Agent Data Tools: Web, documents and search

Connect Remote server

claude mcp add --transport http agent-data-tools-web https://agent-data-tools.revmesh2074.workers.dev/mcp/web --header "Authorization: Bearer <YOUR_API_KEY>"

{
  "mcpServers": {
    "agent-data-tools-web": {
      "url": "https://agent-data-tools.revmesh2074.workers.dev/mcp/web",
      "headers": {
        "Authorization": "Bearer <YOUR_API_KEY>"
      }
    }
  }
}

{
  "servers": {
    "agent-data-tools-web": {
      "type": "http",
      "url": "https://agent-data-tools.revmesh2074.workers.dev/mcp/web",
      "headers": {
        "Authorization": "Bearer <YOUR_API_KEY>"
      }
    }
  }
}

Settings > Connectors > Add custom connector
URL: https://agent-data-tools.revmesh2074.workers.dev/mcp/web

Replace the values in angle brackets with your own. Keys stay on your machine; we never see them.

Tools 42 found in our last check

• search

  Exa-style web search: top 1-20 results with title, URL, snippet, published date and favicon (Brave index); optional domain, date, category and phrase filters; optional live page text, highlights and AI summaries of the top 10 pages. Results are for immediate use only: no storing…

• pack_web_research

  One call to research a question on the web: a Brave web search, then the text of the top 1-5 result pages, read in parallel and clipped to your length, with titles and URLs. A page that cannot be read is listed with its reason. Results are for the caller's immediate use only: no…

• news

  News headlines on any topic, crypto included, as JSON: title, URL, snippet, publisher domain and age, from the Brave Search API's news index. 1-20 results per call; freshness limits results to the past day, week or month. Results are for the caller's immediate use only: no stori…

• pack_news_sentiment

  Brand sentiment from the news on a topic in one call: the latest headlines from the Brave News index (title, URL, publisher, age), each with a positive or negative score from a DistilBERT model, and the balance across them. Up to 10 articles from the past day, week or month. Not…

• contents

  Read one to five public web pages in one call and get each one's clean text (or Markdown), title, author and published date where the page declares them, in the request shape search APIs use (urls as a list). Pages are read in parallel; one that cannot be read is listed in statu…

• image_metadata

  Read an image's metadata from its URL: format (JPEG, PNG, GIF or WebP), width and height, and for JPEG photos the EXIF data: camera make and model, lens, date taken, exposure, aperture, ISO, focal length, orientation, software and the GPS position (latitude, longitude, altitude)…

• url_favicon

  Find a website's icons: every <link rel=icon>, shortcut icon, apple-touch-icon and mask-icon on the page with its size and type, the web app manifest link, and whether /favicon.ico exists, all as absolute URLs, with the best icon picked (SVG, then the largest size; mask icons ne…

• pack_seo_toolkit

  One call for an on-page SEO analysis of a URL: the SEO audit (title and description lengths, canonical, headings, alt text, structured data, score, issues), the top keywords and two-word phrases with their density, the social preview (OpenGraph, Twitter card), the favicon, and r…

• tech_stack

  Detect the technologies behind a website from its home page HTML and response headers: CMS or site builder (WordPress, Shopify, Webflow…), JavaScript framework (Next.js, Nuxt, React…), analytics and ad pixels, support widgets, payments, captcha, CDN and hosting, web server and b…

• extract

  Fetch any public web page URL and get clean, LLM-ready text or Markdown: main content, code blocks, tables, links and headings, for RAG and agent context. Static HTML, Markdown or text; optional section ID. Default 20,000 output characters, max 100,000; input 2 MiB. No JavaScrip…

• extract_rendered

  Same output as /extract, but the page is first rendered in a real browser, so single-page apps and pages that build their content with JavaScript come back with their text instead of an empty shell. Waits for the network to settle (up to 15 seconds). Public pages only; no login.…

• pdf_text

  Extract the text of a PDF from its URL: downloads a public PDF (up to 10 MB) and returns the text page by page, with title, author, page count and character counts. Choose a first page and how many pages to read (up to 200); cap the output with maxChars. arXiv abstract links are…

• sitemap

  Sitemap parser: reads one public XML sitemap or sitemap index as structured URLs and source-reported dates. Supports gzip, substring filtering and pagination. Large sitemaps are read from the start (512 KiB, 1000 entries at most, with a warning). Does not crawl pages or follow c…

• summarize

  Give a URL, get a short summary of the page plus three to six key points, ready to drop into an agent's context. Fetches the page, strips navigation and boilerplate, and summarizes the main text with an LLM. HTML pages only; for a PDF use pdf_text, then ai_summarize_text. Use fo…

• screenshot

  Render any public web page in a real headless Chrome browser, with JavaScript executed, and get a JPEG screenshot (1280 px wide, base64) plus the final URL, HTTP status and page title. Set fullPage=true to capture up to 4000 px of page height. Use for visual checks, page preview…

• papers

  Research papers search across journals, conferences, preprints and books (Crossref): title, authors, year, venue, citation count, DOI link and abstract where available. Optional fromYear filter and up to 20 results per call. Use for research agents, literature reviews, fact-chec…

• arxiv_search

  Search arXiv, the open preprint server for physics, mathematics, computer science and AI: give search words (every word must match, quotes for a phrase) and optionally a category such as cs.AI, and get 1-20 papers by relevance or newest first, each with title, abstract, authors,…

• feed

  Read a public RSS 2.0, RSS 1.0 or Atom feed and get the feed title, link and description plus its newest items: title, link, date (ISO 8601), short plain-text summary, author and id. Up to 50 items, feeds up to 2 MB. Lenient with real-world feeds; a page that is not a feed retur…

• url_meta

  Fetch a public web page's head and return link-preview metadata: title, description, site name, type, preview image, canonical URL, language, author, published time, favicon, theme colour, and every OpenGraph and Twitter-card field. Reads at most 1 MB and never runs JavaScript.…

• agent_readiness

  Score how ready a website is for AI agents, 0-100: llms.txt, sitemap, OpenAPI spec, MCP server card, A2A agent card and x402 payment discovery, each found or missing with its URL, which AI crawlers (GPTBot, ClaudeBot, PerplexityBot and others) robots.txt lets in, and a list of f…

• robots

  Read a site's robots.txt and say whether a crawler may fetch a URL, by RFC 9309 rules as Google applies them (most specific user-agent group, longest matching Allow or Disallow, Allow on ties, * and $ wildcards). Returns the deciding rule, the group used, the rule count and the…

• url_redirects

  Follow a URL's redirects hop by hop (up to 10) and return every hop's status code and Location, the final URL, total hops, timing and whether it loops. Expands short links (bit.ly, t.co…) to their destination without loading the page. Every hop is checked before it is requested;…

• url_uptime

  Check whether a website is up right now: one live request (following redirects) with the HTTP status, up or down, response time in ms, the final URL, content type, server header and page size, and optionally whether the page contains a given text. Timeouts and connection failure…

• seo_audit

  On-page SEO audit of one URL: title and meta description with their lengths, canonical, meta robots, H1s and H2 count, images without alt text, lang and viewport, Open Graph and Twitter card tags, JSON-LD blocks, internal and external link counts and word count, plus a list of i…

• audit_website

  Full website audit of one URL from a single load in a real browser: WCAG 2.1 A/AA accessibility violations with axe-core (rule, impact, elements, fix link), page speed (first byte, FCP, LCP, layout shift) and page weight by type, on-page SEO on the rendered page, and HTTP securi…

• page_publish

  Publish an HTML page and get a public URL for it (valid up to 7 days): send the HTML (up to 200,000 characters) and an optional title; the page is sanitised (no scripts, styles, frames, forms or event handlers; links and https images stay), screened by content moderation, stored…

• wikipedia

  Short summary of a Wikipedia article in any language edition: title, one-paragraph extract, description, thumbnail and page URL. Use to ground an agent's answer in a quick, citable fact sheet. Example: title=Stockholm. Price $0.002/call via x402 USDC or a card key (/credits), fi…

• dictionary

  Dictionary definition of an English word from Wiktionary, grouped by part of speech, with example sentences where Wiktionary gives them, plus the page link and the CC BY-SA attribution to show. Use for writing help, vocabulary, translation checks and word games. Example: word=se…

• search_web

  Web search API for agents: search the web and get the top results as JSON (title, URL, snippet, published date, domain), optionally with the page text, highlights and a summary of each result, and filters by domain, date range and category. Results are for immediate use only (Br…

• news_search

  News search API: current news articles on any topic from the Brave news index, as JSON with title, URL, snippet, publisher and age, 1-20 results, optionally only from the past day, week or month. Results are for immediate use only (Brave API terms). Use when an agent needs the l…

• screenshot_website

  Website screenshot API: render any public web page in a real headless Chrome browser with JavaScript executed and get a JPEG screenshot (1280 px wide, base64) plus the final URL, HTTP status and title; fullPage=true captures up to 4000 px of height. Use for visual checks, previe…

• scrape

  Web scraping API: fetch any public web page URL and get its main content as clean text or Markdown (headings, code blocks, tables and links kept), ready for an LLM, RAG or an agent's context; static HTML, Markdown or text pages, up to 100,000 characters. JavaScript-rendered page…

• page_host

  Host a static web page: send HTML (up to 200,000 characters) and an optional title and get a public URL at once, valid up to 7 days; the page is sanitised (no scripts, styles, frames or forms), screened by content moderation and served with noindex. Use to hand a person a report…

• web_search

  Web search: send a query and get the top web results as JSON (title, URL, snippet, published date), optionally with page text and highlights, filtered by domain, date or category. Results are for immediate use only (Brave API terms); failures are uncharged. Use when an agent nee…

• pdf_extract

  Extract text from a PDF by URL: the text of each page of a public PDF file (up to 10 MB), with the page count, title and author; scanned PDFs without a text layer fail uncharged. Use to read reports, papers, invoices and filings into an LLM, RAG or an agent's context. Example: u…

• page_markdown

  Web page to Markdown: give a public URL and get the page's main content as clean Markdown for an LLM, with headings, links, lists, tables and code blocks kept and navigation, ads and scripts removed, up to 100,000 characters; static HTML, Markdown and text pages. Bot walls, empt…

• wiki_summary

  Wikipedia summary of an article by its title: the one-paragraph extract in plain text with the short description, the page link and the thumbnail image, from the English edition or any other language edition, with the CC BY-SA attribution to show. Use to get quick background on…

• web_fetch

  Web fetch for agents: fetch any public URL and get the page's main content as clean text or Markdown (headings, links, tables and code blocks kept), up to 100,000 characters; static HTML, Markdown and text pages. Bot walls, empty pages and errors are never charged. Use to read a…

• tech_detect

  Website technology detection: which CMS or site builder, JavaScript framework, analytics and ad pixels, payment, support and captcha widgets, CDN, hosting and web server a site runs on, read from its home page HTML and response headers, each with the evidence found. Use for lead…

• crypto_news

  Crypto news today: the latest cryptocurrency headlines (bitcoin, ethereum, DeFi, regulation, markets), or news on any coin or topic you name, as JSON with title, URL, snippet, publisher and age, 1-20 results, from the past day unless you choose a week or month. Results are for i…

• url_unshorten

  URL unshortener: expand a short link (bit.ly, t.co and others) to its final destination without loading the page, with every redirect hop's status code and Location, total hops, timing and whether it loops. Each hop is checked before it is requested; redirects to private address…

• exif

  EXIF data of a photo from its URL: camera make and model, lens, date taken, exposure, aperture, ISO, focal length, orientation, software and the GPS position (latitude, longitude, altitude) when it was recorded, with the image format, width and height. JPEG EXIF; PNG, GIF and We…

Headers

Details

More search and web servers See all

• Live Sports Scores & Betting Odds MCP Server

  Keyless sports scores, betting odds, injuries & news: NFL NBA MLB NHL soccer. No API key.

• Knowra

  Search arXiv papers and read Scout reports with methods, evidence and verification points.

• Contract Compass

  Korean public procurement law: rule-engine rulings, statutes search, live court precedents

• Korea Realty

  Korean real estate: court auctions, 10M+ MOLIT records, subscription notice facts, loan/DSR rules

• 校招宝 · 中国校园招聘岗位数据

  中国校园招聘（秋招/春招/实习/提前批）在招岗位、企业档案、投递截止与求职攻略数据。免 API Key、免注册、只读。

• IBDÅ

  Ask about IBDÅ, a design-led R&D and innovation studio in Dubai, and prepare a project enquiry.