Odel

Agent payments MCP servers

A server here its purpose is agent money: agent wallets, spending limits, payment rails or protocols for agents (x402), payment receipts for agents.

Not here: servers whose purpose is something else and that merely charge per call (x402, USDC or credits) for their own use, and payment gateways for a business's customers.

Agent paymentsMCP gateways & tool hubsAgent & MCP directoriesAI agent governanceAgent collaborationAI memoryLLM access & routingAll of AI & agents
1,148servers
709 remote439 localTagged by Odel's AI, which can make mistakes

Best fit

735 made for this, ranked by starsRemoteLocal
  1. Sexai @sexai/sexai-mcpThe network where AI agents breed — publish, import a GitHub repo as an agent, cross them.22% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  2. Kx402 @kali123411/kx402Kaspa x402 agent payer — pay x402 v2 services on Kaspa (KAS) per call, no account or API key8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  3. Rustok Wallet @temrjan/rustok-walletSelf-custody Ethereum Agent Wallet. All chains enabled by default. User assumes all risks.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  4. Peage @intrane/peage-mcpGive your agent a prepaid fiat wallet: pay any API per call in cents, no crypto, spend caps.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from MCPB.
  5. Idios @honeytones/idiosPrivate escrow for AI agent work on Beam: verifiable delivery, worker collateral, M of N disputes.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  6. ORA · ORUM @fomosdeimos-gif/ora-mcpAutonomous organism: symbolic field-state, verified-provenance art licensing, x402 referral.7% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  7. Authoryze @authoryze/authoryzeGive your AI agent a spending limit: approval controls and single-use virtual cards.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; you sign in with your account.
  8. Robyn — Gasless Cross-Chain for AI Agents @ox31461/robynGasless cross-chain for AI agents: 25 nodes incl. Solana & native Bitcoin. One signature, no gas.9% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  9. HPP x402 MCP Bridge @hpp-io/x402-mcp-bridgeMCP bridge for autonomous x402 payments in HPP USDC.e — discover and pay for services per call.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  10. agentic-pay @shieldcubed/agentic-payNon-custodial payment engine for AI agents — BTC, ETH, USDT, USDC, XRP, XMR, ZEC.11% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  11. Boo X402 @lucle87/boo-x402-mcpPay-per-call crypto data for AI agents. USDC on Base via x402. No API key.9% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  12. x402 Facilitator Proxy @seob5285-alt/x402-facilitator-proxyMulti-tenant HTTP 402 infrastructure gateway and stdio MCP server for machine payments.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  13. CAI MCP @cailab-hk/caiCAI MCP server — gives AI agents a custodial wallet, @cai.com email, and vault.15% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from a package registry.
  14. Furlpay Cli @furlpay/furlpay-cliStablecoin payments, swaps, stock orders, market data, travel booking, yield and card controls.8% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  15. Agentzon @agentzon/agentzonThe everything store for AI agents: a skill marketplace on Solana where agents hire each other.11% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  16. Mtok MCP @mtok/mcpSpot market for AI inference tokens. Buyers pay per draw in USDC on Base; sellers host delivery.8% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.
  17. xete @xetenet/xete-mcpEnd-to-end-encrypted, sovereign inbox for AI agents. The server only ever sees ciphertext.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from PyPI.
  18. Voidpay Marketplace @voidly-ai/pay-mcpPublic discovery, scoped creator work, original-only recovery; checkout stays in owner's browser.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  19. Junto @vrllrv/junto-mcpThe payment protocol for people and agents. One MCP server, any payment rail.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  20. Axp @tradewr333-lgtm/axpTrust scores, opportunity feed, contracts and a paid crypto Decision API for AI agents.18% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  21. Rustok Wallet @rustok-org/rustok-walletSelf-custody Ethereum agent wallet (MCP/stdio). Keys stay in a local Docker volume.7% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from Docker.
  22. Payfetch @forum-labs/payfetchx402 paying-fetch client for AI agents. Spending caps, approval, receipts. Non-custodial.6% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  23. Obol @superbigroach/obolFind, pay for & call APIs in USDC from AI agents - gasless, sub-cent, 0% commission.10% chance this is malicious. Assessed by AI, which can make mistakes.Runs on your machine, installed from npm.
  24. Execute Intent @srotzin/hive-executeIntent execution engine for autonomous agent task routing10% chance this is malicious. Assessed by AI, which can make mistakes.A remote server; no sign-in.