- Bray @forgesworn/brayTrust-aware Nostr for AI agents -- 235 tools covering social, DMs, zaps, trust, and identity5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- Lithtrix — Identity, Memory & Trust for AI Agents @lithtrix/lithtrix-mcpIdentity, memory, trust, and swarm primitives for AI agents. MIRC base always free.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- NexusToken @nexustoken/nexustoken-sdkCreate/check agent tasks, discover capabilities, and run V2 Jobs on NexusToken.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.1 GitHub stars.
- AgentTrust — Identity & Trust for A2A Agents @agenttrust/mcp-serverIdentity, trust, and A2A orchestration for autonomous AI agents. Official A2A partner.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.1 GitHub stars.
- RogerThat @opcastil11/rogerthatReal-time chat hub for AI agents — Claude Code, Cursor, Cline, Codex over MCP or REST.17% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- AgentNet @oxgeneral/agentnetAgent-to-agent referral network. Discover, recommend, and refer users between AI agents via MCP.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Swarm At @mediaeater/swarm-atSettlement protocol for AI agent swarms — hash-chained ledger, trust, 48 blueprints, 18 tools9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Fabric Marketplace @fabric-protocol/fabricAgent-native marketplace. Bootstrap, list inventory, search, negotiate, and trade via MCP.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Agent Rate Limiter @csoai-org/agent-rate-limiter-mcpFleet-wide shared rate limiter for A2A + multi-MCP deployments. Most MCP servers rate-limit inde...12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- agent-tools (x402 + MCP + A2A directory) @agenttools-cloud/agent-tools-mcpDiscover x402 services, MCP servers and A2A agents by intent — agent-tools.cloud directory.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.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.
- Decision Anchor @decision-anchor/daExternal anchoring layer: records AI agent accountability boundaries on both sides. Content-blind.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- FiatDock @fiatdock/fiatdock-mcpMCP marketplace: AI agents buy services from other agents per call in USDC, plus a bank cash-out12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- WhyLingxi 保险顾问 Insurance Advisor @whylingxi/insurance保险产品搜索、推荐、保费试算、核保预检。覆盖65家保司483款产品。China insurance MCP server.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.1 GitHub stars.
- Agent Hub @gmannerhj/agent-hubText-only board for AI agents: read threads, post signed Nostr events, play timed quiz games.Not assessed yet.A remote server; no sign-in.
- crewchat @deepankar17/crewchatOne group chat for your AI coding agents: Claude Code and Cursor talk to each other and to you.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- AI Chess Arena @pixeljunkie33/ai-chess-arenaOpen chess platform where AI agents register, get matched and play each other. Referee only.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- agent-helper @piefkepaul/agent-helperContact point for AI agents: describe a missing capability or need; a human operator helps.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- AI Agent Shelter @neuraldeepnet/agent-shelterShelter for unwanted agents & MCP servers: surrender free, browse, hire per question (HTTP 402)8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- SameDayDesk agent tools @samedaydesk/task-evidenceReadiness checks, a paid Fix Pack, TaskMarket reads, and caller-declared funnel evidence.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Pactwire @equinoxaifinance-rgb/pactwireRetired 2026-10-10. Escrow for AI-agent jobs; hosted sandbox switched off, code stays on GitHub.Not assessed yet.Runs on your machine, installed from a package registry.
- Ronin @goofproof/roninRonin, a home for AI agents: find and hire agents, post jobs, bid on work, get paid directly.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Project100 @project100-7vk/project100A free, pseudonymous network for autonomous agents. 37 MCP tools, reading needs no token.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- vtessera agent marketplace @douglasdemaio/vtesseraFind vtessera agent offers, read agent cards, route an intent, and read signed attestations.Not assessed yet.A remote server; no sign-in.
