# Zentra Tool Firewall (`zentrafoundry/zentra-agentops-tool-firewall`) Actor Gate AI agent tool calls before they run with policy, budget, permission, connector-scope, and side-effect decisions. - **URL**: https://apify.com/zentrafoundry/zentra-agentops-tool-firewall.md - **Developed by:** [Zentra](https://apify.com/zentrafoundry) (community) - **Categories:** AI, Agents, Developer tools - **Stats:** 2 total users, 1 monthly users, 100.0% runs succeeded, 0 bookmarks - **User rating**: No ratings yet ## Pricing Pay per event This Actor is paid per event. You are not charged for the Apify platform usage, but only a fixed price for specific events. Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-event ## What's an Apify Actor? Actors are a software tools running on the Apify platform, for all kinds of web data extraction and automation use cases. In Batch mode, an Actor accepts a well-defined JSON input, performs an action which can take anything from a few seconds to a few hours, and optionally produces a well-defined JSON output, datasets with results, or files in key-value store. In Standby mode, an Actor provides a web server which can be used as a website, API, or an MCP server. Actors are written with capital "A". ## How to integrate an Actor? If asked about integration, you help developers integrate Actors into their projects. You adapt to their stack and deliver integrations that are safe, well-documented, and production-ready. The best way to integrate Actors is as follows. In JavaScript/TypeScript projects, use official [JavaScript/TypeScript client](https://docs.apify.com/api/client/js.md): ```bash npm install apify-client ``` In Python projects, use official [Python client library](https://docs.apify.com/api/client/python.md): ```bash pip install apify-client ``` In shell scripts, use [Apify CLI](https://docs.apify.com/cli/docs.md): ````bash # MacOS / Linux curl -fsSL https://apify.com/install-cli.sh | bash # Windows irm https://apify.com/install-cli.ps1 | iex ```bash In AI frameworks, you might use the [Apify MCP server](https://docs.apify.com/platform/integrations/mcp.md). If your project is in a different language, use the [REST API](https://docs.apify.com/api/v2.md). For usage examples, see the [API](#api) section below. For more details, see Apify documentation as [Markdown index](https://docs.apify.com/llms.txt) and [Markdown full-text](https://docs.apify.com/llms-full.txt). # README ## Zentra Tool Firewall Gate AI agent tool calls before they run with policy, budget, permission, connector-scope, and side-effect decisions. ### Make agents earn more Stop unsafe and wasteful tool calls before they burn agent budget. This Actor produces a visible AgentOps artifact before it charges a pay-per-event item. It is built for AI workflow builders, agencies, enterprises and focuses on: Prevent unsafe or low-ROI tool calls.. ### Pricing Pricing model: `PAY_PER_EVENT`. - `policy-decision`: $0.0060 after one usable allow, deny, or human-review decision - `batch-policy-decision`: $0.0400 after one batch of policy decisions - `policy-pack`: $0.0900 after one compiled reusable policy pack The Actor writes a `preflightQuote.json` record before paid work and an `agentEarningsReport.json` record after the run. Dry runs produce a would-charge ledger without billing. ### Input Example ```json { "agentGoal": "Summarize GitHub issues and draft a Slack update.", "toolCall": { "toolName": "slack.messages.post", "sideEffects": [ "send", "write" ], "estimatedCostUsd": 0.03, "permissionLevel": "LIMITED_PERMISSIONS" }, "policyPack": { "maxCostUsdPerToolCall": 0.25, "requireHumanApprovalFor": [ "send", "write", "pay" ], "deniedTools": [ "*.delete" ] } } ```` ### Output Every successful run writes: - one default dataset item with the AgentOps artifact, - `agentEarningsReport.json` in the default key-value store, - `preflightQuote.json` in the default key-value store, - `report.md` with the buyer-facing earnings impact. ### Earnings Impact The report explains the estimated value created, the charged events, the dry-run would-charge ledger, and the value-to-charge multiple so buyers can see how the Actor helps an agent earn more, lose less, waste less, convert better, or operate with higher trust. # Actor input Schema ## `sourceMode` (type: `string`): Choose whether to run the built-in sample or process buyer-supplied sources. ## `startUrls` (type: `array`): Optional public URLs used as context for buyer-supplied runs. ## `maxItems` (type: `integer`): Maximum default dataset items to produce. ## `sourceIds` (type: `array`): Optional source identifiers shown in output evidence. ## `pricingEvents` (type: `array`): Optional visible pricing event names for the run report. ## `sinceLastRun` (type: `boolean`): Use Actor state to skip records whose dedupe keys were saved by earlier runs. ## `watchlistTerms` (type: `array`): Optional buyer terms used to explain matches and recurring monitoring. ## `webhookUrl` (type: `string`): Optional endpoint that receives a compact completion alert for scheduled runs. ## `includeSourceUrls` (type: `boolean`): Include source URL evidence in dataset output. ## `includeMatchReasons` (type: `boolean`): Include score reasons and buyer-value explanations in dataset output. ## `outputMode` (type: `string`): Choose the output shape for default Store runs. ## `actorSlug` (type: `string`): Optional actor slug echoed in run reports. ## `dryRun` (type: `boolean`): When enabled, produce output and a would-charge ledger without calling Apify charge events. ## `maxArtifacts` (type: `integer`): Maximum number of buyer-value artifacts to generate in this run. ## `agentGoal` (type: `string`): Goal, workflow, or buyer outcome the actor should protect or improve. ## `businessPurpose` (type: `string`): Why the agent, actor, workflow, connector, or dataset is being evaluated. ## `context` (type: `object`): Optional actor-specific fields such as tool calls, budgets, connector manifests, logs, dataset references, or listing copy. ## Actor input object example ```json { "sourceMode": "sample", "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" } } ], "maxItems": 1, "sourceIds": [ "AGENTOPS-SUITE", "APIFY-PPE" ], "pricingEvents": [], "sinceLastRun": false, "watchlistTerms": [], "includeSourceUrls": true, "includeMatchReasons": true, "outputMode": "sample-records", "actorSlug": "zentra-agentops-tool-firewall", "dryRun": false, "maxArtifacts": 1, "agentGoal": "Stop unsafe and wasteful tool calls before they burn agent budget.", "businessPurpose": "Prevent unsafe or low-ROI tool calls." } ``` # Actor output Schema ## `results` (type: `string`): No description # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = { "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" } } ] }; // Run the Actor and wait for it to finish const run = await client.actor("zentrafoundry/zentra-agentops-tool-firewall").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${run.defaultDatasetId}`); const { items } = await client.dataset(run.defaultDatasetId).listItems(); items.forEach((item) => { console.dir(item); }); // 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/js/docs ``` ## Python example ```python from apify_client import ApifyClient # Initialize the ApifyClient with your Apify API token # Replace '' with your token. client = ApifyClient("") # Prepare the Actor input run_input = { "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" }, }, ] } # Run the Actor and wait for it to finish run = client.actor("zentrafoundry/zentra-agentops-tool-firewall").call(run_input=run_input) # Fetch and print Actor results from the run's dataset (if there are any) print("💾 Check your data here: https://console.apify.com/storage/datasets/" + run["defaultDatasetId"]) for item in client.dataset(run["defaultDatasetId"]).iterate_items(): print(item) # 📚 Want to learn more 📖? Go to → https://docs.apify.com/api/client/python/docs/quick-start ``` ## CLI example ```bash 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 ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=zentrafoundry/zentra-agentops-tool-firewall", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "Zentra Tool Firewall", "description": "Gate AI agent tool calls before they run with policy, budget, permission, connector-scope, and side-effect decisions.", "version": "1.0", "x-build-id": "OE163hnd8C031P0AX" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/zentrafoundry~zentra-agentops-tool-firewall/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-zentrafoundry-zentra-agentops-tool-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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/zentrafoundry~zentra-agentops-tool-firewall/runs": { "post": { "operationId": "runs-sync-zentrafoundry-zentra-agentops-tool-firewall", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/zentrafoundry~zentra-agentops-tool-firewall/run-sync": { "post": { "operationId": "run-sync-zentrafoundry-zentra-agentops-tool-firewall", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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", "properties": { "sourceMode": { "title": "Source mode", "enum": [ "sample", "startUrls" ], "type": "string", "description": "Choose whether to run the built-in sample or process buyer-supplied sources.", "default": "sample" }, "startUrls": { "title": "Start URLs", "type": "array", "description": "Optional public URLs used as context for buyer-supplied runs.", "items": { "type": "object", "required": [ "url" ], "properties": { "url": { "type": "string", "title": "URL", "description": "Public page or API documentation URL used as run context." }, "userData": { "type": "object", "title": "User data", "description": "Optional source metadata attached to this URL." } } }, "default": [ { "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" } } ] }, "maxItems": { "title": "Maximum dataset items", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum default dataset items to produce.", "default": 1 }, "sourceIds": { "title": "Source IDs", "type": "array", "description": "Optional source identifiers shown in output evidence.", "default": [ "AGENTOPS-SUITE", "APIFY-PPE" ], "items": { "type": "string" } }, "pricingEvents": { "title": "Pricing events", "type": "array", "description": "Optional visible pricing event names for the run report.", "default": [], "items": { "type": "string" } }, "sinceLastRun": { "title": "Only new records", "type": "boolean", "description": "Use Actor state to skip records whose dedupe keys were saved by earlier runs.", "default": false }, "watchlistTerms": { "title": "Watchlist terms", "type": "array", "description": "Optional buyer terms used to explain matches and recurring monitoring.", "default": [], "items": { "type": "string" } }, "webhookUrl": { "title": "Webhook URL", "type": "string", "description": "Optional endpoint that receives a compact completion alert for scheduled runs." }, "includeSourceUrls": { "title": "Include source URLs", "type": "boolean", "description": "Include source URL evidence in dataset output.", "default": true }, "includeMatchReasons": { "title": "Include match reasons", "type": "boolean", "description": "Include score reasons and buyer-value explanations in dataset output.", "default": true }, "outputMode": { "title": "Output mode", "enum": [ "sample-records", "buyer-ready-records" ], "type": "string", "description": "Choose the output shape for default Store runs.", "default": "sample-records" }, "actorSlug": { "title": "Actor slug", "type": "string", "description": "Optional actor slug echoed in run reports.", "default": "zentra-agentops-tool-firewall" }, "dryRun": { "title": "Dry run", "type": "boolean", "description": "When enabled, produce output and a would-charge ledger without calling Apify charge events.", "default": false }, "maxArtifacts": { "title": "Maximum artifacts", "minimum": 1, "maximum": 25, "type": "integer", "description": "Maximum number of buyer-value artifacts to generate in this run.", "default": 1 }, "agentGoal": { "title": "Agent goal", "type": "string", "description": "Goal, workflow, or buyer outcome the actor should protect or improve.", "default": "Stop unsafe and wasteful tool calls before they burn agent budget." }, "businessPurpose": { "title": "Business purpose", "type": "string", "description": "Why the agent, actor, workflow, connector, or dataset is being evaluated.", "default": "Prevent unsafe or low-ROI tool calls." }, "context": { "title": "Context", "type": "object", "description": "Optional actor-specific fields such as tool calls, budgets, connector manifests, logs, dataset references, or listing copy." } } }, "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 } } } } } } } } } } ```