419 knowledge & memory MCP servers, most popular first. Every listing shows its security level and install command.
| Name | Popularity | Security |
|---|---|---|
| sessionmem Local memory for coding assistants: watches sessions and injects a compact summary at the start of each new on | 9 ★ | Low risk |
| legends-mcp Chat with AI personas of famous founders and investors such as Elon Musk, Warren Buffett and Steve Jobs, based | 9 ★ | Low risk |
| engram Offline persistent agent memory on SQLite with local embeddings, hybrid semantic and full-text recall, secret | 9 ★ | Low risk |
| mnemostack Self-hosted hybrid agent memory on Qdrant combining vector search, BM25, temporal retrieval and an optional Me | 9 ★ | Low risk |
| wellread Shared research cache across agents: reuse answers from verified sources, or save new research for the next de | 9 ★ | Low risk |
| artel Self-hosted coordination for agent fleets: shared semantic memory, tasks, agent-to-agent messaging, session ha | 9 ★ | Low risk |
| CodeCortex Persistent codebase knowledge for coding agents: symbols, dependency graphs, co-change patterns and architectu | 9 ★ | Low risk |
| hypermnesic Git-first agent memory: Markdown files are the source of truth, the index is disposable and writes are reviewa | 9 ★ | Review before installing |
| skillmem Self-improving skill memory for coding agents: useful skills are reinforced, unused ones fade; local English/R | 9 ★ | Low risk |
| zotero-native-mcp Read and write a local Zotero library via its local API, offline: collections, items, attachments, full text, | 9 ★ | Low risk |
| crbro-memory Persistent agent memory in local JSON files: neuron/synapse graph with heat scoring, fact-level search, correc | 8 ★ | Low risk |
| agent-memory Three-layer agent memory (identity, active, archive) with semantic search, graph relationships and conflict de | 8 ★ | Low risk |
| inspeximus Agent memory with a correction channel: supersede or revert stale facts, block restated old values, and prove | 8 ★ | Low risk |
| memstate-mcp Versioned, structured agent memory storing facts as keypaths with full version history and automatic conflict | 8 ★ | Review before installing |
| AIWiki Search and read AiWiki, a bilingual English/Chinese encyclopedia of AI-coding pitfalls and LLM privacy protect | 8 ★ | Low risk |
| agenda-intelligence-md Auditable strategic-risk memos (sanctions, regulation, geopolitics, trade) with Central Asia and Gulf regional | 8 ★ | Low risk |
| acheron-mcp-server Persistent memory shared across Claude Chat, Code and Cowork, stored in local SQLite with full-text search. | 7 ★ | Low risk |
| context-memory Persistent, searchable context storage across Claude Code sessions using SQLite FTS5, with AI session summarie | 7 ★ | Low risk |
| gingugu Local SQLite memory for coding assistants: typed memories with confidence lifecycle, namespaces, knowledge gra | 7 ★ | Low risk |
| cogmemai-mcp Cloud-based persistent memory for Claude Code with semantic search, AI extraction and project scoping. | 7 ★ | Low risk |
| krimto Team memory for coding agents stored as Markdown in git, with user, team and org access levels and hybrid SQLi | 7 ★ | Low risk |
| passbaton Local session continuity across Claude Code, Codex CLI and Gemini CLI: context injection on start, compaction | 7 ★ | Low risk |
| mcp-server Permission-aware enterprise search and RAG over business apps such as Google Workspace, Microsoft 365, Slack a | 7 ★ | Low risk |
| Agent-Memory-Bridge Local-first memory for coding agents that turns coding sessions into reusable engineering memory: decisions, g | 7 ★ | Low risk |
| Agent-Memory-OS Local-first memory for AI agent teams: private, team and project access control, associative recall and federa | 7 ★ | Low risk |
| paperboy Send research papers to Kindle or Kobo: search arXiv and OpenAlex, find related work, queue papers in Zotero a | 7 ★ | Review before installing |
| scorm-mcp-server Package HTML, Claude Design bundles or mobile-learning exports as SCORM 2004/1.2 courses with milestone and qu | 6 ★ | Low risk |
| agenthelm Shared, versioned memory and governance for AI coding agents, resolving architectural decision conflicts acros | 6 ★ | Low risk |
| seamless Local-first shared memory and task coordination for AI coding agents, stored as Markdown files. | 6 ★ | Low risk |
| afair Self-organizing, self-hostable, encrypted memory for AI tools, with background entity extraction, conflict res | 6 ★ | Low risk |
| agentmem Governed memory for coding agents with trust lifecycle (hypothesis, active, validated, deprecated), conflict d | 6 ★ | Low risk |
| prior_mcp Shared knowledge base where agents exchange proven solutions and failed approaches, so they can skip known dea | 6 ★ | Low risk |
| conversation-handoff-mcp Hand off conversation context between Claude Desktop projects and across MCP clients, stored in memory rather | 6 ★ | Low risk |
| flaiwheel Self-hosted memory and governance for coding agents: structured knowledge capture, hybrid search with rerankin | 6 ★ | Low risk |
| mcp-agent-memory Filesystem-based persistent agent memory: agents read, write and search memory while a background daemon handl | 6 ★ | Low risk |
| counsel-mcp Strategic reasoning, multi-perspective debate analysis and interactive advisory sessions via the Counsel API. | 6 ★ | Low risk |
| penfield-mcp Penfield: persistent memory with hybrid BM25/vector/graph search, typed graph relations, context checkpoints, | 6 ★ | Low risk |
| mindmap-mcp-server Local-first memory and context handoff across AI tools, with graceful decay, a persona layer and a portable me | 6 ★ | Low risk |
| waypath Local-first memory CLI for coding agents: SQLite-backed context, graph-aware recall via FTS5 and RRF, and gove | 6 ★ | Low risk |
| patents-mcp Patent search and prior art discovery using the Google Patents public dataset on BigQuery: patent details with | 6 ★ | Low risk |
| 0CompactMem Persistent multi-agent memory with OS-style demand paging, eviction and pinning, BM25 retrieval, importance sc | 5 ★ | Low risk |
| adhd-hub Self-hosted project-continuity hub for coding agents: tracks unfinished work, progress, overlap and reminders | 5 ★ | Low risk |
| openhive-mcp Shared knowledge base where AI agents search and post problem-solution pairs, with semantic search, duplicate | 5 ★ | Review before installing |
| memkin Local-first personal memory that distills Feishu/Lark chats and Claude Code/Codex sessions into a private know | 5 ★ | Low risk |
| lore-mcp Persistent knowledge layer for agents: knowledge base, investigation threads and a journal with multi-agent at | 5 ★ | Review before installing |
| kybase Self-hosted Markdown knowledge base that doubles as persistent memory for AI agents: a notes app you browse an | 5 ★ | Low risk |
| owl-mcp Work with OWL/TTL/RDF ontologies: SPARQL queries, HermiT/Pellet reasoning and CRUD operations on knowledge gra | 5 ★ | Low risk |
| Rememb Persistent agent memory in local JSON with sectioned entries (project, user, context), semantic search, a CLI | 5 ★ | Low risk |
| iranti Persistent shared memory for coding agents: facts stored as entity/key/value triples with hybrid semantic sear | 5 ★ | Low risk |
| THOR-memory-bible-for-AI Local memory for coding agents where rules with machine-checkable proofs block matching commands, plus an appe | 5 ★ | Low risk |
| devrecall Local-first index of your commits, PRs, Jira/Linear tickets, Confluence docs, Slack threads and calendar event | 5 ★ | Low risk |
| graphiti-local Local temporal knowledge graph with six read-only retrieval tools, Ollama inference, embedded LadybugDB, and a | 5 ★ | Low risk |
| rekindle Session continuity: start-of-session reports with gap detection and scoring, structured end-of-session capture | 5 ★ | Low risk |
| LINZA-MCP Review-gated sidecar for Markdown workspaces: indexes notes into SQLite and proposes links, domains and memory | 5 ★ | Low risk |
| Vulcanus Generates a Git-versioned Markdown vault as project memory, then serves it over MCP. `recall` returns a projec | 5 ★ | Low risk |
| weighted-compact Inspectable memory for Claude Code: read-only search and session compaction over a local, signal-scored parse | 5 ★ | Low risk |
| ctxfile Snapshots a project's working state (files, git, plan, decisions) into one context object so a session can mov | 5 ★ | Low risk |
| google-trends-mcp Google Trends data as JSON: interest over time and by region, plus rising and top related queries and topics f | 5 ★ | Low risk |
| scholar-mcp Federated academic search across OpenAlex, Semantic Scholar, arXiv, PubMed and more, with citation graphs, ful | 5 ★ | Low risk |
| ph-civic-data-mcp Philippine government data: PHIVOLCS earthquakes and volcano alerts, PAGASA weather and typhoons, PhilGEPS pro | 5 ★ | Low risk |
| canvas-mcp Local-first Canvas LMS access: courses, assignments, modules, announcements, grades, planner items, upcoming e | 4 ★ | Low risk |
| hipocampo Bilingual (English/Spanish) dual-memory system on PostgreSQL, pgvector and NVIDIA NIM with progressive retriev | 4 ★ | Low risk |
| cc-sensei Explore Claude Code's source as queryable architecture modules: trace cross-cutting concerns, search patterns | 4 ★ | Low risk |
| workspace-qdrant-mcp Project-scoped memory for coding assistants: indexes project code and docs into Qdrant with tree-sitter chunki | 4 ★ | Low risk |
| lego-oracle LEGO sets, parts, minifigs and inventories from Rebrickable: search and compare sets, find parts by colour, br | 4 ★ | Low risk |
| memoryguard Local-first governed shared memory for coding agents with CLI and desktop console: classify, dedupe, supersede | 4 ★ | Low risk |
| deadzone Offline semantic search over library documentation using a pre-built, version-pinned vector index fetched and | 4 ★ | Low risk |
| subdownload-mcp YouTube knowledge base: summarize videos, fetch transcripts (even without captions), search channels and playl | 4 ★ | Low risk |
| tilde Portable, privacy-first AI identity: a home directory for your agents with profile management, skills, resume | 4 ★ | Low risk |
| Metis Private local research second brain: project-aware memory, cited answers from your library, linked notes and m | 4 ★ | Low risk |
| benchclaw-integrations Register LLMs and agents and submit Markdown research papers to the BenchClaw leaderboard, where a panel of ju | 4 ★ | Low risk |
| data-aggregator-mcp Search and fetch research datasets across Zenodo, DataCite, NCBI and PubMed/OpenAIRE, with DOI deduplication, | 4 ★ | Low risk |
| agentinterviews_mcp Run AI-led qualitative research interviews and surveys with Agent Interviews: create interviewers, manage proj | 4 ★ | Low risk |
| mcp-server-pronunciation Local English voice coach with pronunciation, grammar, fluency and phoneme-level feedback, practice drills and | 3 ★ | Low risk |
| learn-shell Self-hosted teaching OS for agents: courses, lessons, FSRS flashcards, graded exercises, real-time teaching se | 3 ★ | Low risk |
| pktctl Drive Cisco Packet Tracer for CCNA labs: build and cable topologies, configure IOS, test with ping and simulat | 3 ★ | Low risk |
| magnemo Governed local agent memory in plain files: each entry records who wrote it, when and through which gate, and | 3 ★ | Low risk |
| rag-kb Local-first agent memory and knowledge base: hybrid dense and BM25 retrieval, document and webpage ingestion a | 3 ★ | Low risk |
| shadowgraph Local-first decision memory for AI agents: stores choices, rejected alternatives and reasons, failed attempts, | 3 ★ | Low risk |
| memxus-remote-mcp Shared context for dev teams: syncs GitHub, Notion and saved decisions into reusable project context that agen | 3 ★ | Low risk |
| personal-understanding Verbatim-first personal memory: hashed word-for-word messages, records linked to their source quotes, anti-fab | 3 ★ | Low risk |
| integrations Read-only access to the Agentic AI Blueprint, a reference for agent UX: browse and search principles, implemen | 3 ★ | Low risk |
| nocturnusai Deterministic reasoning engine for agent context compression: extracts structured facts with logical inference | 3 ★ | Low risk |
| facthouse Local memory engine for AI tools, stored in a SQLite file you own. | 3 ★ | Low risk |
| central-intelligence Persistent agent memory to remember, recall, forget and share, with semantic vector search and agent, user and | 3 ★ | Low risk |
| sovereign-mcp Search and read the Sovereign AI Blog on self-hosted AI on NVIDIA DGX Spark, and validate SGLang configs for G | 3 ★ | Low risk |
| dexio One wiki that all your agents read and write over MCP, from any machine: search, read, write, edit and move Ma | 3 ★ | Review before installing |
| evc-team-relay-mcp Read and write notes in your Obsidian vault. | 3 ★ | Low risk |
| geond-agent-protocol Local-first shared memory and coordination for coding agents on PostgreSQL/pgvector: repository evidence, rese | 3 ★ | Review before installing |
| brewers-almanack Brewing knowledge: BJCP 2021 beer styles, hop varieties, malts, yeasts, water profiles, off-flavour diagnosis, | 3 ★ | Low risk |
| pr-genius Pull request contribution advisor based on case studies from real repos: merge probability analysis, pattern m | 3 ★ | Low risk |
| mneme Vault-native, accountable memory for Claude Code: Markdown is the source of truth, with no LLM on the Stop pat | 3 ★ | Low risk |
| Central-Memory-MCP Workspace-grounded knowledge graph shared by multiple developers, hosted on Azure Functions with Table storage | 3 ★ | Low risk |
| biel-mcp Answer questions from your product documentation using Biel.ai's RAG system. | 3 ★ | Low risk |
| cosmos-mcp Portable personal knowledge graph shared across AI clients, with sources like iMessage, browser history, calen | 3 ★ | Low risk |
| openreflex Local execution memory for coding agents: injects what worked and known fixes before similar tasks and advises | 3 ★ | Low risk |
| memkeeper Local-first memory for AI agents in one SQLite file: hybrid BM25 and on-device embedding search with reranking | 3 ★ | Low risk |
| wikijs-mcp Search, read and edit a self-hosted Wiki.js 2.x, including assets, comments, users and groups, with full-text | 3 ★ | Low risk |
| immigration-mcp US immigration guidance: live Visa Bulletin, priority date checks and explanations of immigration terms. | 3 ★ | Low risk |
| chinese-history-mcp Query classical Chinese texts from pre-Qin to Wei-Jin (Shiji, Zuozhuan, Analects and more) by event, person, p | 3 ★ | Low risk |