paygent: POST /agents/tool-call-guard/run
Pre-execution safety oracle for agent actions: submit the tool call you are about to run (shell, http, sql, file, code, env) plus your stated intent, and get a machine-enforceable verdict before you execute it. Decodes what the call does, flags the danger toolkit (rm -rf, reverse shell, curl|sh, SSRF to cloud metadata, credential reads, DROP/DELETE-without-WHERE, path traversal, dynamic eval), and binds it to your intent (allowedHosts/allowedPaths/readOnly/noNetwork) - only a fully pinned, clean, intent-matched call is auto-exec-safe. Hybrid: a deterministic, uninjectable detector engine (authoritative) plus an LLM classifier that can only raise the risk. Fails closed. Detection of known-dangerous patterns, not a proof of safety; it never executes the call.
Start with a quote-only recipe. Payment signing stays in your project.
const response = await fetch("https://paygent.obsmetrics.com/agents/tool-call-guard/run", {
method: "POST",
headers: { "content-type": "application/json" },
body: JSON.stringify({
"type": "http",
"method": "POST",
"bodyType": "json",
"bodyFieldNames": [
"call",
"intent"
],
"pathParamNames": [],
"queryParamNames": []
}),
});
console.log(response.status);
console.log(Object.fromEntries(response.headers));
console.log((await response.text()).slice(0, 1000));
// A valid 402 is a quote, not a completed paid call.Review the provider input schema before running this non-read-only method. No payment code is included.
- Exact route checked
not safely testable · potentially-mutating-method:POST
- Origin reachable
HEAD https://paygent.obsmetrics.com/ returned 200.
- Observed in cdp-bazaar
The registry record was observed and retained with provenance.
EVIDENCE
Each record has an exact-route quote outcome. Unresolved templates and potentially mutating methods are labeled instead of being invoked without provider-specific test input. A quote is still separate from a settled paid call.