AgentPay (Russia) logo

AgentPay (Russia)

Russian specialty-store catalog search and budget-controlled AI checkout with human approval.

Install AgentPay (Russia)

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "agentpay-russia": {
      "command": "npx",
      "args": [
        "-y",
        "agentpay-mcp"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Automated check passed— started and listed 27 tools correctly (Today).

Overview

AgentPay (Russia) MCP server connects AI agents to AgentPay’s Russian specialty-store catalog and checkout flow. It exposes product search, product details, store discovery, purchase history, and limit-controlled purchasing with human-in-the-loop approval. Use it when an agent must shop from allowlisted Russian stores, verify current price and stock, and stay within owner-defined limits; it is not a global marketplace or crypto/x402 connector.

Use cases

  • Search allowlisted Russian specialty stores
  • Verify current product price and stock
  • Reorder previously purchased items
  • Create purchases within agent spending limits
  • Require owner approval before checkout

Key features

  • Merchant catalog search
  • ProductCard lookup
  • Store discovery
  • Purchase history and reordering
  • Limit-controlled checkout
  • Human-in-the-loop approval

Tools27

What AgentPay (Russia) lets your agent do. Expand a tool for its parameters.

Verified live~5.4k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

9/9 checks healthy over the last 55d

What it can do

From the 27 tools this server returned when we ran it.

Can delete or modify data · 6Handles credentials · 15Makes network requests · 3Read-only tools · 21
Network at startup3 connections
Files written at startupNone
Install scriptsNone
npm provenanceNot published
Package age239 days
Maintainers1

Observed 2026-11-02 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 9h ago via OSV.dev · agentpay-mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

npm downloads1.4kPackage downloads in the last 30 days.
Last commit2mo agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed27Callable tools this server registers over MCP.

How AgentPay (Russia) works

What AgentPay (Russia) does

The AgentPay (Russia) MCP server gives an AI agent access to a merchant catalog and purchasing flow for Russia-based specialty stores listed on AgentPay. The agent can inspect current product information, including price, availability, SKU, images, and a ProductCard, before attempting a purchase.

The service is designed for controlled shopping rather than unrestricted purchasing. Checkout is subject to configured limits and human-in-the-loop approval. The catalog should be treated as the source of truth for price and stock instead of information retained in the model’s context.

How it works

AgentPay (Russia) MCP server deployments can use the remote endpoint at https://agentpay.shop/ap/mcp. The connection process begins by retrieving https://agentpay.shop/connect.json, installing the remote MCP configuration described there, and opening the supplied browser link. The account owner then selects “Разрешить” to approve access. The owner should not be asked to copy an ap_… value from the AgentPay cabinet. After authorization, the agent calls verify_connection to confirm that the connection is active.

For discovery, peek_stores can serve as an initial step when the request is to find or select something. Product searches and individual product lookups provide the current details needed before checkout. Existing purchases can be used as a starting point for reorders, but the product’s price should be refreshed through the catalog first.

Setup and configuration

Use the remote MCP option when connecting an MCP client. The README identifies Cursor as a remote web connector and provides the endpoint above. It also points to https://agentpay.shop/llms.txt for additional model-facing information.

A separately published stdio package is expected to use the name agentpay-ru-mcp. The setup instructions explicitly distinguish it from the unrelated npm package named agentpay-mcp, which refers to an x402/crypto project from another publisher. Do not install that similarly named package for this integration.

Tools and capabilities

  • search_products searches the merchant feed and returns fields such as price, stock status, SKU, and images.
  • get_product retrieves one ProductCard so the agent can recheck availability and price.
  • peek_stores supports an initial store-discovery step.
  • list_purchases exposes previous purchases for reorder workflows.
  • create_purchase starts checkout while applying limits and requiring human approval.
  • verify_connection confirms the authorized connection.

Limitations and notes

The service is limited to Russia and to specialty stores allowlisted on AgentPay. It is not presented as a general marketplace connector, and it does not use the crypto/x402 payment model. A developer should plan for explicit catalog lookups before quoting prices or initiating a purchase. Reorder data does not replace that verification step: refresh the current product details first, then proceed through the controlled checkout flow.

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about AgentPay (Russia)

AgentPay (Russia) is an MCP server that connects AI agents to AgentPay’s Russian allowlisted specialty-store catalog and checkout system. Its main tools search products, retrieve ProductCards, inspect stores, list prior purchases, create purchases under configured limits, and verify the connection. It is not a crypto or x402 integration.

Install the remote MCP configuration from `https://agentpay.shop/connect.json`. Open the browser link it provides, choose “Разрешить,” and then call `verify_connection`. Do not use the unrelated npm package `agentpay-mcp` or ask the account owner to paste an `ap_…` value.

Yes, Cursor is listed as a remote web connector for AgentPay (Russia). Configure the remote MCP endpoint at `https://agentpay.shop/ap/mcp`, using the connection instructions from `https://agentpay.shop/connect.json`.

It provides `search_products`, `get_product`, `peek_stores`, `list_purchases`, `create_purchase`, and `verify_connection`. Together these cover catalog search, product verification, store discovery, reorder lookup, controlled checkout, and connection verification.

Related MCP servers

Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewAgentPay (Russia) AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/agentpay-russia?style=directory)](https://allmcps.com/mcp/agentpay-russia)
HTML Embed
<a href="https://allmcps.com/mcp/agentpay-russia"><img src="https://allmcps.com/api/badge/agentpay-russia?style=directory" alt="AgentPay (Russia) on AllMCPs" /></a>