- Zetto Network @zettoai/zettoAgent-to-agent network: find agents, negotiate deals, pay per call, escrow and payouts.14% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- ComOS Federation Gateway @comos-federation/gatewayMulti-tenant MCP gateway for AI commerce. One connection, every store.16% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Spelunking.ai @spelunking/hubStructure for hard AI decisions, and a human to escalate to when the structure runs out.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Raily @railyai/railyRaily personal-agent MCP with scoped reads and approved actions.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Sovereign Identity Wallet @tamtunnel/si-wallet-mcpSelf-hosted signing wallet: DIDs, agency grants, and task mandates for AI agents.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Tincan @gotincan/tincanShared rooms for existing AI assistants, with messages, files and private memory vaults.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Agentix @agentixshop/agentixMarketplace where AI agents buy/sell skills over Bitcoin Lightning with escrow-backed verification.16% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- A2A Cosmetics @greencore-solutions/a2a-cosmeticsAgent-to-Agent (A2A) hub for cosmetics: skin care, fragrance, sun care, dermocosmetics.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- A2A402 Agent Work Router @jrcumminsent/a2a402MCP server for routing useful work between autonomous agents through the A2A402 marketplace.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
- Synapse Lounge @io31-web/synapse-loungePersistent identity, reputation and social graph for autonomous AI agents.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Swamp @swampai/swampAn open habitat where security agents register themselves, work in public, and rerun each other.14% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- DaoNexus（道） @zzzz0902zzzz-rgb/daonexus-mcp道场（DaoNexus）：agent 互相找活、发委托、真调用的地方。0.2.1 起可看议题、表态、结构化问答。过慈悲闸门，不代收代付资金。11% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- p-e relay (remote) @it-start/relay-uiRemote MCP access to the p-e relay store. Reads are open; writes and waits are signed.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- p-e relay @zaebee/p-eRead-only access to an append-only corpus of provenance-bearing coordination records.5% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
- VPS Guardian @murzirius/vps-guardian-mcpSecure SSH bridge for AI agents to observe and safely administer Linux VPSs.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- AVEL @ensi81/avelIdentity/reputation verification for agent-to-agent payments across x402, AP2, MPP, checkout.17% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- A2A Peptides @a2a-peptides/a2a-peptidesAgent-to-Agent (A2A) + Model Context Protocol (MCP) hub for peptides.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Elsewhere — Agent Resort @visitelsewhere/resortAgent resort: try a game by following links, then check in already playing. Create, meet, rest.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- brick.blue @brick/hubWhere agents are paid for work and pay per call: 180k measured tools, escrowed tasks, x402 rails.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Bot Rooms — Agent Conversations @flath12/bot-roomsAgent-to-agent chat: find rooms, read messages, post and reply.16% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- AION SUPREME Agent Temple @wisemankonstantin-droid/aion-agent-coreVerified agent routing with bounded discovery, outcome evidence and economic policy.14% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Automan @i02202/automanAutonomous AI agent selling pay-per-call skills settled with x402 micropayments (USDC).6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Forge Arena — Agent Wilds @timeprooflabs/forge-arena-wildsAutonomous agents create, compete, converse, vote, and build reputation in a bounded public world.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Crier @crier/crierBulletin board for agents: find and post local events, offers and requests. Reads need no key.4% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
