Vector Search

Local adaptive memory for AI coding agents through a five-tool MCP lifecycle.

Semantic, on-demand skill retrieval for Claude Code — replaces the native skill-listing token tax with a vector retriever over full skill descriptions.

Lightweight MCP Server for RAG-based skill retrieval

Self-steering skill management MCP with RAG-based prediction matching

Knowledge graph + vector search for AI agent skill discovery

Skill lifecycle intelligence MCP — semantic matching, feedback loop, gap detection, scout

Turn internal code libraries into AI-accessible knowledge sources via MCP server with semantic search

Model Context Protocol server for IDE-like code navigation and semantic search

Experimental MCP proxy for filtering large tool lists using hybrid semantic and keyword retrieval

Sync public web sources into cited context packs for AI agents, RAG, and MCP clients.

Spatial Faithfulness Score (SFS) — a domain-agnostic MCP toolkit for measuring context faithfulness in RAG systems

폴더에 문서를 꽂아두면 Claude가 꺼내 읽는 로컬 RAG MCP 서버 (한국어 형태소 검색)

MCP server for semantic code search using local embeddings

Semantic router for MCP ecosystems - Discover, manage, and execute tools across multiple MCP servers with progressive disclosure

Semantic codebase indexer and MCP server for Claude Code

Model Context Protocol server for Project Sekha - Persistent AI Memory Controller (v2.0 multi-provider compatible)

A PDF's real sections for agents: heading tree, pages and section text. Free mode is local.

MCP server that turns an Obsidian vault into semantic memory for any coding agent

Local MCP server for querying Excel files (heavy merged cells, multi-language text) via DuckDB and substring search. No LLM/embedding required.

MCP server for the scrapedatshi RAG pipeline API — use scrapedatshi tools directly from Claude Desktop