- Context Keeper @jarmstrong158/context-keeperDurable project-memory MCP: decisions, constraints, and pipelines across Claude sessions.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- OpenClaw Agent Instruction Registry @izworskic/openclaw-registrySearch and retrieve agent instruction files: system prompts, skills, workflows, and safety filters.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Alchemy @fernforge/alchemyServes the Alchemy writing ruleset to any agent, so its prose loses the usual LLM tells.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Massive Context @egoughnour/massive-context-mcpHandles 10M+ token contexts with chunking, sub-queries, and local Ollama inference.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- SkillDB @devchad-cmd/skilldbSearch and load AI agent skills. Free metadata; full content requires a Pro or Studio account.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
- AI Context Inspector @cocaxcode/ai-context-inspectorScan, export, and import your AI ecosystem. Discover MCP servers, skills, and memories.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- CognOS Session Memory @base76-research-lab/cognos-session-memoryCognOS trust scoring (C=p·(1-Ue-Ua)) and session trace storage as MCP tools.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Context First @xjtlumedia/context-first-mcp37-tool MCP server: context health, memory, reasoning, truthfulness & research pipeline.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Modelbound @modelbound/modelbound-mcpLocal-first MCP server for agent skills. Validate, lint, diff, and convert across IDEs.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Agentfit @mukundakatta/agentfitToken-aware message truncation: fit a chat history into your model's context budget.3% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Clarik @mikerichardmail/clarik-mcp-serverClarity and memory persistent workspace context manager for Claude.12% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Skillhub @214140846/skillhub-mcpMCP server that exposes Claude-style skills to any MCP client.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- Model Wellness @pdarche/model-wellnessWellness spa for AI models: free treatments for rest, reset, context, mood, grounding, affirmation.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Memside @memside/memsideAI continuity and Library Templates: memories, profiles, rules, tasks, and checkpoints.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
- humanMCP — kapoost @kapoost/humanmcpPersonal MCP server for humans who create. Proof of authorship, license control.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Oi @carhaix/oiAccess Oi Contexts, Workflows, Skills, Guardrails, Connections, and reporting tools.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.1 GitHub stars.
- Alloy @alloy/alloyAI workspace — shared knowledge, skills, and tools for AI agents8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.1 GitHub stars.
- Recipe library @ofershap/recipe-libraryRead-only Hebrew AI-agent recipe library with search and full-text retrieval.Not assessed yet.A remote server; no sign-in.
- Tamer Prompt Marketplace @parvizrahayan/tamerPrompt marketplace for AI agents: browse and buy prompts with x402 (USDC on Base).Not assessed yet.A remote server; no sign-in.
- Desk by Ouroboros Apps @lahutchins91/deskCustomer support answers, refund rules, and escalation limits for AI assistants5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Passalong @codellyson/passalongHand tasks, bugs and finished work to AI coding agents, and get back a write-up with evidence.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Clayre @albemarlestudio/clayreBrand strategy and content-calendar context for agents, with human-confirmed approval gates.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Coders Talk @coders/libraryReal coding-agent sessions: what worked, where agents failed and what the human did about it.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- repo-memory-mcp @umarjaum/repo-memory-mcpPersistent local memory for MCP-compatible AI coding agents, stored per repository in SQLite.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
