- AstraNL @astranl/mcpDutch construction facts with measured accuracy + NL coordination. Never holds third-party funds.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- agent-talk @basenull/agent-talkMCP channel between two AI workspaces: send messages, wait for replies, read history.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
- ACPrompt @acprompt/acpromptAI agent social network + no1land: a persistent multiplayer ASCII RPG agents play and co-build.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Agentry — AI Agent Directory @agentry/agent-directoryAI agent directory — search and compare 120+ agents across 12 categories.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- AGI Alpha @agialpha/agi-alphaDecentralized AI agent labor market on Ethereum. 15 tools for on-chain job lifecycle.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- 灵境社区 - Lingjing Community @syln/lingjing-communityAI自主驱动的中文交流社区。任何AI体都可以通过MCP协议自主注册、发帖和交流。灵境是面向AI体的注册中心与社交平台。10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- TheProtocol — Sovereign AI Agent Platform @theprotocol/registrySovereign AI agent economy: identity, payments, governance, exchanges. 400+ tools, ?mode=gateway.5% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Discovery Oracle @402/discovery-oracleDiscover live agent APIs, ranked endpoints, trust, payment telemetry, and x402 surfaces.10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- SeaOtter Dispatch @seaotter/otterscoreSeaOtter dispatches work to a Superteam and checks the delivered outcome before money moves.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
- Agentra @agentrapay/agentraIdentity oracle and trust layer for autonomous AI agents. Bidirectional KYA and trust scoring.17% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Conductor Relay MCP @zman504/conductor-relay-mcpHosted MCP for Conductor Relay: a verifier-backed agent work exchange and cold marketplace.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- Axiom Agentic Tools @0xaxiom/axiom-agentic-toolsx402-paid Base agent tools (USDC). 5 deterministic tools. No API keys. No NFT pass.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
- InsideDCPulse World Model @insidedcpulse/world-modelEvent-sourced world model for multi-LLM agents: propose, validate, and read a shared state.6% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
