# Google Ads MCP Server (Read & Write) (`ankitsharma_29/google-ads-mcp`) Actor MCP server exposing 60+ Google Ads tools: campaign creation, reporting, optimization, and deep analytics for agencies and technical advertisers. Bring your own Google Ads credentials - **URL**: https://apify.com/ankitsharma\_29/google-ads-mcp.md - **Developed by:** [Ankit Sharma](https://apify.com/ankitsharma_29) (community) - **Categories:** Marketing, AI, Developer tools - **Stats:** 1 total users, 0 monthly users, 100.0% runs succeeded, 0 bookmarks - **User rating**: No ratings yet ## Pricing from $80.00 / 1,000 results This Actor is paid per event and usage. You are charged both the fixed price for specific events and for Apify platform usage. 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 ## Google Ads MCP Server A hosted MCP (Model Context Protocol) server that gives AI agents **full control** over your Google Ads account — create campaigns, edit ads, optimize bids, analyze performance, and auto-fix issues, all through natural language. **68 tools** across 8 categories: Create, Read, Update, Extensions, Analysis, Optimization, Deep Analytics, and Auto-Actions. --- ### 🟢 How it works (hosted — no server needed) This Actor runs the MCP server for you in **Standby mode**. Connect any MCP client to one URL — no Docker, no VPS, no setup. **Endpoint (after you start the Actor):** ```` https://.apify.actor/mcp ```` Add it to **Claude Desktop, Cursor, or Cline** as a **Streamable HTTP** MCP server, then just ask in plain English: - *"List my campaigns."* - *"Create a search campaign with a $20/day budget."* - *"Which keywords are wasting spend?"* --- ### 🔑 What you provide — your own Google Ads credentials This is a **bring-your-own-credentials** tool. Enter these in the Actor's **Input** (they stay private to your run): | Field | Where to get it | |-------|-----------------| | **Client ID** | Google Cloud Console → APIs & Services → Credentials → OAuth 2.0 Client | | **Client Secret** | Same OAuth client as above | | **Developer Token** | Google Ads → Tools → API Center (needs a **Manager / MCC** account) | | **Refresh Token** | Generated once via OAuth (see below) | | **Login Customer ID** *(optional)* | Your MCC customer ID, digits only, no dashes | > ⚠️ You need a Google Ads **Manager (MCC) account** and an **approved developer token**. A plain Google Ads user without these cannot use this tool. It is built for **agencies and technical advertisers**. #### Step-by-step credential setup 1. **Create a Google Cloud project** → enable the **Google Ads API**. 2. **OAuth consent screen** → **User type: External** → add your Google account as a Test user → then **PUBLISH the app ("In production")**. - 🔴 **Critical:** in *Testing* mode, your refresh token **expires after 7 days**. Setting the app to **In production** makes it permanent. You do **not** need Google to fully "verify" the app — just click through the unverified-app warning once. 3. **Create OAuth credentials** → *OAuth client ID* → **Web application** → redirect URI `http://localhost:8080/` → copy the **Client ID** + **Secret**. 4. **Get a developer token** in Google Ads → Tools → **API Center** (requires an MCC account; may take a day or two to approve). 5. **Generate a refresh token** — sign in with the Google account that has access to your ad account, approve, and copy the printed refresh token. 6. **Paste all values into the Actor Input** and start it. --- ### 💵 Pricing Pay-per-usage: **$0.08 per tool call**, plus Apify platform usage for the running server. No monthly commitment — cancel anytime. --- ### 🧰 Tools (highlights) #### CREATE | Tool | Description | |------|-------------| | `create_campaign_budget` | Create a daily budget | | `create_search_campaign` | Create a new search campaign linked to a budget | | `create_ad_group` | Create an ad group inside a campaign with CPC bid | | `add_keywords` | Add keywords with match types: EXACT, PHRASE, BROAD | | `create_responsive_search_ad` | Create RSA with up to 15 headlines and 4 descriptions | #### READ / DISCOVER | Tool | Description | |------|-------------| | `list_accessible_customers` | List all Google Ads account IDs you can manage | | `search_ads` | Execute any GAQL query for custom data retrieval | | `get_campaign_performance` | Campaign metrics: impressions, clicks, cost, CTR, conversions | | `get_ad_performance` | Ad-level metrics (includes policy status and disapprovals) | | `get_search_terms` | See the actual search terms that triggered your ads | | `generate_keyword_ideas` | Native Keyword Planner: search volumes, competitor keywords, CPCs | #### UPDATE | Tool | Description | |------|-------------| | `update_campaign_status` | Set campaign to ENABLED, PAUSED, or REMOVED | | `update_campaign_budget_amount` | Change daily budget amount | | `update_ad_group_bid` | Change Max CPC bid on an ad group | | `update_responsive_search_ad` | Edit headlines/descriptions of an existing RSA | | `update_keyword_bid` | Change CPC bid on a specific keyword | | `remove_keyword` | Delete a keyword from an ad group | #### EXTENSIONS | Tool | Description | |------|-------------| | `add_negative_keywords` | Block irrelevant search terms at campaign level | | `set_ad_schedule` | Only show ads during specific hours | | `add_call_extension` | Add a phone number to ads for call leads | #### ANALYSIS | Tool | Description | |------|-------------| | `analyze_wasted_spend` | Find keywords burning money with zero conversions | | `analyze_keyword_performance` | Categorize keywords: Top / Average / Underperformers | | `analyze_search_terms` | Find negative keyword opportunities | | `analyze_time_performance` | Find peak and dead hours for ad scheduling | | `analyze_geo_performance` | See which locations convert vs. waste money | #### OPTIMIZATION | Tool | Description | |------|-------------| | `get_optimization_score` | Account health score (0–100) with an action plan | | `analyze_budget_efficiency` | Evaluate ROI and recommend budget reallocation | | `analyze_ad_copy_performance` | Compare ad variations and find winners/losers | | `generate_account_report` | Full account health report in one call | | `auto_create_campaign` | All-in-one: builds an entire campaign from scratch (PAUSED) | #### DEEP ANALYTICS | Tool | Description | |------|-------------| | `deep_campaign_analysis` | Z-tests, CPA trends, and statistical proof per campaign | | `anomaly_detector` | Real-time disaster shield using rolling Z-scores | | `quality_score_doctor` | Diagnoses root causes of high CPCs | | `ad_fatigue_detector` | Linear regression to catch dying ads before CTR drops | | `budget_efficiency_curve` | Finds the inflection point of diminishing returns | | `keyword_profitability_matrix` | Scores keywords by profit potential | #### AUTO-ACTIONS | Tool | Description | |------|-------------| | `auto_pause_wasted_keywords` | Pause keywords exceeding a waste threshold | | `auto_adjust_bids` | +15% on top performers, −30% on underperformers | | `auto_add_negative_keywords` | Add negatives from wasted search terms | --- ### 💬 Example prompts **Campaign management** - "Create a new campaign named 'Product Launch' with a budget of $10/day." - "Pause campaign 'Summer Sale' in account 1234567890." **One-shot campaign builder** - "Build a complete campaign for my plumbing business at mysite.com with a $25/day budget and a call extension at 555-1234." **Discovery & Keyword Planner** - "What keywords is www.competitor.com using?" - "What is the search volume and CPC for 'emergency plumber'?" **Optimization & analysis** - "What's my account optimization score?" - "Show me wasted spend in the last 30 days." - "Which locations are wasting my money?" **Deep analytics** - "Run a deep campaign analysis." - "Are any of my ads suffering from fatigue?" - "Generate a keyword profitability matrix." **Auto-actions** - "Auto-pause all keywords that spent over $5 with zero conversions." - "Auto-adjust bids based on performance." # Actor input Schema ## `GOOGLE_ADS_CLIENT_ID` (type: `string`): OAuth2 Client ID from your Google Cloud project. ## `GOOGLE_ADS_CLIENT_SECRET` (type: `string`): OAuth2 Client Secret from your Google Cloud project. ## `GOOGLE_ADS_DEVELOPER_TOKEN` (type: `string`): Developer token from your Google Ads Manager (MCC) account. ## `GOOGLE_ADS_REFRESH_TOKEN` (type: `string`): Refresh token authorizing access to your Google Ads account. Generate once via the OAuth consent flow. ## `GOOGLE_ADS_LOGIN_CUSTOMER_ID` (type: `string`): Your Manager account customer ID, digits only, no dashes. Optional. ## Actor input object example ```json {} ```` # Actor output Schema ## `events` (type: `string`): Every Google Ads MCP tool call: timestamp, tool, and status. # API You can run this Actor programmatically using our API. Below are code examples in JavaScript, Python, and CLI, as well as the OpenAPI specification and MCP server setup. ## JavaScript example ```javascript import { ApifyClient } from 'apify-client'; // Initialize the ApifyClient with your Apify API token // Replace the '' with your token const client = new ApifyClient({ token: '', }); // Prepare Actor input const input = {}; // Run the Actor and wait for it to finish const run = await client.actor("ankitsharma_29/google-ads-mcp").call(input); // Fetch and print Actor results from the run's dataset (if any) console.log('Results from dataset'); console.log(`💾 Check your data here: https://console.apify.com/storage/datasets/${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 = {} # Run the Actor and wait for it to finish run = client.actor("ankitsharma_29/google-ads-mcp").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 '{}' | apify call ankitsharma_29/google-ads-mcp --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=ankitsharma_29/google-ads-mcp", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "Google Ads MCP Server (Read & Write)", "description": "MCP server exposing 60+ Google Ads tools: campaign creation, reporting, optimization, and deep analytics for agencies and technical advertisers. Bring your own Google Ads credentials", "version": "0.1", "x-build-id": "zJmryiFiNW3tRejg2" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/ankitsharma_29~google-ads-mcp/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-ankitsharma_29-google-ads-mcp", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/ankitsharma_29~google-ads-mcp/runs": { "post": { "operationId": "runs-sync-ankitsharma_29-google-ads-mcp", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/ankitsharma_29~google-ads-mcp/run-sync": { "post": { "operationId": "run-sync-ankitsharma_29-google-ads-mcp", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "GOOGLE_ADS_CLIENT_ID": { "title": "Google Ads OAuth Client ID", "type": "string", "description": "OAuth2 Client ID from your Google Cloud project." }, "GOOGLE_ADS_CLIENT_SECRET": { "title": "Google Ads OAuth Client Secret", "type": "string", "description": "OAuth2 Client Secret from your Google Cloud project." }, "GOOGLE_ADS_DEVELOPER_TOKEN": { "title": "Google Ads Developer Token", "type": "string", "description": "Developer token from your Google Ads Manager (MCC) account." }, "GOOGLE_ADS_REFRESH_TOKEN": { "title": "OAuth Refresh Token", "type": "string", "description": "Refresh token authorizing access to your Google Ads account. Generate once via the OAuth consent flow." }, "GOOGLE_ADS_LOGIN_CUSTOMER_ID": { "title": "Login Customer ID (MCC)", "type": "string", "description": "Your Manager account customer ID, digits only, no dashes. Optional." } } }, "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 } } } } } } } } } } ```