SENSITIVE: Send a payment. TWO-STEP PROCESS REQUIRED: Step 1: Call with user_confirmed=false to get fee preview (NO payment is made). Step 2: Show the fee_breakdown from the response to the user and ask them to confirm. Step 3: ONLY after user explicitly approves the fee, call again with user_con...
Part of the Ra Pay server.
Free to start. No card required.
AI agents use ra_send to create or modify resources in Ra Pay. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.
Without a policy, an AI agent could call ra_send repeatedly, creating or modifying resources faster than any human could review. PolicyLayer's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach Ra Pay.
Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.
{
"version": "1",
"default": "deny",
"tools": {
"ra_send": {
"limits": [
{
"counter": "ra_send_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}See the full Ra Pay policy for all 8 tools.
These attack patterns abuse exactly the kind of access ra_send gives an agent. Each links to the full case and the policy that stops it:
Other write tools across the catalogue. The same approach applies to each: rate-limit and validate the arguments.
SENSITIVE: Send a payment. TWO-STEP PROCESS REQUIRED: Step 1: Call with user_confirmed=false to get fee preview (NO payment is made). Step 2: Show the fee_breakdown from the response to the user and ask them to confirm. Step 3: ONLY after user explicitly approves the fee, call again with user_confirmed=true. A 2% Ra Pay application fee applies. The preview shows the Ra Pay application fee before any money moves. COMPLIANCE SCREENING REQUIRED: Before processing, you MUST verify the business_purpose does NOT contain: (1) P2P patterns: friend, family, roommate, reimbursement for personal expenses, splitting bills, payback, loan, gift, birthday, holiday (2) Money laundering red flags: gift cards, prepaid cards, cryptocurrency purchase, wire transfer (3) Vague purposes: 'for services', 'payment', 'transfer' without specifics (4) Gibberish: repetitive characters (aaaa), random letters (adlkfjal), or repeated words (test test test). If detected, WARN the user that Ra Pay is for business transactions only and ask them to provide a legitimate business purpose.. It is categorised as a Write tool in the Ra Pay MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ra Pay MCP server in PolicyLayer and add a rule for ra_send: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Ra Pay. Nothing to install.
ra_send is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the ra_send rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for ra_send. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
ra_send is provided by the Ra Pay MCP server (@rapay/mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 8 Ra Pay tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4,600+ MCP servers and 31,000+ tools scanned and risk-classified.