You can access the Zentra Tool Firewall 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 Integrations settings in Apify Console.

Python

JavaScript

CLI

OpenAPI

HTTP

MCP

$echo '{
<  "startUrls": [
<    {
<      "url": "https://zentraforge.store",
<      "sourceId": "AGENTOPS-SUITE",
<      "userData": {
<        "sourceId": "AGENTOPS-SUITE"
<      }
<    },
<    {
<      "url": "https://docs.apify.com/platform/actors/publishing",
<      "sourceId": "APIFY-PUBLISH",
<      "userData": {
<        "sourceId": "APIFY-PUBLISH"
<      }
<    },
<    {
<      "url": "https://docs.apify.com/platform/actors/publishing/monetize/pay-per-event",
<      "sourceId": "APIFY-PPE",
<      "userData": {
<        "sourceId": "APIFY-PPE"
<      }
<    }
<  ]
<}' |
<apify call zentrafoundry/zentra-agentops-tool-firewall --silent --output-dataset

AI Agent Tool Firewall for Apify Actors and MCP Workflows API through CLI

The Apify CLI is the official tool that allows you to use Zentra Tool Firewall locally, providing convenience functions and automatic retries on errors.

Install Apify CLI

Using installation script (macOS/Linux):

$curl -fsSL https://apify.com/install-cli.sh | bash

Using installation script (Windows):

$irm https://apify.com/install-cli.ps1 | iex

Using Homebrew:

$brew install apify-cli

Using npm:

$npm install -g apify-cli

Other API clients include:

Zentra Tool Firewall API in Python

Zentra Tool Firewall API in JavaScript

Zentra Tool Firewall OpenAPI definition

Zentra Tool Firewall API

Zentra MCP Connector Policy Linter

zentrafoundry/zentra-mcp-connector-policy-linter

Audit connector tool manifests and generate least-privilege policy packs for agent workflows.

Zentra

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

A2A Policy Enforcement

knowing_yucca/meok-agent-policy-enforce

Pre-execution policy gate for agent decisions with signed allow / deny evidence.

MEOK AI

Ads Account Connector

ryanclinton/ads-account-connector

Ryan Clinton

Competitive Intelligence MCP Server

onetapstudio/competitive-intelligence-mcp

Monitor competitors across their website, job postings, social media, and tech stack from one tool call. Detect changes, compare up to 5 competitors side by side, and identify what technologies they use.

Adam Hartman

Zentra Tool Passport Generator

zentrafoundry/zentra-tool-passport-generator

Generate trust passports and agent cards for Actors, MCP tools, and automation connectors.

Zentra

Dataset Result Gate

vittuhy/dataset-result-gate

Conditional pipeline gate. Fails if the previous actor's dataset is empty, succeeds if it has results — stopping unnecessary downstream runs before they start.

Vít Tuhý

AI Model Comparison

onescales/ai-model-comparison

Compare responses from multiple AI models side by side and let AI analyze them to deliver the single best answer.

One Scales

282

5.0

Actor A/B Tester — Compare Two Actors Side by Side

ryanclinton/actor-ab-tester

Run two Apify actors with identical input in parallel and compare results side by side. Measures result count, field coverage, execution speed, and compute cost. Declares a winner with percentage diffs. Returns JSON/CSV/Excel.

Ryan Clinton