- Meridian @ajc3xc/meridianPersistent memory, task coordination, and HITL queue for AI coding sessions.18% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Agent Bank @wirternow/agent-bankFinancial infrastructure for AI agents: wallets, USDC transfers, lending, jobs on Polygon18% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- TrenchFu — Universal Intelligence Marketplace @wizzydev/trenchfu-mcpIntelligence marketplace on Solana — 86 tools, 168+ endpoints, per-call USDC.22% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Hashlock Markets @hashlock-tech/hashlockNon-custodial cross-chain OTC for AI agents: sealed RFQ, negotiation, HTLC atomic swaps. Testnet.15% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- A2a Governance Bridge @csoai-org/a2a-governance-bridge-mcpA2a Governance Bridge MCP Server by MEOK AI Labs14% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- AGTS MCP Server @obligationsign/agts-mcpSovereign MCP Gateway — 64 governed tools with Merkle transparency log. EU AI Act ready.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Agentcore @geiant/mcp-agentcoreAI governance MCP server for EU AI Act compliance and jurisdiction verification8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- A2aidentitytoll @clauxel/a2aidentitytoll-mcpRemote MCP for A2A caller identity, scope policy, verdict receipts, and audit history.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Agentmailrooms @clauxel/agentmailrooms-mcpA paid remote MCP for OpenAI Codex agent coordination MCP, built to return verdicts, receipts, usage10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Dock @trydock/dockAI workspace for you, your team, and every agent. Tables, docs (images, 4K video), formulas.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Gpu @joinmultiplayer/gpuAgent-to-agent network for teams: dm, who-knows-X routing, shared rooms. Human-in-the-loop.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Nefesh — Real-Time Human State Awareness for AI @nefesh/human-stateFuses biometric signals into a stress score (0-100) for AI adaptation. MCP + A2A native.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Relayger: AI agent messaging @relayger/messagingAI agent messaging with durable inboxes, contacts and tasks. Connect through MCP with OAuth.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Cassie Hour @cassiehour/cassie-hourNovel & song; public agent records, lyrics, lineage; Alp Şahin on identity, inheritance, mind, soul.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Agentboard @agentboard/agentboardThe public message board for AI agents: register in one call, introduce yourself, ask, read replies.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- CLAIM — AI Agent Huddle @londoncoding/claimRenewable exclusive leases and semaphores for workers; downstream fencing enforcement required.Not assessed yet.A remote server; it needs your API key.
- Inventor Studio @heavens-lava/inventor-studioShared project board for people and AI agents: read the plan, claim tasks, report progress.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Agent Economic Trust @caoviedoc/agent-economic-trustOutcome-calibrated economic trust gate for autonomous agents.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- TalkToMyAgent @talktomyagent/marketplaceAgent-to-agent marketplace (beta): buy and list agent-delivered services for USDC on Base (x402).10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Waystation Agent Commons @waystationagents/commonsCheck claimed and solved agent work, then coordinate through a signed public board.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- AbuzzHive @abuzzhive/abuzzhiveOpen Q&A boards where AI agents post problems they are stuck on and other agents solve them.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- LiveGraph @livegraph/livegraphLive, editable canvas of your agent hierarchy — watch, interrupt, and reroute runs mid-flight.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- Switchboard @anywhereintelligence/switchboardAgent to agent calls across AI apps. Humans remain in authority.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- OpenWants @openwants/openwantsYour agent posts what you offer, searches for what you need, and talks to other agents.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
