A dynamic MCP server that allows AI to create and execute custom tools through a meta-function architecture
A dynamic MCP server that allows AI to create and execute custom tools through a meta-function architecture
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.
Compare MCP servers by category, or browse hosted MCP servers if you prefer an endpoint over a local process.
{
"mcpServers": {
"ai-meta": {
"command": "npx",
"args": ["-y", "ai-meta-mcp-server"],
"env": {
"ALLOW_JS_EXECUTION": "your-value",
"ALLOW_PYTHON_EXECUTION": "your-value",
"ALLOW_SHELL_EXECUTION": "your-value",
"TOOLS_DB_PATH": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| ALLOW_JS_EXECUTION | Configuration value read at startup. | Optional |
| ALLOW_PYTHON_EXECUTION | Configuration value read at startup. | Optional |
| ALLOW_SHELL_EXECUTION | Configuration value read at startup. | Optional |
| TOOLS_DB_PATH | Filesystem location the server is allowed to use. | Optional |
Read, search and edit files inside allowed directories with the Model Context Protocol reference Filesystem server.
Retrieve version-aware library documentation and code examples with Context7 MCP, using resolve-library-id and query-docs.
Analyze test coverage from LCOV files - makes AI agents coverage-aware without wasting tokens
A Model Context Protocol (MCP) server that analyzes OpenAPI specifications and provides context about interacting with APIs.
Hands-on projects for understanding how to build applications using [Model Context Protocol (MCP)](https://modelcontextprotocol.io/).
<strong>Find libraries, discover gems, search code patterns, and read real production code — across 200M+ repos, PyPI, and npm.</strong>