Skip to main content
A collector is wherever you call /v1/guard. When you create or open a collector in the console, its side panel shows the exact steps and a ready-to-paste snippet for the integration you picked. This section documents each one.

Gateway

Enforce at the AI gateway. TrustGate is first-class; Portkey, LiteLLM, Kong, Apigee, and Azure APIM are supported.

Application

Wrap model calls in your app with the Python / Node SDKs, middleware, or the REST API.

Browser

Monitor AI web apps from a managed Chrome / Edge / Firefox extension.

Edge / WAF

Run at the CDN edge: Cloudflare Workers, CloudFront Lambda@Edge, Fastly, Akamai.

​
The call is always the same

Every integration makes one call: 
POST {TRUSTGUARD_URL}/v1/guard
Authorization: Bearer <collector API key>
Content-Type: application/json

{
  "protocol": "llm",                 // llm | mcp | a2a
  "direction": "input",              // "input" (prompt) or "output" (completion)
  "input": { "text": "…" },
  "session_id": "sess-123",          // the conversation
  "consumer_id": "[email protected]"     // the user / device
}
…and reacts to the verdict: 
if  is_flagged             → block the request (e.g. 403)
elif transformed_payload   → forward the masked payload instead
else                       → forward unchanged
Inspect input before calling the model and output before returning it — usually two calls per interaction. See the full contract in the Guard API.

​
Two rules for every integration

  1. Create the API key on the collector’s Auth tab and pass it as Authorization: Bearer <key>.
  2. Always send consumer_id and session_id when you have them. They attribute findings to the right user and conversation in Activity and power the multi-turn and behavioral detectors. Each snippet shows the natural source on its platform (auth context, headers, cookies).

​
SDKs

For application code, prefer the official TrustGuard SDKs over hand-rolled HTTP — they take the base URL and call /v1/guard for you:
LanguagePackage
Node / TypeScript@neuraltrust/trustguard-sdk
Pythonneuraltrust-trustguard (import from trustguard import TrustGuard)
Gogithub.com/NeuralTrust/trustguard-sdk/go
Gateway and edge integrations use raw HTTP, since they run inside vendor config or edge runtimes where the SDKs don’t apply.

​
Run several at once

You can run multiple collectors simultaneously (e.g. gateway + browser). Each has its own key and detector chain, and behavioral signals correlate across them by consumer_id.