uniple-x402-purchase
Enables AI agents to browse, quote, and purchase products from Uniple's x402 catalog API using JPYC payments.
README
Uniple x402 Agent Skill
Skill + MCP server for AI agents buying products exposed through Uniple's x402 catalog API. It is intended for KOVA, Codex, Claude Desktop, and other MCP-capable agent clients.
This is separate from jpyc-ec-purchase: JPYC EC uses x402 v2,
POST /api/v1/checkout, and PAYMENT-SIGNATURE. Uniple currently uses
x402 v1, catalog/payment URLs, and X-PAYMENT.
What It Supports
- Read-only catalog discovery:
GET https://uniple.io/api/x402/shop/eccube/products?merchantSiteId=...
- Quote / payment challenge:
GET paymentUrlwithquantityandshipping*query params- Reads
402+ decodedpaymentRequired
- Optional purchase:
- Signs JPYC EIP-3009
TransferWithAuthorization - Calls the same payment URL with
X-PAYMENT - Returns Uniple's paid response and webhook status
- Signs JPYC EIP-3009
Safety
Use quote_product first. It never signs or sends funds.
purchase_product requires:
BUYER_PRIVATE_KEYenv varmax_amount_atomicbudget cap- matching quote amount within that cap
Do not configure a funded private key unless you intend to allow the MCP server to purchase.
Local Build
cd uniple-x402-agent-skill
npm install
npm run build
npm test
MCP Config Example
{
"mcpServers": {
"uniple-x402-purchase": {
"command": "node",
"args": [
"/absolute/path/uniple-x402-agent-skill/mcp-servers/uniple-x402-purchase/dist/bin.js"
],
"env": {
"UNIPLE_API_URL": "https://uniple.io",
"BUYER_PRIVATE_KEY": "0x..."
}
}
}
}
Omit BUYER_PRIVATE_KEY if you only want catalog and quote tools.
EC-CUBE4 Smoke Target
Catalog:
https://uniple.io/api/x402/shop/eccube/products?merchantSiteId=eccube4.uniple.io
Typical 55 JPYC item quote with the current EC-CUBE4 shipping settings:
- product subtotal: 55 JPYC
- shipping: 150 JPYC
- total: 205 JPYC
- network:
eip155:137 - asset: JPYC Polygon
0xE7C3...3c29
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.