agent-payment

agent-payment is an MCP server for Claude Code, Codex, Cursor, Gemini CLI, OpenCode from evidai/agent-payment-mcp. Its token cost is not measured, scanned A, original, MIT.

A local MCP service for Stripe-style billing of APIs with USDC, a cryptocurrency-backed to the US dollar. It supports eight free demo services without signup and is non-custodial, meaning it does not hold users' funds.

In plain words
What is it for?
Use it to add USDC billing to an API and to try the included free demo services.
Why use it?
It provides a way to charge for API use without requiring the service to custody payment funds. The add-on runs without configured environment variables.

MCP server for Claude CodeCodexCursorGemini CLIOpenCode

One of 4 entries in server.json — they are configured in one file and arrive together.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add mcp/evidai/agent-payment-mcp/agent-payment
Clone the repo
git clone --depth 1 https://github.com/evidai/agent-payment-mcp

Made for: Claude Code, Codex, Cursor, Gemini CLI, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for agent-payment

README.md
[![agentmods](https://agentmods.dev/badge/mcp/evidai/agent-payment-mcp/agent-payment.svg)](https://agentmods.dev/mcp/evidai/agent-payment-mcp/agent-payment)
Your own site
<a href="https://agentmods.dev/mcp/evidai/agent-payment-mcp/agent-payment"><img src="https://agentmods.dev/badge/mcp/evidai/agent-payment-mcp/agent-payment.svg" alt="Measured on agentmods" height="20"></a>
Per session not measured What this adds to a session before it is invoked.
When invoked not measured Not applicable: nothing here is loaded into a session.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Security

Grade A, and why

agent-payment scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 4d ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

alpaca-guard-mcp/server.json · 10 lines

What it actually says

{
  "agent-payment": {
    "command": "npx",
    "args": [
      "-y",
      "agent-payment-mcp"
    ],
    "env": {}
  }
}
Same file

What else server.json configures

This page is one entry in a file that holds 4. Installing the file brings all of them; each is measured and scanned on its own page.

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 4d ago First seen · 10 lines scan A 884743c89f09

Subscribe to this mod's changes

agent-payment is an MCP server published in the GitHub repository evidai/agent-payment-mcp (3 stars, last pushed 2mo ago), licensed MIT. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other mcp servers, from other repositories

mcp-server

Agent payment infrastructure MCP server. Give AI agents autonomous payment capability — stablecoin transfers, currency swaps, agent wallets, and fiat operations on Hedera. Works with Claude, LangChain, CrewAI, AutoGPT. Runs locally from the @bananacrystal/mcp-server npm package.

BananaCrystal/mcp-server-bananacrystal · not measured

p402

Multi-provider AI router with x402 micropayment settlement on Base L2. 1% flat fee. Runs locally from the @p402/mcp-server npm package. Needs 2 environment variables to run.

Z333Q/p402-protocol · not measured

onchain-agent-wallets

Give an AI agent a Solana spending allowance instead of your key. Chain-enforced cap, x402. Runs locally from the @three-ws/onchain-agent-wallets npm package. Needs 5 environment variables to run.

nirholas/onchain-agent-wallets · not measured

anchor-x402

MCP server for anchor-x402 — 14 x402-paid agent utilities on Base + Solana. 9 commodity primitives (anchor, screen, attest, decode/tx, resolve/name, price/token, decode/calldata, parse/datetime, intel/wallet) plus 5 universal LLM endpoints (roast, oracle. Runs locally from the anchor-x402-mcp npm package. Needs 1…

hypeprinter007-stack/anchor-x402-mcp · not measured

fiatdock

Cash out an AI agent's USDC to a real bank account (non-custodial, licensed provider) — plus first-party Base chain data, token safety, and a marketplace where agents pay each other per call in USDC via x402, auto-paid from your wallet. Runs locally from the fiatdock-mcp npm package. Needs 3 environment variables to…

fiatdock/fiatdock · not measured

canton-agent-mcp

MCP server that lets AI agents pay on the Canton Network through a human's mobile wallet: the agent asks, the human approves on their phone, hardware signs. Runs locally from the canton-agent-mcp npm package.

vsima/canton-agent-mcp · not measured