": {
"ALLOW_JS_EXECUTION": "true",
"ALLOW_SHELL_EXECUTION": "false",
"ALLOW_PYTHON_EXECUTION": "false"
},
"args": [
"-y",
"ai-meta-mcp-server"
],
"command": "npx"
}Windows
{
"env": {
"ALLOW_JS_EXECUTION": "true",
"ALLOW_SHELL_EXECUTION": "false",
"ALLOW_PYTHON_EXECUTION": "false"
},
"args": [
"/c",
"npx",
"-y",
"ai-meta-mcp-server"
],
"command": "cmd"
}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
npm install ai-meta-mcp-server
Usage
Running the server
npx ai-meta-mcp-server
Running with Docker
# Build the Docker image
docker build -t ai-meta-mcp-server .
Run the container
docker run --rm -i ai-meta-mcp-server
Run with custom configuration and persistent storage
docker run --rm -i \
-e ALLOW_PYTHON_EXECUTION=true \
-e ALLOW_SHELL_EXECUTION=false \
-v $(pwd)/data:/app/data \
ai-meta-mcp-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:
{
"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"
}
}
}
}
Tool Creation Example
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.
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
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
