Wrap any paid HTTP endpoint in the x402 pay-then-call loop and return the downstream response plus an EIP-191 signed receipt proving InsureLink mediated the call. The signed context envelope contains: { request: {url, method, body_sha256}, payment: {asset, amount, network, settlement_id}, respons...
Risk signalsAccepts URL/endpoint input (url) · Accepts raw HTML/template content (body) · High parameter count (10 properties)
Part of the InsureLink server.
Free to start. No card required.
AI agents use pay_then_call to initiate financial transactions through InsureLink. Financial operations involve real money and are irreversible once processed. PolicyLayer blocks financial tools by default, requiring explicit human approval with transaction-level limits to prevent unauthorised spending.
pay_then_call moves real money. Without a policy, an autonomous agent could initiate transactions that drain accounts or exceed budgets. PolicyLayer blocks financial tools by default, requiring human-in-the-loop approval with configurable spending limits per transaction and per time window.
Financial tools involve real money. Block by default and require explicit human approval before enabling.
{
"version": "1",
"default": "deny",
"tools": {
"pay_then_call": {
"deny_if": [
{
"conditions": [],
"on_deny": "Requires human approval."
}
]
}
}
}See the full InsureLink policy for all 28 tools.
These attack patterns abuse exactly the kind of access pay_then_call gives an agent. Each links to the full case and the policy that stops it:
Other financial tools across the catalogue. The same approach applies to each: deny by default, or require human approval.
Wrap any paid HTTP endpoint in the x402 pay-then-call loop and return the downstream response plus an EIP-191 signed receipt proving InsureLink mediated the call. The signed context envelope contains: { request: {url, method, body_sha256}, payment: {asset, amount, network, settlement_id}, response: {status, sha256, content_type, length}, observed_at, mediator: 'insurelink' } and a signature recoverable to InsureLink's deployer key. Two modes: (a) caller_supplies_payment — pass x_payment_header (base64) so the upstream call is settled by your wallet; (b) mode='quote_only' — return only the 402 quote without paying. Pass idempotency_key to safely retry: identical requests return the cached signed receipt without settling a second payment, and conflicting payloads under the same key are rejected. Use this to give an LLM verifiable provenance for any paid agent call (banking, market data, gov endpoints).. It is categorised as a Financial tool in the InsureLink MCP Server, which means it involves financial transactions. Block by default and require explicit approval.
Register the InsureLink MCP server in PolicyLayer and add a rule for pay_then_call: 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 InsureLink. Nothing to install.
pay_then_call is a Financial tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the pay_then_call 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 pay_then_call. 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.
pay_then_call is provided by the InsureLink MCP server (https://ivnmscuuljqubunqcgkh.supabase.co/functions/v1/mcp-server/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 28 InsureLink 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.