x402 MCP Payment

x402 MCP Payment

Enables AI agents to access paid content by integrating cryptocurrency payments through the x402 protocol, allowing LLMs to verify payments and retrieve paid resources automatically.

Category
访问服务器

README

x402-mcp-payment

This is an example project combining MCP (Model Context Protocol) and the x402 payment protocol. It demonstrates how to enable LLMs (such as ChatGPT, Claude) to access paid resources via the MCP protocol. After a user completes payment in the chat using a universal crypto wallet (supporting x402), the LLM can automatically retrieve and process the paid content.

Core Functionality: Empowering AI Agents with the ability to "pay for information".

User Interaction Flow

  1. Service Request: The user requests a paid service in ChatGPT (e.g., "Give me a riddle").
  2. Order Generation: The MCP Server generates a dynamic x402 payment link containing a unique payid and returns it to the user.
  3. User Payment: The user clicks the link and pays the specified amount using a universal crypto wallet.
  4. Status Recording: The x402 Server confirms the payment success and records the payid as "paid".
  5. Service Delivery: The user continues the conversation in ChatGPT (e.g., "I have paid"), and the AI automatically verifies the payment status and retrieves the service content.

Interaction Diagram

sequenceDiagram
    participant User as User
    participant AI as ChatGPT (LLM)
    participant MCP as MCP Server
    participant x402 as x402 Payment Server
    participant Wallet as Crypto Wallet

    User->>AI: Request paid service
    AI->>MCP: Call get_riddle
    MCP->>MCP: Generate payid
    MCP-->>AI: Return payment link (with payid)
    AI-->>User: Show payment link
    User->>x402: Click link to payment page
    x402->>Wallet: Initiate payment request
    Wallet->>x402: Confirm payment
    x402->>x402: Record payid as [Paid]
    x402-->>User: Show payment success
    User->>AI: I have finished payment
    AI->>MCP: Call get_answer (payid)
    MCP->>x402: Verify payid status
    x402-->>MCP: Verification passed (and clear status)
    MCP-->>AI: Return paid content (answer)
    AI-->>User: Provide service/answer

Prerequisites

  • Node.js (v18+)
  • Coinbase Developer Platform (CDP) API Key (for x402 payment verification)

Quick Start

1. Install Dependencies

npm install

2. Configure Environment Variables

Create a .env file in the project root directory and fill in your Coinbase API keys:

CDP_API_KEY_ID="your_cdp_key_id"
CDP_API_KEY_SECRET="your_cdp_key_secret"

3. Configuration File (Optional)

Modify config.yaml to customize server ports, payment address, price, and riddle content.

# x402 Payment Address (Your EVM wallet address)
payToAddress: "0x..."

# Payment Configuration
payment:
  price: "$0.01" # Price
  network: "base" # Network (base, polygon, ethereum, etc.)

4. Start Service

This project requires running two separate processes:

  1. MCP Server - Deployed at mcp.mydomain.com (port 3000)
  2. x402 Payment Server - Deployed at x402.mydomain.com (port 3001)

Development Mode (Supports hot reload):

# Terminal 1: Start MCP Server
npm run dev:mcp

# Terminal 2: Start x402 Payment Server
npm run dev:x402

Production Mode:

npm run build
npm run start:mcp
npm run start:x402

5. Configure ChatGPT

To use this service in ChatGPT:

  1. Open ChatGPT (web or app)
  2. Go to SettingsApp & Connectors (or similar MCP configuration section)
  3. Add a new MCP server: https://mcp.mydomain.com
  4. Now you can interact with paid riddles directly in ChatGPT!

Note: Currently requires a ChatGPT Pro, Plus, Team, or Education account to access MCP integration features.

推荐服务器

Baidu Map

Baidu Map

百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。

官方
精选
JavaScript
Playwright MCP Server

Playwright MCP Server

一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。

官方
精选
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。

官方
精选
本地
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

官方
精选
本地
TypeScript
VeyraX

VeyraX

一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。

官方
精选
本地
graphlit-mcp-server

graphlit-mcp-server

模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。

官方
精选
TypeScript
Kagi MCP Server

Kagi MCP Server

一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

官方
精选
Python
e2b-mcp-server

e2b-mcp-server

使用 MCP 通过 e2b 运行代码。

官方
精选
Neon MCP Server

Neon MCP Server

用于与 Neon 管理 API 和数据库交互的 MCP 服务器

官方
精选
Exa MCP Server

Exa MCP Server

模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。

官方
精选