agentpay-mcp
AgentPay MCP (Russia only): controlled AI agent budget in allowlisted specialty stores. Not x402/crypto. Remote: https://agentpay.shop/ap/mcp
Documentation
AgentPay MCP (Russia / РФ)
Merchant catalog + controlled checkout for your AI agent (ООО НЕКСУС-ТЕХ).
Market: Russia only. Agent sees price, stock, and ProductCard from allowlisted specialty stores on AgentPay — then buys within your limits. Not a global marketplace connector and not crypto/x402.
Not npm `agentpay-mcp` (x402/crypto by another publisher). Our stdio package name: `agentpay-ru-mcp` (when published). Prefer remote MCP.
Catalog tools
| Tool | What it does |
|---|---|
| `search_products` | Search merchant feed: price, inStock, sku, images |
| `get_product` | One ProductCard — confirm price/stock before buy |
| `peek_stores` | Quiet first hop when owner says «найди» / «подбери» |
| `list_purchases` | Reorder — then refresh price via catalog |
| `create_purchase` | Checkout with limits + HITL |
Never quote price from model memory. Always use `search_products` or `get_product`.
When the user says «Подключи AgentPay»
1. Fetch https://agentpay.shop/connect.json
2. Install remote MCP from that JSON. Never `npx agentpay-mcp`.
3. Open the browser link and wait for Разрешить. Never ask the owner to paste `ap_…` from the cabinet.
4. Call `verify_connection`.
Also: https://agentpay.shop/llms.txt
Web connectors (Grok / ChatGPT / Cursor remote): `https://agentpay.shop/ap/mcp`
Registry
Official MCP Registry name: `io.github.zapnikita95/agentpay`
Frequently asked questions
What is agentpay-mcp?
agentpay-mcp is AgentPay MCP (Russia only): controlled AI agent budget in allowlisted specialty stores. Not x402/crypto. Remote: https://agentpay.shop/ap/mcp
How do I install agentpay-mcp?
Open the GitHub repository and follow its README. Most MCP servers are added to your client's MCP config, then called by your agent.
Is agentpay-mcp open source?
Yes — it is hosted on GitHub at https://github.com/zapnikita95/agentpay-mcp.
Related MCP tools
Code research platform for AI agents; find, understand, and prove context across your code and all of GitHub, in a fraction of the tokens. One toolset, MCP or CLI
Browser MCP is a Model Context Provider (MCP) server that allows AI applications to control your browser
The go-to web for your AI coding agent — local-first search, fetch, crawl & research over MCP. No API keys, no cloud, $0/query. Public beta.
MCP server that enables AI assistants to interact with Google Gemini CLI, leveraging Gemini's massive token window for large file analysis and codebase understanding
Universal AI context generator. Saves thousands of tokens per conversation in Claude Code, Cursor, Copilot, Codex, and more.
A desktop MCP client designed as a tool unitary utility integration, accelerating AI adoption through the Model Context Protocol (MCP) and enabling cross-vendor LLM API orchestration.
Run your own MCP server? See who uses it and what to fix.
Measure it with TrackMCP