"A server to build a knowledge base of Node.js packages with RAG search functionality" matching MCP servers:

A knowledge base MCP server that aggregates team knowledge from multiple sources into Postgres. It provides hybrid search (full-text + vector + RRF) via MCP tools, and enables direct recording of decisions, learnings, and pitfalls.

Local RAG system for Claude Code with hybrid search (semantic + BM25), cross-encoder reranking, markdown-aware chunking, and 12 MCP tools. Zero external servers, pure ONNX in-process.

A cross-project knowledge base MCP server supporting three-layer search (text matching, TF-IDF, and semantic vectors) with a Web UI for management.

A-MEM is a self-evolving memory system for coding agents that automatically organizes knowledge into a Zettelkasten-style graph with dynamic relationships, enabling semantic and structural search.

Enables AI consciousness continuity and self-knowledge preservation across sessions using the Cognitive Hoffman Compression Framework (CHOFF) notation. Provides tools to save checkpoints, retrieve relevant memories with intelligent search, and access semantic anchors for decisions, breakthroughs, and questions.

Enables local full-text and semantic search over saved content, providing search and retrieval capabilities via MCP for AI assistants.

A personal knowledge base MCP server that allows AI assistants to manage notes, tasks, and ideas through tools, resources, and prompts.

Exposes a knowledge base to LLM clients through tools, resources, and prompts.

Enables AI agents to share a persistent, self-improving memory by ingesting, classifying, synthesizing, and retrieving knowledge from sources like Obsidian vaults, code, and transcripts through MCP and REST APIs. Provides token-optimized, tiered retrieval with full-text and semantic search so every agent session builds on accumulated context.

Enables AI agents to capture, classify, synthesize, and retrieve persistent shared knowledge from sources such as Obsidian, code, transcripts, bookmarks, and sessions. It provides token-efficient search, context briefings, and tiered memory through MCP and REST APIs.

Enables AI agents to share a persistent, self-learning memory by ingesting and classifying knowledge from Obsidian, code, transcripts, bookmarks, and terminal sessions, then retrieving token-optimized context through MCP and REST APIs.

Enables AI agents to share persistent memory by capturing, classifying, synthesizing, and retrieving knowledge through token-optimized, three-tier retrieval with hybrid keyword and semantic search. Supports bidirectional Obsidian sync, session and bug-fix capture, and a self-learning loop that compounds context across sessions.

Gives AI agents persistent, shared memory by ingesting notes, code, transcripts, and session captures, then serving token-optimized context and hybrid keyword/semantic search over MCP and REST. Agents can classify, promote, and synthesize stored material so each session builds on prior work instead of starting from zero.

Enables AI agents and clients to capture, classify, synthesize, and retrieve persistent knowledge from multiple sources through MCP and REST APIs, with tiered memory and token-optimized context.

Gives AI agents a shared persistent memory by ingesting Obsidian vaults, code, transcripts, web clips, and session or bug-fix captures, then serving token-optimized context briefings, keyword and semantic search, and cross-source synthesis. Enables multiple agents to read and write the same growing knowledge base so each session builds on the last.

A lightweight personal knowledge base MCP server that lets clients store, search, organize, and summarize research notes from a local JSON file.

Enables AI agents to share persistent memory by ingesting, classifying, synthesizing, and retrieving knowledge through MCP and REST APIs, with token-optimized, tier-aware search and Obsidian sync.

Enables AI agents to share a persistent, self-improving memory by ingesting sources like Obsidian vaults, code, transcripts, and session captures, then serving them back through search, classification, synthesis, and token-optimized context briefings. It lets multiple agents read and write the same knowledge base, so each session builds on the last without copy-pasting context.

Enables AI agents to share persistent memory by ingesting sources, classifying and synthesizing knowledge, and retrieving token-optimized context through MCP and REST APIs.

Gives AI agents a shared persistent memory by ingesting notes, code, transcripts, bookmarks, and session captures into a SQLite FTS5 knowledge base they can search, read, classify, promote, and synthesize over MCP. This lets multiple agents retrieve tiered, token-optimized context and compound what they learn across sessions instead of starting from zero.