# Google Search MCP Server (`viralanalyzer/mcp-google-search`) Actor Expose Google Search to your AI Agents (Claude Desktop, Cursor) as a standardized Model Context Protocol (MCP) Server via SSE HTTP, with Pay-Per-Event billing. - **URL**: https://apify.com/viralanalyzer/mcp-google-search.md - **Developed by:** [viralanalyzer](https://apify.com/viralanalyzer) (community) - **Categories:** AI - **Stats:** 2 total users, 1 monthly users, 0.0% runs succeeded, NaN bookmarks - **User rating**: No ratings yet ## Pricing Pay per usage This Actor is paid per platform usage. The Actor is free to use, and you only pay for the Apify platform usage, which gets cheaper the higher subscription plan you have. Learn more: https://docs.apify.com/platform/actors/running/actors-in-store#pay-per-usage ## 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 Search MCP Server Scraper Connect your local or cloud AI agents (like **Claude Desktop**, **Cursor**, **Windsurf**, or **LangChain**) directly to real-time, organic Google Search results using the standardized **Model Context Protocol (MCP)** via high-performance SSE (Server-Sent Events) HTTP. Fully integrated with Apify's residential/datacenter proxy pool and powered by a highly cost-efficient Pay-Per-Event (PPE) model. --- ### 🇧🇷 Português #### Funcionalidades (Features) * **Compatibilidade MCP Nativa**: Desenvolvido sobre o SDK oficial da Anthropic (`@modelcontextprotocol/sdk`). * **Operação SSE HTTP**: Roda como um microserviço HTTP persistente na nuvem Apify pronto para conexões SSE. * **Busca Orgânica Inteligente**: Extrai títulos, links reais diretos e descrições (snippets) de resultados do Google Search sem necessidade de chaves de API pagas. * **Segurança de IP (Anti-Bot)**: Utiliza a rotação automática de IPs de proxy da Apify (incluindo residencial como fallback) para evitar CAPTCHAs ou bloqueios. * **Precificação Pay-Per-Event (PPE)**: Você só paga frações de centavos por pesquisa realizada na nuvem, com custo operacional de infraestrutura zero para o editor do portfólio. * **Modo de Busca Direta (Autoteste)**: Modos selecionáveis no input para buscas síncronas de autoteste da plataforma. #### Como Conectar seu Agente de IA (Claude Desktop) Para configurar este Actor como ferramenta no seu **Claude Desktop**, adicione as seguintes linhas no seu arquivo de configuração `claude_desktop_config.json`: ```json { "mcpServers": { "google-search": { "url": "https://api.apify.com/v2/acts/viralanalyzer~mcp-google-search/runs?token=SEU_APIFY_TOKEN", "method": "sse" } } } ```` *** ### 🇺🇸 English #### Features - **Native MCP Compatibility**: Fully compliant with Anthropic's official Model Context Protocol server specification. - **SSE HTTP Server**: Runs as a persistent cloud daemon on Apify's serverless infrastructure, exposing SSE (Server-Sent Events) endpoints. - **Organic Search Extraction**: Scrapes titles, direct URLs, and snippets from Google Search without requiring paid external search API keys. - **Anti-Bot Resilience**: Seamlessly integrates Apify’s proxy rotation (datacenter/residential) to bypass captchas and scraping blocks. - **Pay-Per-Event (PPE) Pricing**: Charged transparently per search query triggered, bypassing the typical 14-day free trial limits. - **Direct Mode**: Standard execution mode returning dataset items directly, enabling easy automated platform testing. #### Configuring Claude Desktop / Cursor Add the following connection configuration block to your local `claude_desktop_config.json` to empower your local AI with search capabilities: ```json { "mcpServers": { "google-search": { "url": "https://api.apify.com/v2/acts/viralanalyzer~mcp-google-search/runs?token=YOUR_APIFY_TOKEN", "method": "sse" } } } ``` *** ### 💸 Pricing (Precificação) - **Search Query Execution**: Charged at **$0.05 USD** per successful search query event triggered (`search-query` event). - **Owner Skip**: Free execution for publisher owner credentials. *** ### 🔧 Input Parameter Schema | Field | Type | Description | Default | |---|---|---|---| | `mode` | `string` | Operation mode (`mcp` for daemon server, `direct` for single search). | `"mcp"` | | `query` | `string` | Organic search query (used in direct search mode / autotests). | `"Apify platform"` | | `maxResults` | `integer` | Number of organic results to extract (1-50). | `10` | | `proxyConfiguration` | `object` | Proxy server options (residential recommended for massive runs). | `{ "useApifyProxy": true }` | *** ### 📊 Output Schema (Direct Mode) A sample JSON output from direct search execution: ```json [ { "position": 1, "title": "Apify: Web Scraping and Automation Platform", "url": "https://apify.com/", "description": "Apify is a cloud web scraping and data extraction platform. Build, run, and share serverless web scrapers and automation tools.", "scrapedAt": "2026-05-24T00:00:00.000Z" } ] ``` # Actor input Schema ## `mode` (type: `string`): Choose 'mcp' to run a persistent Model Context Protocol (MCP) server for AI agents, or 'direct' for a single direct search (highly recommended for Apify automated quality tests). ## `query` (type: `string`): The search query to execute immediately when Operation Mode is 'direct'. Used primarily for automated autotests. ## `maxResults` (type: `integer`): Maximum number of search results to return per query. ## `proxyConfiguration` (type: `object`): Proxy configuration. Google search requests require reliable proxies to avoid blockages. ## Actor input object example ```json { "mode": "mcp", "query": "Apify platform", "maxResults": 10, "proxyConfiguration": { "useApifyProxy": true } } ``` # Actor output Schema ## `results` (type: `string`): Dataset containing all organic search results. Each item follows the dataset schema. # 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 = { "query": "Apify platform" }; // Run the Actor and wait for it to finish const run = await client.actor("viralanalyzer/mcp-google-search").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 = { "query": "Apify platform" } # Run the Actor and wait for it to finish run = client.actor("viralanalyzer/mcp-google-search").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 '{ "query": "Apify platform" }' | apify call viralanalyzer/mcp-google-search --silent --output-dataset ``` ## MCP server setup ```json { "mcpServers": { "apify": { "command": "npx", "args": [ "mcp-remote", "https://mcp.apify.com/?tools=viralanalyzer/mcp-google-search", "--header", "Authorization: Bearer " ] } } } ``` ## OpenAPI specification ```json { "openapi": "3.0.1", "info": { "title": "Google Search MCP Server", "description": "Expose Google Search to your AI Agents (Claude Desktop, Cursor) as a standardized Model Context Protocol (MCP) Server via SSE HTTP, with Pay-Per-Event billing.", "version": "1.0", "x-build-id": "Jh9DnAGa8rltU48rZ" }, "servers": [ { "url": "https://api.apify.com/v2" } ], "paths": { "/acts/viralanalyzer~mcp-google-search/run-sync-get-dataset-items": { "post": { "operationId": "run-sync-get-dataset-items-viralanalyzer-mcp-google-search", "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": { "$ref": "#/components/schemas/inputSchema" } } } }, "parameters": [ { "name": "token", "in": "query", "required": true, "schema": { "type": "string" }, "description": "Enter your Apify token here" } ], "responses": { "200": { "description": "OK" } } } }, "/acts/viralanalyzer~mcp-google-search/runs": { "post": { "operationId": "runs-sync-viralanalyzer-mcp-google-search", "x-openai-isConsequential": false, "summary": "Executes an Actor and returns information about the initiated run in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": { "$ref": "#/components/schemas/runsResponseSchema" } } } } } } }, "/acts/viralanalyzer~mcp-google-search/run-sync": { "post": { "operationId": "run-sync-viralanalyzer-mcp-google-search", "x-openai-isConsequential": false, "summary": "Executes an Actor, waits for completion, and returns the OUTPUT from Key-value store in response.", "tags": [ "Run Actor" ], "requestBody": { "required": true, "content": { "application/json": { "schema": { "$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": "Operation Mode", "enum": [ "mcp", "direct" ], "type": "string", "description": "Choose 'mcp' to run a persistent Model Context Protocol (MCP) server for AI agents, or 'direct' for a single direct search (highly recommended for Apify automated quality tests).", "default": "mcp" }, "query": { "title": "Direct Search Query", "type": "string", "description": "The search query to execute immediately when Operation Mode is 'direct'. Used primarily for automated autotests.", "default": "Apify platform" }, "maxResults": { "title": "Maximum Search Results", "minimum": 1, "maximum": 50, "type": "integer", "description": "Maximum number of search results to return per query.", "default": 10 }, "proxyConfiguration": { "title": "Proxy Configuration", "type": "object", "description": "Proxy configuration. Google search requests require reliable proxies to avoid blockages.", "default": { "useApifyProxy": true } } } }, "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 } } } } } } } } } } ```