google-searchserpweb-searchdata-extractionmcp
Queries Google SERPs, AI answers, news, shopping, products, events, and videos as structured JSON over MCP.
Quick Install
Automated & IDE SetupCopy the AI prompt to install this server into Claude Code, Cursor, or another agent — or use 1-click editor setup below.
Not yet automatically verified
We haven't yet run this listing's install command through our automated sandbox check. This isn't a red flag — we're steadily working through the catalog.
Manual Client & Custom JSON ConfigExpand JSON ▾
Client Config & Setup
Configure Environment Variables (API Keys, Tokens, Options):
Add required secrets below — values are included directly in the generated snippet so you can copy and paste with confidence.
Quick Add:
Choose your client or environment
Target File:
💡 Paste the JSON block into your client's configuration file under mcpServers, then restart the application.
Overview
Use cases
Search Google and extract organic results with AI Overview data
Compare shopping offers, prices, merchants, and product ratings
Collect current news articles and source metadata
Retrieve event details, ticket links, and venue information
Find short videos with platform and creator metadata
Key features
Structured Google SERP JSON
AI Overview and AI Mode responses
People Also Ask and follow-up tokens
News, shopping, products, events, and video results
Streamable HTTP access
npm and PyPI stdio launchers
Capabilities & Tool Schemas (10)
Inspect callable tools, capabilities, and parameters exposed to AI agents by HasData Google Search (SERP).
hasdata_google_serp_ai_mode_getAiModeResponseThe conversational response text, cited source links, subtopic breakdowns, follow-up suggestions, and a subsequentRequestToken for multi-turn continuation. 10 credits a call
hasdata_google_serp_ai_overview_getAiOverviewResponseThe AI-generated answer text, referenced source URLs, and expanded subtopic sections. 10 credits a call
hasdata_google_serp_events_getEventInformationEvent title, start date/time, venue name and address, ticket/source links, description, and thumbnail. 10 credits a call
hasdata_google_serp_immersive_product_getImmersive_e29f691177Multi-store offers (merchant, price, shipping, condition, URL), product specs, images, ratings, and the nextPageToken. 10 credits a call
hasdata_google_serp_news_getGoogleNewsArticle title, snippet, source publisher, published date, thumbnail, and URL, plus tokens for navigating topics, sub-sections, and story clusters. 10 credits a call
hasdata_google_serp_product_getProductInformationProduct title, images, price, ratings, specs, merchant offers (seller, shipping, condition, total price), and review text depending on searchType. 10 credits a call
How HasData Google Search (SERP) works
What HasData Google Search (SERP) does
HasData Google Search (SERP) MCP server provides read-only access to parsed Google search results through MCP. It covers standard search pages as well as specialized result types, returning structured fields instead of requiring an agent to interpret an HTML page.
The standard SERP tools can return organic listings, advertisements, knowledge graph data, related searches, People Also Ask entries, local results, featured snippets, and AI Overview information. Separate tools handle Google AI Mode, Google News, Shopping, product details, immersive product pages, events, and short videos.
This fits agents that need current search data for research, comparison workflows, content analysis, event discovery, or product lookup. It does not require a Google Cloud project or Programmable Search Engine configuration.
How it works
The hosted endpoint uses streamable HTTP:
https://mcp.hasdata.com/mcp?apis=google_serp
Requests authenticate with the x-api-key header. A SERP response can include tokens for follow-up operations. For example, People Also Ask entries can provide an AI Overview page token, and shopping results can provide a token for expanding a product into a fuller multi-store view. AI Mode can return a subsequent request token for continuing a conversation.
Responses are JSON objects containing fields appropriate to the selected search type. AI-related tools return generated text with source references, while news and video tools return result metadata such as titles, publishers or platforms, dates, thumbnails, and URLs.
Setup and configuration
Create a HasData API key from the HasData dashboard and send it in the x-api-key header. The hosted URL is the simplest setup for clients that support remote streamable HTTP MCP servers.
The README documents configurations for Claude Code, Claude Desktop, Cursor, Windsurf, Cline, VS Code, and Gemini CLI. Claude Desktop uses a local stdio launcher because its documented configuration loads local servers; the npm package @hasdata/google-search-mcp or the PyPI package hasdata-google-search-mcp can provide that launcher. Clients with OAuth support can add the remote URL as a connector instead of placing the key in a configuration file.
No other cloud service configuration is required. Usage consumes HasData credits, and the README states that the free tier includes 1,000 credits per month without requiring a card.
Tools and capabilities
HasData Google Search (SERP) includes tools for:
- Full and lighter-weight Google SERP retrieval, including organic results and related page features.
- Google AI Overview answers with referenced sources and expanded subtopics.
- Google AI Mode responses with citations, subtopics, follow-up suggestions, and continuation tokens.
- Google News articles with publisher, publication date, thumbnail, URL, and navigation tokens.
- Shopping listings and expanded immersive product information, including merchants, prices, shipping, conditions, specifications, ratings, images, and review data.
- Product detail lookups with offers and review text where supported by the search type.
- Event information such as title, time, venue, address, ticket links, description, and thumbnail.
- Short-video results with titles, platforms, creators, dates, durations, thumbnails, and direct URLs.
The full and light SERP tools expose overlapping search-result data with different response coverage. Choose the specialized tool when the workflow needs a particular result type or follow-up token.
Limitations and notes
The server is read-only: the documented tools retrieve search and result data rather than changing Google content or external records. Calls consume credits, and the supplied tool list assigns different credit costs to different operations. Follow-up workflows can require additional calls, such as resolving individual People Also Ask answers or expanding shopping products.
Results reflect Google search data returned at request time and may vary by query and result type. The server requires an MCP client that supports streamable HTTP and custom headers when using the hosted endpoint. Stdio-only clients need one of the documented npm or PyPI launchers.
Related MCP Servers
Adoption & maintenance
Factual signals from GitHub, npm, and our automated checks — not a rating.
GitHub stars
18
Stargazers on the source repository.
npm downloads
1.1k
Package downloads in the last 30 days.
Last commit
2d ago
Most recent push to the default branch.
Tools exposed
10
Callable tools this server registers over MCP.
Directory activity
1 views
Config copies, upvotes, and views on AllMCPs.
Reviews
No reviews yet — be the first to share how this listing worked for you.
Frequently Asked Questions about HasData Google Search (SERP)
AllMCPs Directory Badge
Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.
Badge Style:
Live Dynamic SVG Preview
Markdown (GitHub README)
[](https://allmcps.com/mcp/hasdata-google-search-serp)HTML Embed
<a href="https://allmcps.com/mcp/hasdata-google-search-serp"><img src="https://allmcps.com/api/badge/hasdata-google-search-serp?style=directory" alt="HasData Google Search (SERP) on AllMCPs" /></a>