Solo.io · AsyncAPI Specification

Solo Io Webhooks

Version

View Spec View on GitHub CompanyAPI GatewayService MeshKubernetesIstioEnvoyAI GatewayAgentic AIMCPDeveloper PortalCloud-NativeOpen-SourceAsyncAPIEvents

AsyncAPI Specification

Raw ↑
generated: '2026-08-02'
method: searched
source: openapi/solo-io-ai-gateway-guardrail-webhook-openapi.yml, https://docs.solo.io/agentgateway/2.3.x/llm/guardrails/webhook/
spec_type: Webhooks
asyncapi: none
asyncapi_note: >-
  No AsyncAPI document is published anywhere on solo.io, docs.solo.io, or the solo-io GitHub
  organization (a code search for "asyncapi" across the org returned zero results). Solo.io
  ships no event bus, message broker, or subscription API of its own — its event surface is
  the customer's own data plane, observed through Envoy access logs and OpenTelemetry rather
  than through a Solo.io-hosted event stream. Recorded as absent; nothing fabricated.
note: >-
  Solo.io does publish a real, specified webhook contract, and it runs in the inverse
  direction from the usual provider webhook: the operator implements the endpoints and the
  Solo.io AI gateway calls them synchronously on the LLM request/response path. It is
  contracted in OpenAPI 3.1.0 with a `Webhooks` tag, not in AsyncAPI.
webhooks:
- name: guardrail-request
  direction: gateway-to-operator
  operation: process_prompts_request_post
  method: POST
  path: /request
  spec: openapi/solo-io-ai-gateway-guardrail-webhook-openapi.yml
  description: >-
    Called with the normalized prompt (GuardrailsPromptRequest) before it is sent to the
    large language model. The implementation returns a GuardrailsPromptResponse carrying a
    PassAction, MaskAction, or RejectAction.
  responses: [200, 422]
  docs: https://docs.solo.io/agentgateway/2.3.x/llm/guardrails/webhook/
- name: guardrail-response
  direction: gateway-to-operator
  operation: process_responses_response_post
  method: POST
  path: /response
  spec: openapi/solo-io-ai-gateway-guardrail-webhook-openapi.yml
  description: >-
    Called with the normalized LLM response (GuardrailsResponseRequest) before it is returned
    to the caller. The implementation returns a GuardrailsResponseResponse carrying a
    PassAction, MaskAction, or RejectAction.
  responses: [200, 422]
  docs: https://docs.solo.io/agentgateway/2.3.x/llm/guardrails/webhook/
actions:
- {name: PassAction, effect: allow the content through unchanged}
- {name: MaskAction, effect: return modified content with sensitive information masked}
- {name: RejectAction, effect: block the content and return an error response}
products:
- kgateway
- Agentgateway Enterprise
- Gloo Gateway
security:
  declared_in_spec: none
  note: authentication between the gateway and the webhook is deployment configuration (mTLS,
    network policy, or a shared header), not part of the contract

Work with this as data

Every AsyncAPI spec here is available over the APIs.io API and to AI agents over MCP.

MCP server

One button, every client — Claude, Cursor, VS Code and the rest.

https://apis.io/mcp

Tools for asyncapi

4 MCP tools reach this
  • find_asyncapisBrowse and filter every AsyncAPI spec in the catalog.
  • apis_io_searchSTART HERE — APIs, providers and tags for one query, each with its total.
  • resolveTurn a domain, URL or GitHub org into the provider it belongs to.
  • find_cohortsEvery scored population of providers in the catalog.
All 92 tools →

Call it yourself

curl for this page
This AsyncAPI spec
curl "https://apis.io/api/v1/asyncapis/solo-io-webhooks"
All asyncapi
curl "https://apis.io/api/v1/asyncapis?limit=25"

Discovery needs no key. Ratings and market analysis are Pro.

Get an API key

Free tier, no form to fill in. Signing in shares your email address with us — we store it to create your key and to recognise you if you sign in with another provider. See our Privacy Policy and Terms.

A second provider on the same verified email joins the account you already have.