amanmcp
Verified Safeby Aman-CERP
Overview
High-performance local text embedding for codebases using MLX on Apple Silicon, serving as a component within the AmanMCP local RAG system.
Installation
python server.pyEnvironment Variables
- PORT
- HOST
- MODEL_NAME
- AMANMCP_MLX_MODELS_DIR
- LOG_LEVEL
- AMANMCP_LOG_DIR
Security Notes
The server's core functionality is local processing of code for embeddings. Models are downloaded from HuggingFace (a generally trusted source for ML models) and stored locally. The server binds to 0.0.0.0 by default, making it accessible from the local network, but it's intended for local use. Logging is well-structured, with health checks excluded from file logs to reduce noise. No explicit 'eval' or directly malicious patterns are observed in the provided code snippets. Overall, it adheres to a privacy-first, local-only philosophy.
Similar Servers
osaurus
Osaurus is an AI edge runtime for macOS, enabling local and cloud model inference, exposing shared tools via MCP, and providing a native foundation for AI applications and workflows on Apple Silicon.
mcp-documentation-server
A local-first MCP server for document management, semantic search, and AI-powered document intelligence.
mcp-local-rag
A local RAG-like web search server that provides relevant context from web pages to Large Language Models for enhanced responses without external APIs.
codeweaver
Provides precise, AI-optimized code context and semantic search capabilities for AI agents to understand and work with codebases efficiently.