Serper MCP
Serper ships NO MCP server of its own — no hosted endpoint, no published package, no mention of MCP anywhere on serper.dev. The tool list below is a CANDIDATE derived from the OpenAPI definitions in this repo, not something Serper publishes. Every MCP server that exposes Serper today is a third-party wrapper around Serper's REST API, installed and run by the end user with their own API key.
One-click install for Cursor, VS Code, Claude, and 20+ other MCP clients, powered by API Commons MCP Install — visit install.apicommons.org for more information.
Descriptor
Candidate descriptor · transport
Tools
web_search— Run a Google web search and return organic results, knowledge graph, answer box, people-also-ask and related searches.image_search— Search Google Images and return structured image results.video_search— Search Google Videos.news_search— Search Google News.places_search— Search Google for local businesses and places.maps_search— Search Google Maps by query, lat/long, placeId or cid.place_reviews— Retrieve Google reviews for a place, paginated by nextPageToken.shopping_search— Search Google Shopping for products.scholar_search— Search Google Scholar for academic publications.patents_search— Search Google Patents.autocomplete— Return Google autocomplete suggestions for a query prefix.lens_search— Reverse image search with Google Lens from an image URL.scrape_webpage— Fetch and extract a webpage's contents, optionally as markdown with images, links and videos.list_locations— Look up the canonical location strings accepted by the `location` parameter.
About MCP
The Model Context Protocol (MCP) is an open protocol Anthropic introduced for connecting LLM-based agents to external tools and data sources. Providers publish MCP servers that expose their API surface as structured, discoverable tools — an MCP-compatible client (Claude Desktop, Cursor, Cline, Continue, etc.) can connect to the server and call its tools without any per-provider integration code.
Browse every MCP server on the APIs.io network or compare with the broader Agent Skill surfaces of the same providers.