AmanMCP is a local-first RAG server that provides semantic code search capabilities for AI coding assistants through the MCP protocol. Built in Go with hybrid search combining BM25 keyword matching and vector embeddings, it supports multiple embedding backends including a bundled MLX server for Apple Silicon, Ollama integration, and static embeddings for offline use. The implementation features automatic project indexing with tree-sitter parsing for intelligent code chunking across many programming languages.
Cognium trust score
50%
Tier
Unverified
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
Returns 7 tools: search_skills, get_skill, list_leaderboard, get_trust_breakdown, resolve_composition, plus the ChatGPT-connector search and fetch. Every tool is annotated read-only.
Resolve this skill directly via MCP tools/call get_skill.