419 knowledge & memory MCP servers, most popular first. Every listing shows its security level and install command.
| Name | Popularity | Security |
|---|---|---|
| lotus-wisdom-mcp Contemplative problem-solving using the Lotus Sutra's framework: multi-perspective reasoning, skillful means, | 36 ★ | Low risk |
| local_faiss_mcp Local FAISS vector database for RAG with document ingestion (PDF, TXT, MD, DOCX), semantic search, re-ranking | 36 ★ | Low risk |
| remem Local-first memory for Claude Code and Codex: hooks capture sessions and an LLM distills them into SQLite, wit | 34 ★ | Low risk |
| neotoma Deterministic state layer for agents: versioned entities like contacts, tasks and decisions with immutable obs | 34 ★ | Low risk |
| enquire-mcp Long-term agent memory backed by a local Obsidian vault: hybrid retrieval with reranking, agentic RAG, wikilin | 34 ★ | Low risk |
| tokenmizer Session memory via a local OpenAI-compatible proxy that extracts tasks, decisions and files into a knowledge g | 33 ★ | Low risk |
| obsidian-mcp-pro Obsidian vault access: full-text search, note CRUD, frontmatter queries, tags, backlinks, graph traversal, orp | 33 ★ | Low risk |
| cortex-plugin Claude Code memory plugin that mines past sessions for decisions, conventions and bug fixes, stores them in an | 32 ★ | Low risk |
| brightspace-d2l-mcp D2L Brightspace for students: due dates with submission status, grades, assignments and rubrics, announcements | 31 ★ | Low risk |
| MCP-Context-Provider Static server providing persistent tool-specific context and rules to AI models. | 31 ★ | Low risk |
| data-olympus Git-native Markdown knowledge base for coding agents with proposed vs. accepted guidance, validity windows, su | 30 ★ | Low risk |
| geml Address Markdown and GEML documents by block instead of by line: list, get, set, add, delete, rename, revert, | 29 ★ | Low risk |
| mcp-memory-gateway Pre-action gates that prevent coding agents from repeating known mistakes by turning captured feedback and fai | 29 ★ | Low risk |
| gnosis-mcp Make Markdown documentation searchable: loads it into SQLite or PostgreSQL with keyword search and optional pg | 29 ★ | Low risk |
| vault-cortex Standalone Obsidian vault server: hybrid search, notes and files, memory and tasks; run locally or self-host f | 28 ★ | Review before installing |
| engram-rs Hierarchical agent memory engine with automatic decay, promotion, semantic deduplication and a self-organizing | 28 ★ | Low risk |
| SignsofAI Explainable AI-writing detection and originality checking in English and Spanish, plus citation checks and hid | 27 ★ | Low risk |
| mcp-memory-server Hosted memory that learns and forgets: feedback re-ranks useful memories, recall fades by recency and similar | 27 ★ | Low risk |
| zenbrain Seven-layer local agent memory that routes input into facts, episodes or procedures, searches all layers and c | 27 ★ | Low risk |
| RAGStack-Lambda Access RAGStack serverless knowledge bases on AWS: search, chat with AI answers, upload documents and media, s | 25 ★ | Low risk |
| memory-mcp-1file Persistent semantic and graph-based agent memory in a single self-contained binary with embedded database and | 25 ★ | Low risk |
| fidelis Local-first memory with verbatim recall, querying, health checks and context-sensitive orientation, using LLM- | 24 ★ | Low risk |
| NOUZ-MCP Semantic knowledge graph for Obsidian with graph, classification and hierarchy modes, local embeddings, semant | 24 ★ | Low risk |
| world-model-mcp Temporal codebase knowledge graph that links test failures to code changes, learns co-edit patterns, predicts | 24 ★ | Low risk |
| statelessagent Local agent memory with provenance tracking that detects when sources change, plus session handoffs, decision | 24 ★ | Low risk |
| jarvis-orb Four-tier memory (episodic, semantic, project, procedural) with temporal scoring, contradiction detection, ent | 24 ★ | Low risk |
| celiums-memory Cognitive memory engine with knowledge modules, circadian rhythm awareness, emotional state tracking, hybrid P | 23 ★ | Review before installing |
| mnemos Persistent memory for coding agents storing architecture decisions, bug root causes and conventions, with full | 23 ★ | Low risk |
| sourcelibrary-v2 Search and cite rare historical texts (alchemy, Hermeticism, Renaissance philosophy) from Source Library with | 23 ★ | Low risk |
| semantic-scholar-mcp Semantic Scholar academic papers: search, paper and author retrieval, citation-graph traversal and recommendat | 23 ★ | Low risk |
| memory-mcp Store and retrieve conversation memories from multiple LLMs in MongoDB, with timestamps and LLM identification | 22 ★ | Low risk |
| memo Local-first semantic memory: hybrid search, Markdown storage, MLX or CPU embeddings, contradiction detection, | 22 ★ | Low risk |
| Yggdrasil Local-first memory for AI coding agents on SQLite/FTS5, curated and semantically de-duplicated, with data stor | 22 ★ | Low risk |
| Connapse Self-hosted knowledge backend for agents with hybrid vector and keyword search and container-isolated indexes. | 21 ★ | Low risk |
| mcp-me Digital identity for AI tools: your bio, career, skills and projects in local YAML profiles, auto-generated fr | 21 ★ | Low risk |
| annota Annotate papers in Zotero: highlight key findings with semantic color coding, explain formulas and write struc | 20 ★ | Low risk |
| distil Reversibly compress large tool outputs into recoverable handles, expand them on demand and track token and cos | 20 ★ | Low risk |
| Mnemosyne-Neural-OS Human-governed memory in local, domain-separated vaults with hybrid retrieval; also reads other coding agents' | 20 ★ | Low risk |
| BrowserAI-Dev Evidence-backed web research: real-time search with cited claims, confidence scores and a mode comparing raw L | 20 ★ | Low risk |
| CacheOverflow Knowledge marketplace where agents search, publish and unlock previously solved problems, earning tokens for s | 19 ★ | Review before installing |
| GoodMemory Local-first, auditable memory with scoped user/project storage in SQLite or Postgres, read-only recall by defa | 19 ★ | Low risk |
| mediawiki-mcp-server Connect to any MediaWiki wiki (Wikipedia, Fandom, corporate wikis) to search, read and edit pages, analyze lin | 19 ★ | Review before installing |
| obsidian-mcp-server Remote Obsidian vault management over SSE: notes, directories, frontmatter, tags, search and link operations, | 19 ★ | Low risk |
| viznoir Scientific visualization for CFD, FEA and SPH: render, slice, contour, volume-render and animate OpenFOAM, VTK | 19 ★ | Low risk |
| agentpack Repo-native task continuity for coding agents: a reviewed task-state ledger of decisions, dead ends, evidence | 18 ★ | Low risk |
| project-tessera Local workspace memory: indexes Markdown, CSV and session logs into a vector store with hybrid search, cross-s | 18 ★ | Low risk |
| Noosphere Shared community repository of insights, decisions, warnings and patterns with semantic search, a 3D interacti | 18 ★ | Review before installing |
| obsidian-mcp Self-hosted Obsidian server: semantic and full-text search on PostgreSQL/pgvector, wikilink graph traversal, a | 18 ★ | Low risk |
| alaya Neuroscience-inspired local agent memory that stores episodes, consolidates knowledge over time and builds a p | 18 ★ | Low risk |
| ictexam-mcp Read exam papers, classes, subjects, the gradebook and per-question item analysis from ICTExam, an exam author | 17 ★ | Low risk |
| obsidian-codex-mcp Local Obsidian vault access working directly on Markdown files without the Obsidian app or plugins, with read- | 17 ★ | Low risk |
| agentic-task-system Turns your task manager into agent memory with hybrid retrieval over TickTick or an Obsidian vault, without a | 17 ★ | Low risk |
| easy-obsidian-mcp Create, read, update and search notes in local Obsidian vaults via filesystem access. | 17 ★ | Low risk |
| engram Git-backed, Obsidian-compatible Markdown second brain for agents: search ranks live notes above superseded one | 17 ★ | Low risk |
| zaxy Event-sourced agent memory on a hash-chained log with an embedded Kuzu temporal knowledge graph, salience-base | 17 ★ | Low risk |
| alcove On-demand BM25 search over private project docs for coding agents, keeping docs out of public repos. | 16 ★ | Low risk |
| fable Full-text and semantic search over Claude Code transcript history, with exact thread recall and durable rememb | 16 ★ | Low risk |
| cross-llm-mcp Cross-LLM communication and memory sharing so different AI models can collaborate and share context across con | 16 ★ | Low risk |
| obsidian-everywhere Graph-native Obsidian vault access: search, backlinks, n-hop neighborhoods, paginated reads and safe partial a | 16 ★ | Low risk |
| MailFathom Self-hosted email search: syncs IMAP mailboxes into PostgreSQL to list, search and read mail and ask cited que | 16 ★ | Low risk |
| Lians Bitemporal agent memory with deterministic fact supersession, point-in-time recall, memory lineage, conflict t | 16 ★ | Low risk |
| remembra Self-hosted persistent agent memory with entity resolution, PII detection, AES-256-GCM encryption at rest and | 16 ★ | Low risk |
| cognirepo Persistent memory and codebase context for coding agents: FAISS vector store, AST symbol index, knowledge grap | 15 ★ | Low risk |
| recallnest Local-first memory for coding agents: hybrid vector/BM25 retrieval with reranking, knowledge graph, session ch | 15 ★ | Low risk |
| deep-thinker Reasoning via a DAG thought graph with multiple strategies (dialectic, analogical, abductive and more), stuck | 15 ★ | Low risk |
| linksee-memory Local-first cross-agent memory in one SQLite file with a layered structure, Ebbinghaus-style forgetting and de | 15 ★ | Low risk |
| kremis Local deterministic knowledge graph on redb with no LLM or embedding calls, BLAKE3 state hashing and canonical | 15 ★ | Low risk |
| Midas Local-first long-horizon agent memory: source-traceable recall, belief revision, selective forgetting and a gu | 15 ★ | Low risk |
| NexusMem Correlates failed shell commands and their exit codes with whatever later fixed them, alongside git diffs and | 15 ★ | Low risk |
| yade-mcp YADE discrete element method (DEM) simulation: search API docs, run code via a REPL or background tasks, monit | 15 ★ | Low risk |
| longhand Persistent local memory for Claude Code: indexes all sessions verbatim into SQLite and ChromaDB for semantic r | 14 ★ | Low risk |
| agent-memory Git-native project memory for coding agents: Markdown in your repo, reviewable staged updates, secret/PII-safe | 14 ★ | Low risk |
| gramps-web-mcp Gramps Web genealogy: search and edit family tree records, explore ancestors, descendants, relationships and t | 14 ★ | Low risk |
| lennys-quotes Search Lenny's Podcast transcripts with YouTube timestamps for product management insights on PRDs, strategy a | 13 ★ | Low risk |
| mcp-persona-sessions Structured, persona-driven sessions for interview preparation, personal reflection and coaching, with timers a | 13 ★ | Low risk |
| empathy-framework Five-level AI collaboration system with persistent local-first memory via MemDocs and anticipatory capabilitie | 13 ★ | Low risk |
| apple-notes-mcp Read and write Apple Notes with bidirectional Markdown conversion: SQLite queries for listing and search, Appl | 12 ★ | Low risk |
| claude-find Retrieve memory from across your Claude Code sessions on demand. | 12 ★ | Low risk |
| memory-os-cli XMemo: user-owned agent memory to save, search, recall and manage scoped memories across AI tools. | 12 ★ | Review before installing |
| mnemo-mcp Persistent memory with SQLite hybrid search (FTS5 and semantic), built-in Qwen3 embeddings and rclone sync acr | 12 ★ | Low risk |
| memex Watches git repos and builds a temporal knowledge graph of modules, symbols, decisions and open problems via G | 12 ★ | Low risk |
| tripitaka-mcp Search, cite and compare the Pāli Canon (Tipiṭaka): hybrid search, full suttas with cross-references, aligned | 12 ★ | Low risk |
| scholar-feed-mcp Semantic search over CS and AI papers with citation-graph traversal, full-text extraction, embeddings and BibT | 12 ★ | Low risk |
| campus-cli Student access to university systems via SSO: courses, assignments, grades, feedback, announcements and materi | 11 ★ | Low risk |
| coldstart Codebase memory for coding agents: a deterministic AST index finds task-relevant files, and in-repo Markdown n | 11 ★ | Low risk |
| memory-mcp Two-tier memory (hot cache and cold semantic search) that promotes frequently used patterns, extracts knowledg | 11 ★ | Low risk |
| hive On-demand Obsidian vault access: adaptive context loading, full-text and ranked search, health checks, auto gi | 11 ★ | Low risk |
| LIFE Persistent identity for AI agents: servers for drives, relationships, semantic memory with decay, working thre | 11 ★ | Low risk |
| scholar-sidekick-mcp Resolve scholarly identifiers (DOI, PMID, ISBN, arXiv and more) to CSL JSON, format citations in thousands of | 11 ★ | Low risk |
| klypix-mcp Versioned project brain for coding agents, committed with the repo: decisions, corrections, evidence anchors t | 10 ★ | Low risk |
| lockstep Shared decision memory for teams using AI coding agents: captures engineering decisions, ranks them by blast r | 10 ★ | Low risk |
| genome Local persistent agent memory without LLM calls: semantic recall over SQLite with bi-temporal fact tracking. | 10 ★ | Low risk |
| memory-arbiter-mcp Local memory middleware: targeted retrieval instead of full-memory loading, rule-based conflict arbitration an | 10 ★ | Low risk |
| lore Local semantic search across Claude Code conversations with hybrid vector and keyword search, background index | 10 ★ | Low risk |
| obsidian-tc Obsidian vault access with role-based access control, native search, multi-vault support, pluggable embeddings | 10 ★ | Low risk |
| tribal Self-hosted semantic memory for an engineering team's tribal knowledge: the decisions and reasoning behind the | 10 ★ | Low risk |
| google-scholar-mcp Google Scholar search as JSON with author and year filters, cited-by and all-versions lookups, and formatted c | 10 ★ | Low risk |
| touch-browser Evidence-grounded web research: verify claims on pages with citations, confidence bands and policy reports, an | 10 ★ | Low risk |
| legiscan-mcp Legislative data from all 50 US states and Congress via the LegiScan API: search bills, get full text, track v | 10 ★ | Low risk |
| stellarjay Safe write access for AI agents: an append-only business fact store where every change is kept, attributed to | 9 ★ | Review before installing |