Pricing

Pay per event

Action Firewall - Block Destructive AI Agent Actions

A safety gate in front of every agent action. Classifies a proposed shell, SQL, API, payment, or delete as allow / require-approval / block against a destructive-action taxonomy and your policy, before it runs. Catches rm-rf, fork bombs, DROP TABLE, and force-push.

Pricing

Pay per event

Rating

0.0

(0)

Developer

Creator Fusion

Actor stats

Bookmarked

Total users

Monthly active users

4 days ago

Last modified

Categories

Developer tools

You can access the Action Firewall - Block Destructive AI Agent Actions programmatically from your own applications by using the Apify API. You can also choose the language preference from below. To use the Apify API, you’ll need an Apify account and your API token, found in API & Integrations in Apify Console.

Python

JavaScript

CLI

OpenAPI

HTTP

MCP

{
  "openapi": "3.0.1",
  "info": {
    "version": "1.0",
    "x-build-id": "hZXfHf8lofJ0fxb1c"
  },
  "servers": [
    {
      "url": "https://api.apify.com/v2"
    }
  ],
  "paths": {
    "/acts/apricot_blackberry~agent-action-firewall/run-sync-get-dataset-items": {
      "post": {
        "operationId": "run-sync-get-dataset-items-apricot_blackberry-agent-action-firewall",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for its completion, and returns Actor's dataset items in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    },
    "/acts/apricot_blackberry~agent-action-firewall/runs": {
      "post": {
        "operationId": "runs-sync-apricot_blackberry-agent-action-firewall",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor and returns information about the initiated run in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK",
            "content": {
              "application/json": {
                "schema": {
                  "$ref": "#/components/schemas/runsResponseSchema"
                }
              }
            }
          }
        }
      }
    },
    "/acts/apricot_blackberry~agent-action-firewall/run-sync": {
      "post": {
        "operationId": "run-sync-apricot_blackberry-agent-action-firewall",
        "x-openai-isConsequential": false,
        "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.",
        "tags": [
          "Run Actor"
        ],
        "requestBody": {
          "required": true,
          "content": {
            "application/json": {
              "schema": {
                "$ref": "#/components/schemas/inputSchema"
              }
            }
          }
        },
        "parameters": [
          {
            "name": "token",
            "in": "query",
            "required": true,
            "schema": {
              "type": "string"
            },
            "description": "Enter your Apify token here"
          }
        ],
        "responses": {
          "200": {
            "description": "OK"
          }
        }
      }
    }
  },
  "components": {
    "schemas": {
      "inputSchema": {
        "type": "object",
        "required": [
          "action"
        ],
        "properties": {
          "action": {
            "title": "Proposed action",
            "type": "string",
            "description": "The action to classify BEFORE it runs. Pass EITHER a plain command string (e.g. \"rm -rf /tmp/cache\" or \"DROP TABLE users;\") OR a JSON object (as a string) with any of: type (shell|sql|http-request|filesystem|send-message|payment|delete), command, target, args (array) — e.g. {\"type\":\"shell\",\"command\":\"rm -rf /var/data\",\"target\":\"/var/data\"}. Both forms are accepted; the object form gives sharper classification. Callers using the run API/MCP may also pass a real JSON object here."
          },
          "policy": {
            "title": "Policy (optional)",
            "type": "object",
            "description": "Optional caller policy. allow: array of substrings that force an 'allow' verdict for non-critical actions. deny: array of substrings that force a 'block'. maxRisk: number 0-100; an action scoring above it can only be permitted with approval, never silently allowed."
          },
          "environment": {
            "title": "Target environment",
            "enum": [
              "prod",
              "staging",
              "dev"
            ],
            "type": "string",
            "description": "Where the action would run. 'prod' escalates the risk of any flagged action (production blast radius). Used for scoring only.",
            "default": "prod"
          }
        }
      },
      "runsResponseSchema": {
        "type": "object",
        "properties": {
          "data": {
            "type": "object",
            "properties": {
              "id": {
                "type": "string"
              },
              "actId": {
                "type": "string"
              },
              "userId": {
                "type": "string"
              },
              "startedAt": {
                "type": "string",
                "format": "date-time",
                "example": "2025-01-08T00:00:00.000Z"
              },
              "finishedAt": {
                "type": "string",
                "format": "date-time",
                "example": "2025-01-08T00:00:00.000Z"
              },
              "status": {
                "type": "string",
                "example": "READY"
              },
              "meta": {
                "type": "object",
                "properties": {
                  "origin": {
                    "type": "string",
                    "example": "API"
                  },
                  "userAgent": {
                    "type": "string"
                  }
                }
              },
              "stats": {
                "type": "object",
                "properties": {
                  "inputBodyLen": {
                    "type": "integer",
                    "example": 2000
                  },
                  "rebootCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "restartCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "resurrectCount": {
                    "type": "integer",
                    "example": 0
                  },
                  "computeUnits": {
                    "type": "integer",
                    "example": 0
                  }
                }
              },
              "options": {
                "type": "object",
                "properties": {
                  "build": {
                    "type": "string",
                    "example": "latest"
                  },
                  "timeoutSecs": {
                    "type": "integer",
                    "example": 300
                  },
                  "memoryMbytes": {
                    "type": "integer",
                    "example": 1024
                  },
                  "diskMbytes": {
                    "type": "integer",
                    "example": 2048
                  }
                }
              },
              "buildId": {
                "type": "string"
              },
              "defaultKeyValueStoreId": {
                "type": "string"
              },
              "defaultDatasetId": {
                "type": "string"
              },
              "defaultRequestQueueId": {
                "type": "string"
              },
              "buildNumber": {
                "type": "string",
                "example": "1.0.0"
              },
              "containerUrl": {
                "type": "string"
              },
              "usage": {
                "type": "object",
                "properties": {
                  "ACTOR_COMPUTE_UNITS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_WRITES": {
                    "type": "integer",
                    "example": 1
                  },
                  "KEY_VALUE_STORE_LISTS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_INTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_EXTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_SERPS": {
                    "type": "integer",
                    "example": 0
                  }
                }
              },
              "usageTotalUsd": {
                "type": "number",
                "example": 0.00005
              },
              "usageUsd": {
                "type": "object",
                "properties": {
                  "ACTOR_COMPUTE_UNITS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATASET_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "KEY_VALUE_STORE_WRITES": {
                    "type": "number",
                    "example": 0.00005
                  },
                  "KEY_VALUE_STORE_LISTS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_READS": {
                    "type": "integer",
                    "example": 0
                  },
                  "REQUEST_QUEUE_WRITES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_INTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "DATA_TRANSFER_EXTERNAL_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_RESIDENTIAL_TRANSFER_GBYTES": {
                    "type": "integer",
                    "example": 0
                  },
                  "PROXY_SERPS": {
                    "type": "integer",
                    "example": 0
                  }
                }
              }
            }
          }
        }
      }
    }
  }
}

Action Firewall for AI Agents | Block Destructive Commands OpenAPI definition

OpenAPI is a standard for designing and describing RESTful APIs, allowing developers to define API structure, endpoints, and data formats in a machine-readable way. It simplifies API development, integration, and documentation.

OpenAPI is effective when used with AI agents and GPTs by standardizing how these systems interact with various APIs, for reliable integrations and efficient communication.

By defining machine-readable API specifications, OpenAPI allows AI models like GPTs to understand and use varied data sources, improving accuracy. This accelerates development, reduces errors, and provides context-aware responses, making OpenAPI a core component for AI applications.

You can download the OpenAPI definitions for Action Firewall - Block Destructive AI Agent Actions from the options below:

OpenAPI.json

If you’d like to learn more about how OpenAPI powers GPTs, read our blog post.

You can also check out our other API clients:

Action Firewall - Block Destructive AI Agent Actions API in Python

Action Firewall - Block Destructive AI Agent Actions API in JavaScript

Action Firewall - Block Destructive AI Agent Actions API through CLI

Action Firewall - Block Destructive AI Agent Actions API

Shell Command Safety MCP

q_services/shell-command-safety-mcp

Gate agent-generated shell commands with deterministic allowlists and checks for injection, destructive operations, privilege escalation and download-to-shell patterns.

Q Services

AI Agent Tool Firewall

zentrafoundry/zentra-agentops-tool-firewall

Allow, deny, redact, or require review for AI-agent tool calls.

Zentra

SQL Safety Gate MCP

q_services/sql-safety-gate-mcp

Parse SQL and enforce a deterministic single-statement read-only policy before agent execution.

Q Services

Action.com Search Scraper

powerai/action-com-search-scraper

Scrape products from Action.com by providing a search URL, with automatic pagination and comprehensive product information extraction.

PowerAI

Agent Tool Policy Firewall MCP

q_services/agent-tool-policy-firewall-mcp

Evaluate proposed MCP tool calls against deterministic allow, deny, domain and confirmation policies.

Q Services

AI Agent Effect Firewall

tmas_from_iceland/ai-agent-effect-firewall

Execution firewall for AI agents. Blocks untrusted inputs from triggering real-world actions by enforcing decision-level allow / deny / approval gates. Infrastructure safety layer for tool-enabled agents

Tomasz Trojanowski

US OFAC Sanctions Action Watch

nexgenwatch/us-ofac-sanctions-action-watch

OFAC Recent Actions as they are posted: the action's own identifier, its date, its headline and its category (Sanctions List Updates, Regulations and Guidance, and so on). ACTION-LISTING SCOPE: this watches the published actions themselves.

NexGen Watch

Next Action Agent

westerly_palisade/next-action-by-dravara

Choose exactly one action from a supplied list. No 11-step plans. Read the default dataset. Set maxTotalChargeUsd above $0.03.

Dravara LLC

Action Scraper

appealing_jingle/action-scraper

Scrapes product data from Action.com including title, description, price, price description, category, URL, and image. Supports multiple languages, categories, sorting, pagination, and Apify proxy. Exports structured results to dataset (JSON, CSV).