Back to Home
LibraxisAI icon

mcp_memex

by LibraxisAI

Overview

Provides a local Retrieval-Augmented Generation (RAG) toolset with an embedded vector store and local/optional remote embeddings for MCP clients.

Installation

Run Command
cargo run --release -- --log-level info

Environment Variables

  • DISABLE_MLX
  • DRAGON_BASE_URL
  • MLX_JIT_MODE
  • MLX_JIT_PORT
  • EMBEDDER_PORT
  • RERANKER_PORT
  • EMBEDDER_MODEL
  • RERANKER_MODEL
  • FASTEMBED_CACHE_PATH
  • HF_HUB_CACHE
  • LANCEDB_PATH
  • PROTOC

Security Notes

The `rag_index` function, which allows indexing of arbitrary file paths provided by the client via JSON-RPC, presents a local information disclosure risk. A malicious client could instruct the server to index sensitive system files (e.g., '/etc/passwd', private keys). If these indexed documents are subsequently retrieved via `rag_search`, their content could be exposed. Input path validation or restriction to specific directories is missing. SQL injection into LanceDB queries is mitigated by proper escaping. No direct 'eval' or code injection risks were identified in the RPC handler.

Similar Servers

Stats

Interest Score0
Security Score4
Cost ClassMedium
Avg Tokens1000
Stars0
Forks0
Last Update2026-01-11

Tags

RAGVector StoreEmbeddingsRustMCP Server