Guard

CompanyArtificial IntelligenceGovernancePlatformEnterprise

Properties

Name Type Description
id string
slug string
name string
description stringnull
checks array
threshold number Score threshold that triggers the guard action
action string Action to take when threshold is exceeded. `redact` masks the matched text, `warn` allows the call but shows a warning, `warn_user` requires the user to approve the request before it proceeds, and `bl
status string
is_default boolean Whether this is a built-in default guard
scope stringnull When the guard is evaluated
created_at string Creation timestamp.
org_id string Organization this record belongs to.
message stringnull Message shown to the user when this guard blocks or warns a call. Absent on the built-in default guards.
settings objectnull Guard-level settings.
sort_order integer Position used when ordering guards for evaluation.
updated_at string Last modification timestamp.
View JSON Schema on GitHub

JSON Schema

webrix-guard-schema.json Raw ↑
{
  "$schema": "https://json-schema.org/draft/2020-12/schema",
  "$id": "https://raw.githubusercontent.com/api-evangelist/webrix/main/json-schema/webrix-guard-schema.json",
  "title": "Guard",
  "x-generated": "2026-10-19",
  "x-method": "derived",
  "x-generator": "derive-json-schema.py",
  "x-source": "openapi/_original/webrix-api-openapi.json#/components/schemas/Guard",
  "type": "object",
  "properties": {
    "id": {
      "type": "string"
    },
    "slug": {
      "type": "string"
    },
    "name": {
      "type": "string"
    },
    "description": {
      "type": [
        "string",
        "null"
      ]
    },
    "checks": {
      "type": "array",
      "items": {
        "$ref": "#/$defs/GuardCheck"
      }
    },
    "threshold": {
      "type": "number",
      "description": "Score threshold that triggers the guard action"
    },
    "action": {
      "type": "string",
      "enum": [
        "redact",
        "warn",
        "warn_user",
        "block"
      ],
      "description": "Action to take when threshold is exceeded. `redact` masks the matched text, `warn` allows the call but shows a warning, `warn_user` requires the user to approve the request before it proceeds, and `block` prevents the call entirely."
    },
    "status": {
      "type": "string",
      "enum": [
        "active",
        "draft"
      ]
    },
    "is_default": {
      "type": "boolean",
      "description": "Whether this is a built-in default guard"
    },
    "scope": {
      "type": [
        "string",
        "null"
      ],
      "enum": [
        "buildtime",
        "runtime"
      ],
      "description": "When the guard is evaluated"
    },
    "created_at": {
      "type": "string",
      "format": "date-time",
      "description": "Creation timestamp."
    },
    "org_id": {
      "type": "string",
      "format": "uuid",
      "description": "Organization this record belongs to."
    },
    "message": {
      "type": [
        "string",
        "null"
      ],
      "description": "Message shown to the user when this guard blocks or warns a call. Absent on the built-in default guards."
    },
    "settings": {
      "type": [
        "object",
        "null"
      ],
      "additionalProperties": true,
      "description": "Guard-level settings.",
      "properties": {
        "sync_checks": {
          "type": "boolean",
          "description": "Whether the guard's checks are kept in sync with their source."
        },
        "redact_fallback_action": {
          "type": "string",
          "enum": [
            "block",
            "warn",
            "allow"
          ],
          "description": "What a redact guard does when it triggers but nothing could be masked (for example when the match only exists inside encoded content). Defaults to `block`."
        }
      }
    },
    "sort_order": {
      "type": "integer",
      "description": "Position used when ordering guards for evaluation."
    },
    "updated_at": {
      "type": "string",
      "format": "date-time",
      "description": "Last modification timestamp."
    }
  },
  "$defs": {
    "GuardCheck": {
      "type": "object",
      "required": [
        "id",
        "type",
        "certainty"
      ],
      "properties": {
        "id": {
          "type": "string",
          "description": "Unique identifier for the check"
        },
        "name": {
          "type": "string",
          "description": "Display name for the check"
        },
        "type": {
          "type": "string",
          "enum": [
            "builtin",
            "regex",
            "jsonata",
            "llm"
          ],
          "description": "Type of check to perform"
        },
        "certainty": {
          "type": "number",
          "description": "Certainty score (0-10) contributed when this check matches"
        },
        "config": {
          "$ref": "#/$defs/GuardCheckConfig"
        },
        "disabled": {
          "type": "boolean",
          "description": "Whether the check is disabled"
        }
      }
    },
    "GuardCheckConfig": {
      "type": "object",
      "description": "Check-specific configuration",
      "properties": {
        "pattern": {
          "type": "string",
          "description": "Regex pattern (for regex type)"
        },
        "replacement": {
          "type": "string",
          "description": "Replacement text for redaction (for regex type)"
        },
        "expression": {
          "type": "string",
          "description": "JSONata expression (for jsonata type)"
        },
        "prompt": {
          "type": "string",
          "description": "LLM prompt (for llm type)"
        },
        "precondition_pattern": {
          "type": "string",
          "description": "Optional regex the content must match (case-insensitive) before the LLM is called (for llm type). Content that doesn't match is skipped and scores 0."
        },
        "builtin_id": {
          "type": "string",
          "description": "Built-in check identifier (for builtin type)"
        },
        "min_confidence": {
          "type": "number",
          "minimum": 0,
          "maximum": 1,
          "description": "Minimum model confidence (for the person-name-builtin check)"
        },
        "allowlist": {
          "type": "array",
          "items": {
            "type": "string"
          },
          "description": "Spans to never report (for the person-name-builtin check)"
        }
      }
    }
  }
}

Work with this as data

Every JSON Schema 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 schemas

4 MCP tools reach this
  • find_json_schemasBrowse and filter every JSON Schema 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 JSON Schema
curl "https://apis.io/api/v1/json-schemas/webrix-guard"
All schemas
curl "https://apis.io/api/v1/json-schemas?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.