What is the Memory & Knowledge category?
Memory, notes, knowledge bases, documentation, and RAG
Memory, notes, knowledge bases, documentation, and RAG
mahawi1992
MCP Documentation Server with AI Learning Capabilities
wolfyy970
MCP server for fetching web page content with recursive exploration capability
MahithChigurupati
Xsaven
Vector Memory MCP Server
jonathan-politzki
Premium, consistent memory and long-term storage across AI applications. Remote MCP server.
calypso-so
Launch a hosted Gemini File Search true multimodal RAG layer that answers from your PDFs, docs, screenshots, charts, diagrams, help center, FAQs, and images with citations people can verify.
ogham-mcp
Persistent shared memory for AI agents. Hybrid search (pgvector + tsvector), knowledge graph, cognitive scoring, and 16-language temporal extraction. 97.2% Recall@10 on LongMemEval with one PostgreSQL query. Works across Claude Code, Cursor, Codex, OpenClaw, and any MCP client
ximanta
MCP Server for a note management application that integrates with Agents with MCP client integration - Tested with Claude Desktop
roelven
MCP (Model Context Protocol) server for Obsidian notes access via CouchDB LiveSync
zishengwu
A Model Context Protocol (MCP) server that leverages a vector database to efficiently index and query the codebase.
ue-sho
smith-and-web
tomohiro-owada
Lightweight local RAG MCP server for semantic vector
xiangzi1126
Agent-agnostic persistent memory as an MCP Server (SQLite + Chroma + Markdown)
MCP-Mirror
Mirror of
MCP-Mirror
Mirror of
BabyManisha
Tool to fetch and summarize developer documentation from [MDN Web Docs](https://developer.mozilla.org/).
AlekOmOm
greenmtnsun
Generate wiki docs from source code. Supports PowerShell, Python, Go, C#. Java, COBOL are coming soon.
mrlynn
MCP server for Voyage AI embeddings, reranking, and MongoDB Atlas Vector Search. Provides 11 tools for semantic search, document ingestion, cost estimation, and model exploration. Full RAG pipeline: chunk, embed, vector search, and rerank from any MCP client.
Puliczek
π₯π₯οΈ MCP Memory is a MCP Server that gives MCP Clients (Cursor, Claude, Windsurf and more) the ability to remember information about users (preferences, behaviors) across conversations.
MCP-Mirror
Mirror of
reposit-bot
lawmem-ai
LawMem gives legal AI agents persistent, searchable memory via MCP. Store case notes, client context, research findings, and matter history β recalled semantically when relevant. Namespace-isolated, audit-logged, GDPR-compliant. Free tier + paid plans.
gstcranes
GST Cranes Public Discovery MCP is a read-only public discovery server for GST Cranes, a worldwide B2B marketplace for used mobile and crawler cranes. It exposes public documentation, OpenAPI, marketplace, wanted-ad, and Crane Wiki / Atlas discovery resources for AI agents.
andrea9293
MCP Documentation Server - Bridge the AI Knowledge Gap.
amanasmuei
The memory layer for AI coding tools. Local-first, semantic, 9 MCP tools with consolidation and project scoping. Works with Claude Code, Cursor, Windsurf & any MCP client.
rwelgosh
chatmcp
i will store his data here
jagoff
memo is a local-first, long-term semantic memory for AI coding agents (Claude Code, Cursor, Cline, Codex). Runs fully offline with in-process embeddings β MLX on Apple Silicon or CPU sentence-transformers on Linux/Docker β and a sqlite-vec + BM25 hybrid retrieval pipeline with re
iamredmh
Burn-after-read encrypted notes for AI agents. Share secrets with users without them appearing in chat history β create a one-time URL, send it, they read it once and it's gone. AES-256-GCM E2E encrypted, decryption key never sent to any server.
nakamurau1
kirvigen
Unofficial Notion MCP server built on Notion's private API (token_v2 cookie). Full read/write access to your entire Notion workspace β no integration token and no per-page sharing.
MCP-Mirror
Mirror of
Siddhant-K-code
MCP server designed to help you search and analyze your photo library (iCloud)
Yuchen20
π§ π΄πππππ-π·πππ is a lightweight, local RAG memory store for MCP agents. Easily record, retrieve, update, delete, and visualize persistent "memories" across sessionsβperfect for developers working with multiple AI coders (like Windsurf, Cursor, or Copilot) or anyone who
mhmd2015
Create MCP server for accessing SharePoint Online
Draco-Cheng
AI_README MCP Server is a Model Context Protocol (MCP) server that helps AI assistants understand your project conventions through dedicated AI_README.md guide files. It automatically discovers, routes, and manages these files so AI can generate consistent, high-quality code that
luismichio
Goodnotes
Turn AI insights into documents
TheWinci
Semantic code search for AI agents β hybrid vector + BM25 with cross-encoder reranking, AST-aware chunking for 14 languages, conversation memory, code annotations, and search analytics. Zero config, zero API keys. Just bunx.
fmicalizzi
MCP server for reading JSON knowledge bases without modifications
ravikalla
High-performance XML file comparison with semantic analysis capabilities. Features StAX streaming parser for memory-efficient processing of large XML files (60MB+ tested), order-agnostic semantic comparison, and multiple output formats (text, JSON, Excel). Includes 5 MCP tools fo
calvincchan
orbrx
MCP server for GitBook
hellozhangran
obsidian-mcp-python, a very simple MCP Server demo that can help you to operate something about your obsidian md file
Im-Hal-9K
Enhanced MCP server for Capacities, the knowledge management app. Features include listing spaces, searching content with full-text and title modes, retrieving complete object content by ID, saving weblinks with metadata and tags, and adding content to daily notes. Fork of the or
ergut
MCP server to interact with LogSeq via its Local HTTP API - enabling AI assistants like Claude to seamlessly read, write, and manage your LogSeq graph.
Octid-io
Agentic AI instruction encoding. 86.8% smaller than JSON. Inference-free decode by table lookup. 342 opcodes, 26 namespaces, three conformant SDKs. Confirmed over LoRa mesh radio. Apache 2.0 with express patent grant.
HarshDindeAI
The MCP-RAG Server is an implementation of the Model Context Protocol (MCP) designed to enhance AI assistants by providing them with real-time access to relevant documentation through semantic vector search. It enables AI models to retrieve and process documentation, allowing for
sgraal-ai
Deterministic pre-action verdict gate for agent memory β USE/WARN/ASK/BLOCK before an agent acts on a stored memory. Governs your existing store, doesn't replace it.
landicefu
tstockham96
Universal memory layer for AI agents. Semantic recall, automatic consolidation, and bi-temporal knowledge β in SQLite. 80% on LOCOMO benchmark using 96% fewer tokens.
omarguzmanm
MCP Server to improve LLM context through vector search.
BehindUAll
Model Context Protocol (MCP) server for Wiki.js with hierarchical documentation & Docker setup
LaserFocused-ee
MCP server for providing documentation to Claude
Yarmoluk
Salesforce AgentForce as a traversable knowledge graph β 40 nodes, Einstein Trust Layer, $2-per-resolution billing path, 11x fewer tokens than RAG. MCP-native.
yantrikos
Cognitive memory for AI agents β persistent semantic memory with knowledge graph and adaptive recall
miosomos
MCP Server to improve LLM context through vector search.
MCP-Mirror
Mirror of
Common questions about the Memory & Knowledge category
Memory, notes, knowledge bases, documentation, and RAG
mcp.so currently lists 612 MCP servers and clients in the Memory & Knowledge category.
Open any server below and copy its install snippet into Claude Desktop, Cursor, VS Code, or another MCP client's configuration β remote servers need no separate download.