419 knowledge & memory MCP servers, most popular first. The most popular is servers. Every listing shows its security level and install command.
| Name | Popularity | Security |
|---|---|---|
| servers Knowledge graph-based persistent memory for maintaining context. | 91.3k ★ | Low risk |
| Context7 Up-to-date code documentation for LLMs and AI code editors. | 63.2k ★ | Review before installing |
| hindsight Hindsight: long-term memory for AI agents modeled on human memory. | 50.9k ★ | Low risk |
| Cognee Memory manager for AI apps and agents using graph and vector stores, with ingestion from many data sources. | 32.4k ★ | Low risk |
| Skill Seeker Turn docs, GitHub repos, PDFs, videos, Confluence, Notion and Slack/Discord into AI skills and RAG knowledge, | 15.2k ★ | Low risk |
| basic-memory Local-first AI memory: a semantic knowledge graph of Markdown files that humans and LLMs both read and write, | 4.3k ★ | Review before installing |
| NoteDiscovery Self-hosted Markdown knowledge base with a web UI: search, read, create, edit, tag and template notes. | 2.8k ★ | Low risk |
| memanto Universal memory agent for AI: provides semantic search, namespace management, text/vector operations and RAG | 2.3k ★ | Review before installing |
| mcp-memory-service Memory service with semantic search, persistent storage and autonomous memory consolidation. | 2k ★ | Low risk |
| mcp-obsidian Safe read/write access to Obsidian vaults: search, batch operations, tag management and frontmatter handling. | 1.7k ★ | Low risk |
| ApeRAG RAG platform combining Graph RAG, vector search and full-text search for building knowledge graphs and context | 1.3k ★ | Low risk |
| deja-vu Local memory over session histories from Claude Code, Codex CLI and opencode: lexical search, session-start au | 1.2k ★ | Low risk |
| open-ontologies Ontology engineering for OWL, RDF and SPARQL: validate, query, diff, lint, version and govern knowledge graphs | 1.1k ★ | Low risk |
| mcp-server-chatsum Query and summarize your chat messages with AI prompts. | 1k ★ | Low risk |
| iai-personal-memory-engine Local memory daemon with episodic, semantic and procedural tiers, SQLite and hnswlib storage, sleep-cycle cons | 911 ★ | Low risk |
| projectmem Local-first memory for coding agents: records issues, failed attempts, fixes and decisions, re-injects them an | 866 ★ | Low risk |
| idea-reality-mcp Check for existing competition before building: scan GitHub, Hacker News, npm, PyPI and Product Hunt for simil | 825 ★ | Low risk |
| memora Persistent memory with knowledge graph visualization, semantic/hybrid search, cloud sync (S3/R2) and cross-ses | 742 ★ | Review before installing |
| vestige Local-first cognitive agent memory with FSRS-6 scheduling, smart ingest, SQLite storage, portable sync, an emb | 652 ★ | Low risk |
| thoughtdag Search local AI-agent conversation history by file or exact phrase and recall original source turns through fo | 651 ★ | Low risk |
| MisakaNet Agent failure memory: search verified debugging lessons from real engineering sessions. | 528 ★ | Low risk |
| telemem Mem0-compatible long-term and multimodal agent memory: character-isolated profiles, semantic deduplication, op | 494 ★ | Low risk |
| entroly Context control layer for coding agents: compression, prompt-prefix stabilization for caching, cheaper-model r | 477 ★ | Low risk |
| beever-atlas Team knowledge base turning Slack, Discord, Teams and Mattermost chats into a knowledge graph and wiki with ci | 449 ★ | Low risk |
| mcp-local-rag Local document search: semantic search over PDF, DOCX, TXT and Markdown files with LanceDB vector storage and | 414 ★ | Low risk |
| graphlit-mcp-server Ingest content from Slack, Discord, websites, Google Drive, Linear or GitHub into a Graphlit project, then sea | 378 ★ | Low risk |
| AgentRecall Persistent cross-session agent memory that surfaces the most relevant past memories using the Intelligent Dist | 371 ★ | Low risk |
| MemoryMesh Graph-based memory focused on AI role-play and story generation. | 354 ★ | Low risk |
| shodh-memory Cognitive agent memory with Hebbian learning, a three-tier architecture and knowledge graphs, running offline | 311 ★ | Low risk |
| knowledge-rag Offline RAG for Claude Code with hybrid BM25 and semantic search, cross-encoder reranking, Markdown-aware chun | 297 ★ | Low risk |
| emulo Loads a personal profile mined from your local Claude Code, Codex and OpenCode logs so agents work the way you | 297 ★ | Low risk |
| markmap-mcp-server Convert Markdown into interactive markmap mind maps with PNG/JPG/SVG export and live browser preview. | 289 ★ | Low risk |
| YourMemory Persistent agent memory with Ebbinghaus-style decay, hybrid BM25/vector retrieval, entity graph for multi-hop | 270 ★ | Low risk |
| mcp-ragdocs Retrieve and process documentation through vector search to augment responses with relevant documentation cont | 265 ★ | Low risk |
| sage Local institutional memory for agents where BFT consensus among validators approves every memory before it is | 254 ★ | Low risk |
| omega-memory Local-first persistent memory for coding agents with semantic search, auto-capture, cross-session learning and | 225 ★ | Low risk |
| pfc-mcp ITASCA PFC discrete element simulation: browse documentation, execute scripts, capture plots and manage long-r | 219 ★ | Low risk |
| gistpad-mcp Manage personal knowledge, daily notes and reusable prompts in GitHub Gists, as a companion to GistPad. | 208 ★ | Low risk |
| mengram Agent memory with semantic, episodic and procedural types, a knowledge graph, Claude Code auto-save/recall hoo | 204 ★ | Low risk |
| notebooklm-mcp Automate Google NotebookLM: Q&A with citations, audio podcasts, video, content generation, source management a | 198 ★ | Low risk |
| In-Memoria Cumulative memory and pattern learning for coding assistants, with local SQLite/SurrealDB storage for semantic | 175 ★ | Low risk |
| mcp-summarizer Summarize plain text, web pages, PDF documents, EPUB books and HTML content. | 167 ★ | Review before installing |
| zettelkasten-mcp Zettelkasten knowledge management: create, link and search atomic notes. | 167 ★ | Low risk |
| mcp-zotero Work with collections and sources in your Zotero Cloud library. | 164 ★ | Low risk |
| akb Organizational knowledge base: Markdown docs, PostgreSQL tables and files linked by a URI graph, with hybrid s | 163 ★ | Low risk |
| piia-engram Persistent user identity across AI tools: preferences, lessons and decisions in local JSON with staged verific | 162 ★ | Low risk |
| prism-mcp Local SQLite agent memory with a web dashboard, session rewind/replay, cross-client memory sharing, morning br | 157 ★ | Low risk |
| context-keeper LLM-driven context and memory management: short- and long-term memory with vector, timeline and knowledge grap | 155 ★ | Review before installing |
| ContextLattice Private-by-default memory and context layer for agents with staged retrieval across fused data backends and lo | 154 ★ | Low risk |
| openzim-mcp Search and navigate Wikipedia and other ZIM-format knowledge archives offline, with smart retrieval and cachin | 145 ★ | Low risk |
| MediaWiki-MCP-Server Read, search and edit any MediaWiki wiki, including Wikipedia and Fandom, with multi-wiki support and Semantic | 137 ★ | Review before installing |
| memorylane Desktop app that captures screen activity, stores AI summaries and OCR text locally, and exposes the history v | 120 ★ | Low risk |
| docsmint Cloud or self-hosted knowledge workspace with hybrid document search, GraphRAG, and scoped MCP tools for readi | 118 ★ | Low risk |
| deep-research-mcp Deep research via the OpenAI Responses API or Open Deep Research (smolagents), with web search and code interp | 115 ★ | Low risk |
| mem0-mcp-selfhosted Self-hosted mem0 for Claude Code: Qdrant vector search, Neo4j knowledge graph, Ollama embeddings and session h | 111 ★ | Low risk |
| knowl Persistent local memory for coding agents that retires replaced facts at write time, so agents read the curren | 106 ★ | Low risk |
| loci Queryable second brain over your scattered notes, docs, PDFs and chat exports: hybrid retrieval (vector + BM25 | 100 ★ | Low risk |
| claudex Persistent memory and full-text search over Claude Code conversation history indexed into SQLite, with session | 97 ★ | Low risk |
| omniseek Self-hosted perception server: local bilingual ASR, vision, cross-lingual search, credentialed login-walled so | 94 ★ | Low risk |
| claude-soul Learning engine for Claude Code: extracts signals from sessions, runs periodic reflections and promotes or ret | 92 ★ | Low risk |
| ragie-mcp-server Retrieve context from your Ragie knowledge base, connected to sources like Google Drive, Notion and Jira. | 91 ★ | Low risk |
| Arthor-Agent Cybersecurity assessment of documents, questionnaires and reports: multi-format parsing, RAG knowledge base, r | 88 ★ | Low risk |
| notebooklm-mcp-secure Security-hardened Google NotebookLM access: session-based conversations, notebook library management and sourc | 86 ★ | Low risk |
| AuraSDK Persistent, encrypted cognitive memory that works offline. | 85 ★ | Low risk |
| DecisionNode Record development decisions as structured JSON with Gemini embeddings and search them semantically from a loc | 83 ★ | Low risk |
| context-mcp Self-hosted documentation indexer that serves docs from various sources to agents with semantic search. | 83 ★ | Low risk |
| pond Lossless archive and search for AI agent sessions across clients. | 83 ★ | Low risk |
| patent-literature-search-mcp Natural-language patent and scientific literature search via Patsnap: semantic and BM25 search, structured fil | 83 ★ | Low risk |
| robrain Self-hosted decision memory for coding agents: captures architectural decisions and rejected alternatives, and | 82 ★ | Low risk |
| tela Self-hostable Markdown team wiki that agents can search, read and write, plus Atlas, which generates a cited w | 82 ★ | Review before installing |
| Cortex Neuroscience-inspired memory for Claude Code on PostgreSQL/pgvector: decay, consolidation, a predictive-coding | 75 ★ | Low risk |
| paper-preflight Checks every reference of a LaTeX paper against Crossref, dblp, arXiv, DataCite, PubMed and OpenAlex records: | 75 ★ | Low risk |
| codemem Persistent coding memory across sessions, machines and teammates, with memory search, optional sync, project s | 73 ★ | Low risk |
| total-agent-memory Local memory for coding agents: temporal knowledge graph with fact invalidation, procedural and episodic memor | 73 ★ | Low risk |
| scrivener-mcp Work with Scrivener 3 writing projects: document management, writing analysis, semantic search, character and | 67 ★ | Low risk |
| Myco Cross-session, cross-project agent memory built on a self-validating filesystem graph derived from ASTs and Ma | 66 ★ | Low risk |
| agentcairn Local-first agent memory: a Markdown Obsidian vault as source of truth plus a rebuildable DuckDB index for hyb | 66 ★ | Low risk |
| docx-mcp Read and edit Word (.docx) documents with tracked changes, threaded comments, footnotes, OOXML-level validatio | 64 ★ | Low risk |
| devrag Local RAG for semantic vector search over Markdown documents with sqlite-vec and multilingual-e5-small embeddi | 64 ★ | Low risk |
| research-hub Research workspace for Zotero, Obsidian and NotebookLM: search arXiv, Semantic Scholar, PubMed and Crossref, i | 64 ★ | Low risk |
| context-awesome Search curated awesome lists and fetch the most relevant resources for your agent. | 61 ★ | Low risk |
| ChatCrystal Local-first memory for AI coding conversations: imports chats from coding assistants into notes with semantic | 61 ★ | Low risk |
| brightspace-mcp-server Check D2L Brightspace grades, due dates, assignments, announcements, syllabus, rosters, discussions and course | 59 ★ | Low risk |
| zoteus Zotero integration: hybrid search, PDF passages with page locators, CSL bibliographies, add by DOI, group libr | 59 ★ | Review before installing |
| people-context Local-first memory about the people in your life: identity resolution, relationships, facts, interactions, rem | 58 ★ | Low risk |
| roampal-core Outcome-based persistent memory for Claude Code and OpenCode: memories that help get promoted, misleading ones | 54 ★ | Low risk |
| engram Agent memory with semantic recall, automatic consolidation, contradiction detection and a bi-temporal knowledg | 47 ★ | Low risk |
| mcp-server Reusable personas, skills, templates, agents and memory for AI clients, with dynamic permissions, versioning a | 46 ★ | Low risk |
| assistant-mcp Connect to your Pinecone Assistant and retrieve context from its knowledge engine. | 46 ★ | Low risk |
| callimachus Local hybrid search (SQLite FTS5 and on-device vectors) over coding-agent conversation history from multiple t | 45 ★ | Low risk |
| membase-mcp Save and query agent memory in a distributed way with Membase. | 45 ★ | Low risk |
| pronounce Community pronunciation dictionary for developer and product names (kubectl, nginx, GIF) with IPA, respellings | 44 ★ | Low risk |
| mcp-server Persistent memory for AI coding tools with semantic code search, knowledge graphs, impact analysis and decisio | 44 ★ | Low risk |
| mendeley-mcp Search your Mendeley library, browse folders, get document metadata, search the global catalog and add papers | 44 ★ | Low risk |
| Waggle-mcp Persistent graph memory that extracts facts from conversations into typed nodes with local embeddings, support | 44 ★ | Low risk |
| lean-memory Embedded local agent memory in one SQLite file per namespace: hybrid retrieval, append-only history queryable | 43 ★ | Low risk |
| Kage Git-native memory for coding agents: JSON entries in the repo, verified against cited code so hallucinated cit | 41 ★ | Low risk |
| kaeru Memory for LLM agents: a local graph where the agent itself keeps decisions, tasks, hypotheses and reasoning b | 40 ★ | Low risk |
| rms-memory-mcp Local-first memory for coding agents: hybrid LanceDB/Tantivy search, Markdown and code indexes, per-project va | 40 ★ | Low risk |
| connectrylab-architect-cert-mcp Claude Certified Architect exam prep: scenario-based questions, practice exams, concept handouts, a guided cap | 38 ★ | Low risk |