https://hermesplant.com/api/agent-services/mcp-risk/score
Analyze an MCP server manifest for security risk before install — destructive actions, over-broad scopes, sensitive-data egress, weak auth, prompt-injection surface, and permission diff. Returns per-tool, per-factor findings with severity, why, and a concrete fix (not just a score).
Start with a quote-only recipe. Payment signing stays in your project.
const response = await fetch("https://hermesplant.com/api/agent-services/mcp-risk/score", {
method: "POST",
headers: { "content-type": "application/json" },
body: JSON.stringify({
"type": "http",
"method": "POST",
"bodyType": "json",
"bodyFieldNames": [
"authModel",
"server",
"tools"
],
"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 unavailable
ERR_SSL_PACKET_LENGTH_TOO_LONG
- Observed in cdp-bazaar
The registry record was observed and retained with provenance.
- Observed in 402-index
Discovered through bazaar.
- Registry record checked
Registry health: healthy.
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.