# MCP: Cross-Platform Ad Intelligence - Meta/Google/TikTok (`seibs.co/mcp-ad-library-intel`) Actor MCP server for ad-library-intel. AI-agent tools: search\_advertiser\_ads, get\_active\_creatives, compare\_competitors, track\_new\_creatives, search\_ads\_by\_keyword across Meta + Google + TikTok ad archives. x402 (USDC on Base) and Skyfire ready. For performance marketers, DTC, agencies. - **URL**: https://apify.com/seibs.co/mcp-ad-library-intel.md - **Developed by:** [Seibs.co](https://apify.com/seibs.co) (community) - **Categories:** MCP servers, Marketing, Developer tools - **Stats:** 1 total users, 0 monthly users, 0.0% runs succeeded, 0 bookmarks - **User rating**: No ratings yet ## Pricing $5.00 / 1,000 mcp tool calls 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 ## MCP: Cross-Platform Ad Intelligence (Meta + Google + TikTok) > **TL;DR:** An MCP server that gives any AI agent five tools to research competitor ads across **Meta Ad Library + Google Ads Transparency Center + TikTok** in one call: `search_advertiser_ads`, `get_active_creatives`, `compare_competitors`, `track_new_creatives`, `search_ads_by_keyword`. It wraps the upstream [`ad-library-intel`](https://apify.com/seibs.co/ad-library-intel) actor, reshapes its dataset into small, deterministic, agent-ready JSON, and is **x402 (USDC on Base) + Skyfire ready** for token-less agentic payments. ### How it works This is a thin, AI-agent-facing wrapper. Each tool call invokes the upstream `seibs.co/ad-library-intel` actor with the right mode/inputs, then returns a clean `{ ok, count, items, summary, error }` envelope - no megabyte media blobs, no nested archive cruft. Upstream PPE events (ad_record, creative_analysis, advertiser_tracking) pass through to the same run, plus a flat `$0.005` `mcp_tool_call` per invocation. ### Modes | Mode | What it does | |---|---| | `list_tools` (default) | Emit the tool catalog (names, descriptions, JSON schemas) + the agentic-payment descriptor. Free - no charge. | | `call_tool` | Invoke one tool. Requires `tool` + `args`. | | `batch` | Invoke a list of `{tool, args}` calls (max 10) in one run. | ### Tools | Tool | Use for | |---|---| | `search_advertiser_ads` | A competitor's creatives across all three platforms - format, copy, CTA, run-dates, active-vs-stopped, hook/offer tags. | | `get_active_creatives` | Only the currently-running creatives - what a competitor is spending on right now. | | `compare_competitors` | A cross-advertiser comparison: per-advertiser active/stopped, format lean, top angles, shared angles. | | `track_new_creatives` | An advertiser's current set newest-first (the snapshot to diff; schedule the upstream actor for an automatic delta). | | `search_ads_by_keyword` | Discover ads by keyword/term - which advertisers run a given offer/angle. | ### Call it ```python from apify_client import ApifyClient client = ApifyClient("") run = client.actor("seibs.co/mcp-ad-library-intel").call(run_input={ "mode": "call_tool", "tool": "compare_competitors", "args": {"advertisers": ["Nike", "Adidas"], "platforms": ["meta", "google", "tiktok"], "country": "US"} }) for item in client.dataset(run["defaultDatasetId"]).iterate_items(): print(item) ```` ### Agentic payments (x402 + Skyfire) The tool catalog advertises an agentic-payment descriptor so AI agents know they can pay per call with no pre-provisioned token. Enable rails via actor env vars: `X402_ENABLED=1` + `X402_PAY_TO_ADDRESS` (USDC on Base), and/or `SKYFIRE_ENABLED=1` + `SKYFIRE_SELLER_ID`. Settlement is handled by Apify's platform when MCP monetization is enabled; this server just advertises the capability. ### Pricing Flat **$0.005 per `mcp_tool_call`** + upstream `ad-library-intel` pass-through (ad\_record $0.004 / creative\_analysis $0.008 / advertiser\_tracking $0.010). `list_tools` is free. ### Related Upstream actor: [`ad-library-intel`](https://apify.com/seibs.co/ad-library-intel). Part of the Seibs.co intelligence portfolio. # Actor input Schema ## `mode` (type: `string`): list\_tools = emit the MCP tool catalog (free). call\_tool = invoke one tool (requires 'tool' + 'args'). batch = invoke a list of {tool, args} calls. ## `tool` (type: `string`): Required when mode=call\_tool. One of: search\_advertiser\_ads, get\_active\_creatives, compare\_competitors, track\_new\_creatives, search\_ads\_by\_keyword. ## `args` (type: `object`): Arguments for the selected tool. Example for search\_advertiser\_ads: {"advertiser": "Allbirds", "platforms": \["meta","google","tiktok"], "country": "US"}. ## `calls` (type: `array`): Required when mode=batch. Each entry is an object with 'tool' and 'args'. Example: \[{"tool": "search\_advertiser\_ads", "args": {"advertiser": "Nike"}}, {"tool": "compare\_competitors", "args": {"advertisers": \["Nike","Adidas"]}}]. Max 10 calls per run. ## Actor input object example ```json { "mode": "list_tools", "tool": "search_advertiser_ads", "args": { "advertiser": "Allbirds", "platforms": [ "meta", "google", "tiktok" ], "country": "US" }, "calls": [] } ``` # 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 = { "mode": "list_tools", "args": { "advertiser": "Allbirds", "platforms": [ "meta", "google", "tiktok" ], "country": "US" } }; // Run the Actor and wait for it to finish const run = await client.actor("seibs.co/mcp-ad-library-intel").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 = { "mode": "list_tools", "args": { "advertiser": "Allbirds", "platforms": [ "meta", "google", "tiktok", ], "country": "US", }, } # Run the Actor and wait for it to finish run = client.actor("seibs.co/mcp-ad-library-intel").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 '{ "mode": "list_tools", "args": { "advertiser": "Allbirds", "platforms": [ "meta", "google", "tiktok" ], "country": "US" } }' | apify call seibs.co/mcp-ad-library-intel --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=seibs.co/mcp-ad-library-intel", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "MCP: Cross-Platform Ad Intelligence - Meta/Google/TikTok", "description": "MCP server for ad-library-intel. AI-agent tools: search_advertiser_ads, get_active_creatives, compare_competitors, track_new_creatives, search_ads_by_keyword across Meta + Google + TikTok ad archives. x402 (USDC on Base) and Skyfire ready. For performance marketers, DTC, agencies.", "version": "0.1", "x-build-id": "jxhdDiLi94umtXRkI" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/seibs.co~mcp-ad-library-intel/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-seibs.co-mcp-ad-library-intel", "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/seibs.co~mcp-ad-library-intel/runs": { "post": { "operationId": "runs-sync-seibs.co-mcp-ad-library-intel", "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/seibs.co~mcp-ad-library-intel/run-sync": { "post": { "operationId": "run-sync-seibs.co-mcp-ad-library-intel", "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": [ "mode" ], "properties": { "mode": { "title": "Mode", "enum": [ "list_tools", "call_tool", "batch" ], "type": "string", "description": "list_tools = emit the MCP tool catalog (free). call_tool = invoke one tool (requires 'tool' + 'args'). batch = invoke a list of {tool, args} calls.", "default": "list_tools" }, "tool": { "title": "Tool name", "enum": [ "search_advertiser_ads", "get_active_creatives", "compare_competitors", "track_new_creatives", "search_ads_by_keyword" ], "type": "string", "description": "Required when mode=call_tool. One of: search_advertiser_ads, get_active_creatives, compare_competitors, track_new_creatives, search_ads_by_keyword.", "default": "search_advertiser_ads" }, "args": { "title": "Tool arguments (JSON object)", "type": "object", "description": "Arguments for the selected tool. Example for search_advertiser_ads: {\"advertiser\": \"Allbirds\", \"platforms\": [\"meta\",\"google\",\"tiktok\"], \"country\": \"US\"}." }, "calls": { "title": "Batch calls", "maxItems": 10, "type": "array", "description": "Required when mode=batch. Each entry is an object with 'tool' and 'args'. Example: [{\"tool\": \"search_advertiser_ads\", \"args\": {\"advertiser\": \"Nike\"}}, {\"tool\": \"compare_competitors\", \"args\": {\"advertisers\": [\"Nike\",\"Adidas\"]}}]. Max 10 calls per run.", "default": [] } } }, "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 } } } } } } } } } } ```