Paylo MCP Server

Paylo MCP Server

Enables AI agents to interact with the Paylo commerce ecosystem, allowing them to discover merchants, search products, manage shopping carts, and facilitate transactions through Paystack payment integration.

Category
访问服务器

README

Paylo MCP Server

The Commerce Gateway for AI Agents

The Paylo MCP Server is a bridge that empowers AI models (like Claude, GPT-4) to interact with the real-world commerce ecosystem of Paylo.

By adding this server to your AI agent's context, you transform it from a text processor into a capable shopping assistant that can browse storefronts, find products, and facilitate transactions across the Paylo network.


🚀 Capabilities

This server exposes a set of structured tools that allow AI agents to perform the following actions autonomously:

🛍️ Discovery & Search

  • Merchant Discovery: Find active storefronts based on categories or names.
  • Product Search: Semantic and keyword search across the entire Paylo product catalog.
  • Product Details: Retrieve rich metadata, pricing, and availability for specific items.

💳 Commerce & Transactions

  • Cart Management: intelligently build orders with multiple items.
  • Checkout: Generate secure Paystack payment links for users to complete purchases.
  • Order Tracking: Check the real-time status of payments and orders.

🏗️ Architecture

This server implements the Model Context Protocol (MCP) to standardize how AI agents interface with Paylo's infrastructure.

graph LR
    A[AI Agent / Claude] -- MCP Protocol --> B[Paylo MCP Server]
    B -- Queries --> C[(Supabase DB)]
    B -- Transactions --> D[Paystack API]
    C -- Returns --> B
    D -- Payment Link --> B
    B -- JSON Response --> A

🛠️ Integration

Quick Start for Claude Desktop

To give your local Claude Desktop app access to Paylo:

  1. Clone and Build

    git clone https://github.com/nodeshift-nigeria/paylo-mcp-server.git
    cd paylo-mcp-server
    npm install
    npm run build
    
  2. Add to Claude Config Edit your claude_desktop_config.json:

    {
      "mcpServers": {
        "paylo": {
          "command": "node",
          "args": ["/absolute/path/to/paylo-mcp-server/build/index.js"]
        }
      }
    }
    

🐳 Docker Quick Start

You can also run the server directly from the published Docker image without installing Node.js:

docker run -i --rm ghcr.io/nodeshift-nigeria/paylo-mcp-server:latest

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "paylo": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "ghcr.io/nodeshift-nigeria/paylo-mcp-server:latest"
      ]
    }
  }
}

📦 Available Tools

When integrated, the following tools become available to the AI:

Tool Name Description
list_merchants Lists available Paylo storefronts with metadata.
search_products Searches for products across all merchants or within a specific store.
get_product_details Gets full details (price, description, stock) for a product.
create_order Creates a pending order for a list of items.
generate_payment_link Generates a checkout URL for a specific order.
check_payment_status Verifies if an order has been paid.

🔒 Security & Privacy

  • Read-Only Access: The server primarily performs read operations on the product catalog.
  • Secure Payments: No payment information is processed by the AI. The AI only generates a secure link; the user completes the payment on Paystack's hosted checkout.
  • Sandboxed: The server runs locally or in your controlled environment, ensuring data privacy.

📄 License

This project is licensed under the MIT License - see the LICENSE file for details.


Built by NodeShift Nigeria for the Paylo Ecosystem.

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