Smithery is now a part of Arcade.dev! Read more in our announcement here
Fast, intelligent web search and web crawling. Get fresh information about libraries, APIs, and SDKs.
Docs: https://docs.keenable.ai/mcp-server Keenable is a free, remote MCP server that gives agents access to the web index. Search the web with ranked results and date/site filters, then fetch any indexed page as clean markdown. Works out of the box with no account or API key. Tools: searchwebpages: Search the web and return ranked results. fetchpagecontent: Fetch an indexed URL and extract its content as clean markdown
Search the web in real time to get trustworthy, source-backed answers. Find the latest news and comprehensive results from the most relevant sources. Use natural language queries to quickly gather facts, citations, and context.
Search the web with fast, accurate results optimized for AI. Get clean, structured answers with source URLs and relevance scoring.
Highest accuracy web search for AIs
Search the web with Brave's independent index — web, news, images, and videos. Bring your own subscription token from the Brave Search API dashboard.
AI-powered search and retrieval platform. Search the web, read page content, extract structured data, and ground AI responses.
GroundRoute gives your AI agent web search across six engines (Serper, Brave, Exa, Tavily, Firecrawl, Perplexity) through a single search tool. That one tool covers web, news, and academic search, synthesized answers with citations, and full-page fetch, all selectable with a mode parameter, so you never wire up or pay for six separate APIs. It routes each query to the cheapest engine that meets a quality bar, caches repeats, and fails over automatically. Pricing is gain-share: you keep about half the cache savings, so it never costs more than going direct. Bring your own engine keys (BYOK) or let GroundRoute manage them. New accounts start with $10 in free search credit, no card. Get a key at https://groundroute.ai/keys, and see the live benchmark across all six engines (170 real agent queries) at groundroute.ai/state-of-ai-search.
Web search for AI agents. Ranked results with page passages already extracted, plus clean markdown extraction of any URL. $2 per 1,000 searches, 1,000 free credits a month, no signup.
Search the live web to retrieve up-to-date information and bypass knowledge cut-offs. Convert any webpage into clean, readable Markdown while navigating around captchas and complex layouts. Access real-time data from across the internet to improve research and verification tasks.
Web search API for AI agents. Search the web and get structured results: title, URL, snippet, and metadata. Up to 10 results per query. Current news, documentation, research papers — everything indexed. Tools: websearchquery. Use this when your agent needs to find information, research topics, check current events, or verify facts. The fundamental research tool every agent needs. IMPORTANT: For deep fact-checking with evidence, use researchcheckfact. Returns: {results: [{title, url, snippet}]}. No API key required — x402 micropayment $0.003/call on Base L2.
pixserp is an AI-native search MCP server. Add it to your client and your AI assistant gets access to the live web — with structured citations, across ten answer shapes, from a single tool call. Web, news, images, places, shopping, flights, hotels, YouTube videos & transcripts, any URL. One endpoint. One bill. Ask in natural language, get a cited answer from the live web.
Live web search for AI agents. Up to 10 results for $0.001 USDC via x402 on Base. No signup or API key.
Accesses the web to provide detailed, contextually relevant search results with accurate citations. Delivers real-time information and deep insights by querying advanced language models. Streamlines research tasks by synthesizing data from multiple online sources into concise answers.
.png)
MCP server and REST API giving AI agents live access to the web — with especially deep coverage of Russian-language sources. Ten tools in one server: websearch — Live web search across multiple engines. Returns ranked results with title, URL and snippet. Supports time filters (day/week/month/year), language selection (auto/ru/en), category (general/news/it/science), domain allow/block lists, and an excerpts flag that pulls full page text for the top results in one call. imagesearch — Image search returning direct file URLs, source pages and resolution. Up to 48 results per call. readurl — Fetches a single page and returns clean Markdown — no ads, no navigation, no HTML. JavaScript is executed server-side so SPAs and React apps read correctly. Long pages are paginated via offset. readurls — Same as readurl but reads up to 5 URLs in parallel in one call. Failed URLs are listed separately; the rest still return. fetchpage — Opens a page in a r
Web search and page-reading for AI agents. Requires a Caesar API key.
Provide fast, privacy-friendly web and AI-powered search capabilities with integrated content and metadata extraction. Enhance your AI assistants by enabling comprehensive web scraping without requiring API keys. Optimize performance with caching and secure usage through rate limiting and user agent rotation.
The official MCP server for Search1API — web search, news, page retrieval, sitemap discovery, and trending topics in one API. Supports OAuth and API key authentication.
Unified real-time search engine skill for AI agents.
Real-time web search built for AI agents. One tool, serpdivesearch, returns the actual content of the best pages — extracted, cleaned, and sized for LLMs — not a list of links to crawl. Why SERPdive On a public, replayable 1,000-question benchmark against Tavily: Same speed (median ~1.7 s server-side) 20.2% fewer tokens fed to your LLM per search 🏆 60.7% of decided quality duels won Same questions, same judge, replayable end to end on your machine. The tool serpdivesearch(query, model?, answer?, maxresults?) query — the search, in any language; localization is automatic model — mako (default): the fact-carrying sentences of each page, fast. moby: the full readable text, for deep research answer — true adds a direct answer synthesized from the sources (cited on moby) maxresults — hard cap on results, 1 to 10 Every result ships as `{ url, title, date?,
