mcpField
R
Ra Pay

Ra Pay

Local
github.com/Ra-Pay-AIFinance

About Ra Pay

Send fiat payments via MCP with two-step confirmation and Stripe Connect

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
"mcpServers": {
"ai-rapay": {
"command": "npx",
"args": [
"-y",
"@rapay/mcp-server"
]
}
}
}
Run commandnpx -y @rapay/mcp-server

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npm@rapay/mcp-server1.2.5

Tools

7

Saved tool list · updated 3w ago

ParameterTypeRequiredDescription
amountnumberYesAmount to send in USD cents (e.g., 10000 = $100.00). Minimum: 100 cents ($1.00)
recipient_idstringYesStripe connected account ID (format: acct_xxx). Must be a valid Stripe account.
user_confirmedbooleanYesREQUIRED. Must be false on first call to get fee preview. Only set to true AFTER showing user the fee_breakdown and getting their explicit approval.
business_purposestringYesBusiness purpose for this payment (10-200 characters). Required for compliance. Must describe actual goods or services rendered (e.g., 'Logo design work', 'API consulting'). REJECT purposes containing: friend, family, roommate, reimbursement, loan, gift, birthday, gift card, prepaid card, splitting bills, payback, personal expense, crypto, bitcoin. ALSO REJECT gibberish: repetitive chars (aaaa), random letters, repeated words (test test test). Ra Pay is a B2B payment platform - NOT for peer-to-peer transfers. Valid examples: 'Freelance development work - Invoice #123', 'API consulting services - March 2026'. Invalid examples: 'Lunch reimbursement', 'Gift for friend', 'Gift cards for team', 'aaaaaaaaaa', 'asdfghjkl'.

Details

The maintainer has not added details yet. Check the README in the repository.

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.