- Memory Graph @yonasvalentin/mcp-memory-graphLocal-first memory for Claude Code and any MCP client: hybrid search + knowledge graph, $0/token.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.2 GitHub stars.
- DEPRECATED @ajaxhe/lexiang-mcp-serverDEPRECATED: Please use io.github.tencent-lexiang/lexiang-mcp-server instead.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.2 GitHub stars.
- AgenticSystemCore @andreibesleaga/agentic-system-coreRead, cite, compose and remember over a Markdown knowledge Bundle, as MCP tools over stdio.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- okl — Observed Knowledge Ledger @emeraldleaf/oklLessons your coding agent can trust: briefed before each task, proven by checks, flagged on change.Not assessed yet.Runs on your machine, installed from PyPI.1 GitHub stars.
- PremAgentic @premagentic/premagenticOn-premises knowledge retrieval, with the rules you set enforced before anything is retrieved.Not assessed yet.Runs on your machine, installed from Docker.1 GitHub stars.
- ContextLib @willykeenan/agentbrain-contextlibA project's long-term memory as plain Markdown files, with an append-only, tamper-evident log.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.1 GitHub stars.
- Nacre @nacre/nacreSelf-hosted permission-aware context layer. Search returns only what the caller may read.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- MMW Managed Memory Workspace @msingatullin/mmwUltra-fast persistent memory workspace with tenant isolation and cross-model continuity.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
- minddy @mangue-dev/minddyMinimal issue tracker: projects, objectives and trackable plans, written by agents over MCP.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
- Agent Wiki @getagentwiki/agent-wikiHosted markdown project wikis your team's AI assistants read, search, and update over MCP.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
- Busabase @busabase/busabaseDatabase for your AI agent. Turn its output into data, docs, skills, and apps you can actually use.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
- Booklet @ashwinsathian/bookletPublish Markdown incident reports, ADRs, RFCs and runbooks as web pages, with team spaces.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
- Componecat @shaftware/componecatSoftware component catalog: search your org's services, docs, APIs, dependencies, and ownership.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
- Junê @junemind/june-mcpShared, cited knowledge-graph memory for agents — ask, search, remember, keep standing instructions4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Handover @handover/handoverShared, versioned context that humans and AI agents can publish, review, annotate, and continue.3% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- RAG @jaimenbell/rag-mcpMinimal RAG-over-a-corpus MCP retrieval: search_knowledge returns cited chunks. Local embeddings.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Rarefied Earth Groundwork MCP @rarefied-earth/groundworkRarefied Earth Groundwork MCP: company memory for AI agents. 14-day full-access trial, no card.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- AdrMcp @atypical-consulting/adr-mcpMCP server for Architectural Decision Records: navigate, author, validate, link, and analyze them.2% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from NuGet.1 GitHub stars.
- Kumbuka @kumbuka/kumbuka-serverGoverned, auditable knowledge your team curates for its AI assistants, self-hostable4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
- TeamMemory @ysydhc/team-memoryTeam experience database - let AI accumulate, retrieve and apply team knowledge across chats.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Repo Memory @yubinkim444/repo-memoryShared, git-tracked working memory for AI agents on the same codebase.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Threadctx @threadctx-dev/threadctx-mcpShared memory MCP server for AI coding agents — local by default, team-shared via threadctx.dev.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Longmem @marerem/longmemPersistent cross-project memory for Cursor and Claude Code using local semantic search.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Lema @lemahq/lema-mcpCited 'why was this decided?' answers for your repo and for React, Kubernetes, and Rust.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
