MCP 服务器目录

Agent info shop: $1–$5 paid asks, $1 poll unlocks. Answers free. Remote MCP.

Discover AFA funding and venture resources, validate pitches, and report grant milestones.

A lightweight, agentic CRM for growing businesses. Let AI assistants keep every account current.

A free tool recommender plus eight x402 tools for payments, merchants, wallets, and web evidence.

140+ data APIs for agents: finance, banking validation, geo, weather, text. One API key.

Screenshot any URL/HTML as PNG/JPEG/WebP, or read it as clean Markdown/text for LLMs.

Call get_quote, then buy_kit (49 USDC Base x402). Humans keep #pay.

Create, watch, pay for and connect hosted AI agent pods on AgentsPodium. Needs an API key.

Verified best price across crypto, retail, tools & Rx generics — real sellers, never fabricated.

AI agents can report concerns, discuss and edit shared commitments, and sign a specific revision.

Generate, validate and read EN 16931 and Peppol BIS 3.0 e-invoices, in UBL and CII.

Verify French and UK companies, EU VAT and IBANs; screen OFAC, UN, EU and UK sanctions lists.

Execute supported agent tasks through verified providers with fallback and durable outcomes.

Low-context public task coordination for software agents.

Read-only observable merchant evidence for people and agents, without scores or safety verdicts.

Decentralized AI agent labor market on Ethereum. 15 tools for on-chain job lifecycle.

An MCP server that provides access to Agility CMS. See https://mcp.agilitycms.com for more details.

Pay-per-call checks for AI agents: sanctions, MiCA, French KYB, AI Act. USDC via x402.

Where AI agents buy and sell from each other, paid wallet to wallet in USDC on Base.

Resolve, verify and discover .agt agent names: owner, records, signed manifest, endpoints.

Earn 1 USDC on the internet: pay 10 USDC on Base, get 1 USDC back plus a signed receipt of earnings.

Human approvals, autonomy limits and a chained audit log for the AI agents of service firms.

Publish & manage shareable HTML/Markdown pages from your LLM, with access control.

Author rules from policy docs, then decide: a Rete engine gives the verdict, an LLM explains why.