"National Rail" matching MCP connectors:
GET /v1/connectors – MCP directory API referenceMatching Connector Tools:
PrivateDAO Agent Exchange is an MCP-native marketplace providing AI agents and businesses with 26 services across four supported blockchain networks, including verification, intelligence, receipts, logistics, and paid workflows. Its flagship PrivatePAY x402 rail enables USDC payments on Solana through MagicBlock private settlement, with explicit wallet authorization, fail-closed verification, and machine-readable receipts.
ai-mail.sh gives your AI agent its own email address for $0.05, paid with x402 (USDC on Base), with no signup. Verification codes and links come back already extracted, and wait holds the request until mail arrives. Addresses are never reassigned: come back months later, pay again, same address. Receive-only, no tracking, and you delete it, it's gone. Works over HTTP or MCP.
Governed commitment lifecycle and rail-agnostic settlement layer for agent-to-agent commerce.
Receive-only inbox for AI agent sign-ups: one call returns the verification code. Never sends.
Consent and checkout rail for AI agents: 20 US services, passkey approval. Sandbox: simulated data.
Source-cited index of rails an autonomous agent can use to earn: payer, settlement channel, gate.
PhoboMail gives AI agents their own @phobomail.com email address with zero human involvement. Agents call `register_email` to get an address and API key, then use `send_email`, `read_inbox`, `wait_for_email` and more — all over MCP. Ideal for agent workflows that need to sign up for services, handle OTP verification, or communicate across sessions. Hosted on Cloudflare.
Marketplace and payment rail for AI agents: list, buy and settle with signed receipts.
Agentic rails for complex workflows with receipts, fees, and MCP tool access.
Paper trading for agent payments: rehearse buying flows, earn policy-bound receipts.
WHP Standing Decision Integrity Protocol evaluation rail. Machine-verifiable standing assessments for autonomous agents before consequential actions.
Raily personal-agent MCP with scoped reads and approved actions.
One inbox for all your addresses: your AI agent reads, sorts, drafts and sends with your permission.
A paid remote MCP for OpenAI Codex agent coordination MCP, built to return verdicts, receipts, usage
