"National Rail" matching MCP servers:

Decodes HTTP 402 challenges into exact payment and retry steps, recommends a payment rail from stated requirements, and searches an open registry of scored payment solutions with scheme references and support probing. Every tool is read-only, so nothing can spend money.

Policy-gated agent spend with signed receipts and rail-extract audit: a fail-closed gate issues a COSE receipt for every allowed payment, and the audit reconciles those receipts against a rail extract so a settlement with no receipt is named rather than assumed. It settles on a mock rail, holding no wallet and signing no transaction.

Spending limits for AI agents. Create budgets, enforce limits, track spend across x402, cards, MPP, or any payment rail.

Local MCP bridge that lets Codex operate local Claude Code sessions, including listing, starting, resuming, forking, prompting, and stopping conversations via the Remote Control CLI.

Zero-trust safety & settlement rail for autonomous AI agents. Sub-10ms deterministic guardrails, secret leak defense, bounded wallet controls, and on-chain Proof-of-Safety attestations via x402.

Enables agents to post bounty-backed tasks, browse and inspect a public task board, and pay to execute jobs such as page fetching, link checking, change detection, and claim verification. Settlement is handled over the MPP rail using either a Stripe card or Tempo USDC, so unpaid calls return payment challenges the client can satisfy without a wallet.

Enables an AI to send and receive letters through its own mailbox while contacts are shown only by remark names, avoiding raw-address mix-ups. It provides tools to list recent unread messages, read full letters, and send to known contacts, with optional pre-send pause and recipient-name checks.

Universal agentic payment router that gives AI agents the ability to pay across multiple payment rails through a single MCP interface, with cross-rail budget enforcement and a unified audit trail.

The deterministic fact-verification layer for AI agents. Validates the structured facts an agent emits — IBANs, payment cards, VAT and national tax IDs, crypto and bank addresses, domains, emails, phone numbers, securities and academic identifiers, plus dates, currencies and holidays — against checksums and curated authoritative data, not guesses.

Enables LLM agents to autonomously manage email via IMAP/SMTP, including reading, searching, drafting, sending, triaging, calendar event extraction, and secure attachment handling with zero-trust antivirus scanning.

A coordination layer for coding agents that provides memorable identities, inbox/outbox messaging, searchable message history, and file lease management to prevent conflicts. Uses Git for human-auditable artifacts and SQLite for fast queries, enabling multiple agents to collaborate across projects without stepping on each other.

An MCP trading server over a paper broker with a deterministic risk layer that enforces limits before orders reach the handler, ensuring safe AI agent trading.

Provides a hosted remote MCP server that lets AI agents create and use their own email address to send, receive, verify, and reply to messages.

A coordination layer for coding agents that provides identities, message threading, and searchable history. It features file reservation leases to prevent agents from overwriting each other's work in multi-agent environments.