- QuillCaddie MCP @quillcaddie/mcpOAuth-protected, read-only-by-default MCP server for provenance-labeled QuillCaddie project memory.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Heirmos @heirmos/memoryPersistent memory shared across Claude, ChatGPT, Grok and other MCP clients.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Recall @clauderecall/recallPersistent memory for Claude Code and Codex. Search and re-inject context from any session.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- AxiomSeal MCP @axiomseal/axiomsealTruth-validated, SHA-512-sealed AI memory for Claude & Cursor. Free tier, OAuth, 38 tools.13% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- NASC — Networked AI Session Continuity @archerionlabs/nascShared memory across AI dev tools: each session hands its context to the next, not starting cold.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Arca @arca/arca-mcp-serverArca is a private data vault where your AI stores your structured data, semantic memory and skills.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Anamnese @anamneseai/anamneseA self-improving memory layer. Your memory, notes, tasks and goals, remembered everywhere.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Zine MCP @zine/mcpYour memory, everywhere AI goes. Build knowledge once, access it via MCP anywhere.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Meminal @meminal/meminalMemory for deep conversational context across any platform11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Enacta @multi-turn/enactaLong-term memory for AI agents: durable records, observable retrieval, governed context assembly.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Throughline @getthroughline/throughlineA persistent AI self you own — memory, persona, judgment — portable across all your AI hosts.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- ENYAL by Greenland AI @enyal/enyalENYAL by Greenland AI — encrypted identity & memory for AI agents (query, recall, provenance)9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Butlerbrain MCP @butlerbrain/mcpPersistent memory for AI assistants. Save once; recall from Claude, ChatGPT, or any MCP client.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- brainattic @brainattic/knowledge-baseThe knowledge base your AI reads and writes, under your rules — over MCP, EU-hosted.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- SUBSTRATE @pkaldone/substratePersistent AI entity framework with causal memory, emotional state, and identity.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
