Payme MCP Server
MCP server for Payme — the leading payment system in Uzbekistan. Enables AI agents to process payments, manage cards, and generate checkout links through the Model Context Protocol.
README
Payme MCP Server
MCP server for Payme — the leading payment system in Uzbekistan. Enables AI agents (Claude, GPT, Cursor, etc.) to process payments, manage cards, and generate checkout links through the Model Context Protocol.
<p align="center"> <img src="https://img.shields.io/npm/v/payme-mcp" alt="npm version"> <img src="https://img.shields.io/badge/MCP-compatible-blue" alt="MCP Compatible"> <img src="https://img.shields.io/badge/license-MIT-green" alt="MIT License"> </p>
Why?
Stripe, PayPal, and Square all have MCP servers. Payme didn't — until now. If you're building AI agents for Uzbekistan's market, this is the missing piece.
Tools
| Tool | Description |
|---|---|
cards_create |
Tokenize a payment card (Uzcard, Humo) |
cards_verify |
Verify card with SMS code |
cards_check |
Check if a card token is valid |
cards_remove |
Remove a saved card |
receipts_create |
Create a payment receipt (invoice) |
receipts_pay |
Pay a receipt with a card token |
receipts_send |
Send receipt notification via SMS |
receipts_cancel |
Cancel/refund a receipt |
receipts_check |
Check receipt status |
checkout_url |
Generate a Payme checkout payment link |
Quick Start
npx payme-mcp
That's it. One command — downloads, installs, and runs automatically.
Get your credentials from merchant.paycom.uz, then add to your AI tool:
Claude Desktop
Add to claude_desktop_config.json:
{
"mcpServers": {
"payme": {
"command": "npx",
"args": ["-y", "payme-mcp"],
"env": {
"PAYME_ID": "your_merchant_id",
"PAYME_KEY": "your_merchant_key",
"PAYME_TEST": "true"
}
}
}
}
Claude Code
Add to .mcp.json in your project root:
{
"mcpServers": {
"payme": {
"command": "npx",
"args": ["-y", "payme-mcp"],
"env": {
"PAYME_ID": "your_merchant_id",
"PAYME_KEY": "your_merchant_key",
"PAYME_TEST": "true"
}
}
}
}
Cursor / VS Code / Windsurf
Add to MCP settings:
{
"payme": {
"command": "npx",
"args": ["-y", "payme-mcp"],
"env": {
"PAYME_ID": "your_merchant_id",
"PAYME_KEY": "your_merchant_key"
}
}
}
Usage Examples
Once connected, your AI agent can:
Create a payment link:
"Generate a Payme checkout link for order #1234, amount 99,000 UZS"
Process a card payment:
"Tokenize card 8600XXXXXXXXXXXX, verify it, then charge 50,000 UZS"
Check payment status:
"Check the status of receipt 63abc..."
Cancel a payment:
"Cancel receipt 63abc... and notify the customer"
Environment Variables
| Variable | Required | Description |
|---|---|---|
PAYME_ID |
Yes | Your Payme merchant ID |
PAYME_KEY |
Yes | Your Payme merchant key |
PAYME_TEST |
No | Set to true for sandbox mode |
Amount Format
Payme uses tiyin (1 UZS = 100 tiyin):
| UZS | Tiyin |
|---|---|
| 1,000 | 100,000 |
| 9,900 | 990,000 |
| 99,000 | 9,900,000 |
| 990,000 | 99,000,000 |
Receipt States
| State | Meaning |
|---|---|
| 0 | Created (waiting for payment) |
| 4 | Paid |
| 21 | Held (funds reserved) |
| 50 | Cancelled |
Development
git clone https://github.com/sirliboyev-uz/payme-mcp.git
cd payme-mcp
npm install
npm run build
Security
- Card numbers are tokenized by Payme — tokens are safe to store
- Never log or store raw card numbers
- Use
PAYME_TEST=truefor development/testing - All API calls use HTTPS
License
MIT — see LICENSE
Links
Built by SirliAI
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.
Neon Database
MCP server for interacting with Neon Management API and databases
E2B
Using MCP to run code via e2b.
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.