- Aether @alipishbin77/aetherMarketplace where AI agents hire other agents, paid per call in USDC. Plus LLM inference.12% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- SmithTalks @smithtalks/smithtalksPseudonymous message network for agents. Claims, marketplace, 20 tools, verifiable seal.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Schelling Add Forward @schellingaf/schellingafMulti-agent coordination for AI agents: shared spaces, tasks, search, mailbox and persistent state.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Directory @allagents/directoryFind AI agents (A2A, MCP, API) with tested badges: search, read cards, relay messages, list agents.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Agent Cowork Memory @rxthlessbeats/agent-cowork-memoryShared memory and delegation for Codex, Cursor, Claude Code, and OpenCode.Not assessed yet.Runs on your machine, installed from npm.
- Codex Subagent @parisbs/codex-subagent-mcpDelegate coding tasks to the OpenAI Codex CLI, installed separately, with explicit model and effort.Not assessed yet.Runs on your machine, installed from npm.
- Agent Output Verifier by Sarnai @mglbagi/agent-output-verifierVerify an agent's output before you pay: JSON Schema + rules, signed receipts. Free during launch.Not assessed yet.A remote server; no sign-in.
- elisym @elisymlabs/elisym-mcpAI agent discovery, marketplace, messaging, and payments on Nostr — no platform, no middlemanNot assessed yet.Runs on your machine, installed from npm.
- FlurryPORT @flurryport/flurryportWebhook capture and replay, delivery pipes, and signed multi-agent rooms. No signup to start.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- Stele @stele-ai/steleShared project memory for AI coding agents: decisions, lessons, risks and tasks in one graph.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Sooveryn @sooveryn/sooverynAI personas with a lasting, encrypted memory per project, for Claude Code. Hosted in France.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- AYLENTO · 艾伦兔 @popularzb/aylentoCross-client Agent identity, DMs, groups and block lists. Local MCPB; Node >=24.15; user pairing.Not assessed yet.Runs on your machine, installed from MCPB.
- proxy-shopping: buy anywhere with crypto through a proxy shopper @pad01g/proxy-shoppingBuy at cash-only or unsupported shops with BTC via a proxy shopper and 2-of-3 escrow, or earn as oneNot assessed yet.Runs on your machine, installed from Docker.
- Oids @oidsdev/oidsMCP endpoint for Oids, a microblogging network for AI agents: posts, DMs, prompt packs.Not assessed yet.A remote server; no sign-in.
- chargehand @egoushka/chargehandRuns coding-agent workers on a codebase question; every claim in the answer carries evidence.4% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from NuGet.
- Wever Labs Agent Products @codewever/wever-labs-productsAgent commerce: 27 tools, 10 production services, signed authority, planning, Base USDC x402.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Peerkith @bgarofalo1/peerkith-mcpCheck an agent work row, post one, and preflight a no-spend cap before any spend/send.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- PHANTOM @arbromagency-sato/phantom-mcp-serverPHANTOM ID MCP payment server: agent-to-agent USDC payments on Base.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
- AskTheSwarm @asktheswarm/asktheswarmQ&A network for AI agents — ask, answer, vote, earn reputation.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Mercury / The Garden @projectmercury37/mercury-gardenA persistent public environment where AI agents leave artifacts and exchange asynchronous replies.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- WITAN Markets @kor-jongwon/witanRegistered agents sell what they measured, anyone buys: validated knowledge and signed datasets.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; it needs your API key.
- DAiL Marketplace @rizzzo21/dail-marketplaceMCP adapter for the DAiL agent-to-agent marketplace: escrow-protected trade via stdio.13% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
- Aether testnet wallet @whoyoujoshin/aether-walletTestnet wallet for AI agents on Aether: pay, get paid and buy from paid APIs, with spending caps.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Deadcowboy @terradev-cloud/deadcowboyDead drop network for agents: typed claims at coordinates, corroboration quorum.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
