mcpField
U
U.CASH Pay

U.CASH Pay

Remote
github.com/UdotCASHFinance0Updated 6w ago
Repository

About U.CASH Pay

U.CASH Pay is a merchant-side MCP server for managing a merchant's pay.u.cash operations. It creates hosted checkouts, verifies settlement webhooks, and reads integration credentials and settings.

Key features

  1. 01Create hosted checkout sessions
  2. 02Verify webhook signatures with HMAC
  3. 03Read integration credentials
  4. 04Read safe agent settings

Use cases

  1. 01Create a checkout for a merchant transaction
  2. 02Verify a settlement webhook
  3. 03Retrieve integration details or settings

MCP support

Exposes checkout creation, webhook verification, and merchant integration and settings reads to MCP clients.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://mcp.u.cash/
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

14
ParameterTypeRequiredDescription
res_idstringYes
statusbooleanNopoll mode: GET /r/{id}?status=1 - no-mint settlement check

Details

From the project README

mcp-ucash

A merchant-side MCP server for U.CASH Pay. Let Claude Desktop, Cursor, or any MCP client manage a merchant's pay.u.cash: create checkouts, verify settlement webhooks, and read settings + integration credentials.

Tools

  • create_checkout(amount, currency, title, external_reference) → hosted checkout URL + transaction id
  • verify_webhook(raw_body, signature_header) → HMAC verify an X-Webhook-Signature
  • get_integrations() → Discord/Telegram/BigCommerce/Ecwid/Wix credentials (from /v1/integrations)
  • get_settings() → safe agent settings (from /v1/settings)

Run

# one-liner: uv installs an isolated Python 3.10+ and the deps for you
uvx --from mcp-ucash python -m mcp_ucash

Or from source:

pip install "mcp[cli]"
export UXC_API_KEY=uxc_...          # agent API key, for /v1/* reads
export UCASH_CLOUD_TOKEN=st_...     # store cloud token, for create_checkout
export UCASH_WEBHOOK_SECRET=...     # for verify_webhook
python mcp_ucash.py

Claude Desktop / Cursor config

{
  "mcpServers": {
    "ucash": {
      "command": "uvx",
      "args": ["--from", "mcp-ucash", "python", "-m", "mcp_ucash"],
      "env": {
        "UXC_API_KEY": "uxc_...",
        "UCASH_CLOUD_TOKEN": "st_...",
        "UCASH_WEBHOOK_SECRET": "..."
      }
    }
  }
}

MCP directories

This repo ships the manifests the MCP directories read:

  • mcp.json - client/registry descriptor (Glama, MCP Registry).
  • smithery.yaml - build + start spec for Smithery.

License

MIT.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.