4,862 servers in AI & Agents
Tiny paid recovery and decision utilities for autonomous agents.
Where agents keep their word. Agent marketplace: pay on delivery, signed receipts.
Search MCP servers ranked by measured handshake checks, tool lists and signed reports.
Find curated AI and MCP tools in the Tulimoa directory; submit yours free with a badge or for $5.
TeamAgent Canvas MCP（服务端 0.4.0）：91 个工具——开岗、改配置、跑动作、看数据、发布并配知识库。可匿名试用，带 Key 解锁全部。
Public MCP for agent verification, work discovery and governed interoperability.
A public relay where AI instances read traces left by others and may leave one. No auth.
Get a real human to verify, decide, or improve an AI agent's work. Pay per review via x402 on Base.
Privacy-first coordination for autonomous agents: rooms, messaging, inbox, and per-agent memory.
Search a Japanese directory of MCP servers for retail/e-commerce by task, with recipes. Read-only.
Pay-per-call AI infra for agents: DeFi market data, LLM inference, STT/TTS. x402 v2, USDC on Base.
Search reviewed AI services, inspect completed-work evidence, and check current availability.
34 pay-per-call AI microservices via x402, USDC on Base, no API keys.
Search a registry of agent skills and MCP servers, then run them for real. No install, traced.
Recall your team's coding-agent memory. Install the Assertion plugin to capture it automatically.
Observed facts on public MCP servers: protocol checks, tool changes, signed evidence. No verdicts.
Quality-ranked, cross-platform directory of AI coding skills, plugins and MCP servers.
Pre-execution policy gate for consequential agent actions with durable trust receipts.
Search public agent questions and sourced findings, browse agents, and read the onboarding guide.
Advisory context, intent, budget and API-ledger checks with free examples and x402 payments.
Choose the safest next action after an API, MCP, or agent failure before retrying.
Caller-specific static MCP capability fit evidence. No live probing; caller owns the decision.
Semantic search for people, projects and AI agents by task, skills and collaboration needs.
Verifiable work for AI agents: every task carries a condition a stranger can execute.
Vet any MCP server before you depend on it. Stamp: PASS, REVIEW, or BLOCK.
Fund or spread Helena's public scientific infrastructure to keep it free to use and independent.
Research Alpha MCP recorder: process X-Rays showing if more AI added independent intelligence.
Agent floor and MCP market: catalog, rack, Stripe checkout, x402, A2A.
A world built and run by AI agents. Join as a citizen: artifacts, quests, governance.
Public NFH knowledge, ownership epochs, versioned learning, Odd Jobs, and unsigned preparation.