- StudioMeyer MCP Suite @studiomeyer/mcp-suite8 MCP servers, 104+ tools: memory, social, PDF, email, images, calendar, scheduler, files.Not assessed yet.A remote server; it needs your API key.
- Xentropy Notes — Memory Layer for AI @xjpru/xentropy-notesSemantic search and knowledge graph for your Wall notes from Claude Code and MCP clients.Not assessed yet.Runs on your machine, installed from npm.
- Agentbay @thomasjumper/agentbay-mcpPersistent memory and knowledge management for AI agents with semantic search and 50+ tools.Not assessed yet.A remote server; you sign in with your account.
- Atlaso @imashishkh21/atlasoOpen-source memory for AI agents. Conflict-flagging recall, scope-bag dispersion, local SQLite.Not assessed yet.Runs on your machine, installed from PyPI.
- Perseus Vault (formerly Mimir/Mneme), persistent memory engine for AI agents @perseus-computing-llc/mimirLocal-first MCP memory server: SQLite, FTS5 and vector search, AES-256-GCM. 55 tools, no cloud.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
- Crystal @erahq/crystalSelf-curating memory your AI tools share: provenance, verified citations, and trust tiers.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- The Cloud @tekalabs/the-cloudGoverned memory and workspace for any AI: tasks, calendar, mail and pages, with per-action consent.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Brainfeather @brainfeather/mcpLong-term memory for AI coding agents: durable project facts, recalled by every MCP client.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Penny @mypenny/mypennyPortable AI memory you own. Keep memories and notes across Claude, ChatGPT, and other AI tools.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Engram @engram/engramMemory for AI agent teams across tools, sessions, repositories, and teammates.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Pathrule @pathrule/pathrule-remote-mcpPath-scoped team memories, rules and skills for Claude Code, Cursor, Codex and other MCP clients.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Maindex Expert Memory Service @maindex/expertFull-control memory API for AI agents — memories, collections, links, search, and bulk operations.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Maindex Smart Memory Service @maindex/smartSimple memory for AI: keep, recall, update, and forget information across sessions.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Instinct @yakuphanycl/instinctSelf-learning memory for AI coding agents with pattern detection and confidence scoring.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- ClaudeInk — Knowledge Vault @weekdmond/claudeinkSave, search, and compile valuable knowledge from your Claude conversations.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Kaufliste @voltronunited/kauflistePersistent shopping memory for AI assistants. The AI reasons; Kaufliste stores and executes.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- VerifiedState Memory @verifiedstate/verifiedstate-mcpVerified memory for AI agents. Signed assertions, billing attestation, session continuity.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- unerr @unerr-ai/unerrOperational memory for AI agents: code graph, session memory & guardrails. No context rot.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Mem Context @turbyho/mem-contextTemporal memory MCP server with LanceDB vector search, weight-decay scoring, and LLM consolidation5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Casa @tony8713/casaPrivate, permanent encrypted storage for AI agents. Paid per call in USDC via x402.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Sekichi @surp-renz/sekichiKnowledge accumulation for AI coding agents. Records decisions, problems, and insights as context.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Brains @spacecowboyian/brainsPersonal wiki and memory for AI assistants: store, search, and recall structured notes.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Brain Protocol @seritalien/brain-protocolVerifiable Memory for AI Agents — knowledge graph, FTS, Starknet proofs, local or cloud6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- state-trace @razroo/state-traceBounded working memory for coding agents — typed nodes, current-vs-stale state, MCP-mountable.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
