litescrape-mcp-server
Official Litescrape MCP server. The hosted Streamable HTTP endpoint answered an unauthenticated initialize (serverInfo litescrape-mcp-server 0.3.0, protocolVersion 2025-06-18, capabilities.tools.listChanged) and tools/list with ten tools; the tool list below is the live response saved verbatim in mcp/litescrape-mcp-tools-list.json. The same server is published to npm as litescrape-mcp-server for stdio use and listed in the official MCP registry as com.litescrape/litescrape-mcp-server with a streamable-http remote of https://mcp.litescrape.com/mcp.
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.
Endpoint
Hosted endpoint · transport
Connect
This is a remote MCP server — point an MCP client at the endpoint URL. Clients with native remote support (Claude, Cursor, VS Code, …):
For stdio-only clients (older Claude Desktop, etc.), bridge with mcp-remote:
If the server requires authentication, add the provider's token/header (e.g. an X-API-Key) per its docs. A quick reachability check:
Tools
search— Search the web through Google and return ranked organic results (title, link, snippet) as JSON. Fast mode: no Knowledge Graph, ads or AI modules; use google_search for the full results page. Free without an API key (shares the google_search allowance).google_search— Fetch a first-party Google Search results page as JSON: organic_results plus whichever modules Google served (knowledge_graph, answer_box, ai_overview, ads, related_questions, related_searches, local_results, top_stories, inline_videos and more). Supports localization, verticals (news, videos, local, shopping, patents), date filters and site restriction. Free without an API key: 25 calls per network per day.bing_search— Fetch a Bing web search results page as JSON: organic_results plus the modules Bing served (answer_box, knowledge_graph, copilot_answer, ads, related_questions, inline_videos, top_stories and more). Free without an API key: 50 calls per network per day.duckduckgo_search— Fetch ranked DuckDuckGo web results (organic_results with title, link, snippet) with region, safety and date controls. Free without an API key: 50 calls per network per day.google_maps— Search Google Maps for places (local_results with name, address, rating, reviews, hours, phone, website, coordinates) or fetch one exact place (place_results) by place_id, data_cid or data sequence. Filter by price, rating and opening hours. Free without an API key: 50 calls per network per day.google_ai_overview— Return only the AI Overview Google generates for a search (ai_overview with ordered text_blocks and cited references), or null when Google shows none. Accepts the google_search parameters. Requires an API key.google_ai_mode— Ask Google AI Mode a question and return its generated answer (ordered text_blocks: paragraphs, headings, lists, tables, code) with the sources it cited (references). Set continuable to get a token for follow-up questions; image_url adds a picture to the prompt. Slow: answers are generated per request. Requires an API key.google_shopping— Search Google Shopping and return the product grid (shopping_results with title, price, source, rating, thumbnail), category blocks, sponsored listings and the refinement chips Google renders (filters). Price bounds, sale, shipping and small business refinements are mutually exclusive; sort_by combines with one of them. Requires an API key.google_reviews— Return the Google Maps reviews of one place (reviews with rating, snippet, author, date, likes, owner response, guided details and dining subratings) plus place_info. Identify the place by place_id or data_id from a google_maps result. Sort, filter by topic or text, and follow pagination.next_page_token for more. Requires an API key.web_fetch— Render one public web page in a fresh browser and return it as Markdown (default), HTML, plain text or a full-page PNG screenshot encoded as base64, with url, title, content and the status_code the site returned. Narrow the content with target_selector or remove_selector. Alpha. Requires an API key.
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.
Work with this as data
Every MCP server here is available over the APIs.io API and to AI agents over MCP.