Verify an on-chain transaction against a previously-issued intent. Reads the chain via public RPC, confirms recipient/asset/amount/timing. Cross-rail replay protection enforced: a tx_hash can be verified at most once across all rails.
Part of the PaymentOracle — Verifiable Multi-Rail Payment Receipts server.
Free to start. No card required.
AI agents call verify_payment to retrieve information from PaymentOracle — Verifiable Multi-Rail Payment Receipts without modifying any data. This is common in research, monitoring, and reporting workflows where the agent needs context before taking action. Because read operations don't change state, they are generally safe to allow without restrictions -- but you may still want rate limits to control API costs.
Even though verify_payment only reads data, uncontrolled read access can leak sensitive information or rack up API costs. An agent caught in a retry loop could make thousands of calls per minute. A rate limit gives you a safety net without blocking legitimate use.
Read-only tools are safe to allow by default. No rate limit needed unless you want to control costs.
{
"version": "1",
"default": "deny",
"tools": {
"verify_payment": {}
}
}See the full PaymentOracle — Verifiable Multi-Rail Payment Receipts policy for all 6 tools.
These attack patterns abuse exactly the kind of access verify_payment gives an agent. Each links to the full case and the policy that stops it:
Other read tools across the catalogue. The same approach applies to each: allow, with a rate cap to control cost.
Verify an on-chain transaction against a previously-issued intent. Reads the chain via public RPC, confirms recipient/asset/amount/timing. Cross-rail replay protection enforced: a tx_hash can be verified at most once across all rails.. It is categorised as a Read tool in the PaymentOracle — Verifiable Multi-Rail Payment Receipts MCP Server, which means it retrieves data without modifying state.
Register the PaymentOracle — Verifiable Multi-Rail Payment Receipts MCP server in PolicyLayer and add a rule for verify_payment: 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 PaymentOracle — Verifiable Multi-Rail Payment Receipts. Nothing to install.
verify_payment is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the verify_payment 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 verify_payment. 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.
verify_payment is provided by the PaymentOracle — Verifiable Multi-Rail Payment Receipts MCP server (https://tooloracle.io/payments/mcp/). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 6 PaymentOracle — Verifiable Multi-Rail Payment Receipts 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.