Fetching, rendering and extracting from pages, including sites that fight back. Every tool below was read from that server's own
tools/list, so the name and arguments are what the server exposes, not what
its description claims.
| Tool | Server |
|---|---|
| playwright__screenshotanswers [Playwright Browser] Take a PNG screenshot of the current page (or a specific element). Returns base64 PNG. arguments: full_page, selector | com.thenextgennexus/enterprise-mcp-gateway com.thenextgennexus |
| playwright__get_htmlanswers [Playwright Browser] Return the HTML of the page or a specific element. arguments: selector, outer | com.thenextgennexus/enterprise-mcp-gateway com.thenextgennexus |
| browser_screenshotanswers Take a screenshot of the current page. Returns the file path. arguments: filename, session_id | lumbox.co MCP server ora.ai |
| browser_screenshotanswers 给网页拍一张截图（境内真 Chromium 渲染），PNG 落文件中转站并返 15 分钟下载 URL。
比 browser_run 简单直接：一个 URL 进、一张图出；固定 1 credit，失败不计费。 arguments: url, full_page, wait_ms | stagenth · 托管浏览器 com.stagenth |
| playwright__close_browseranswers [Playwright Browser] Close the underlying browser, freeing resources. | com.thenextgennexus/enterprise-mcp-gateway com.thenextgennexus |
| GET /Urls/browser-screenshot Generate screenshot (browser) Visits the URL with full browser and creates a screenshot. This request costs 5 credits. REST-Endpoints | link.fish API link.fish |
| get_web_page_htmlanswers Fetch (scrape) a URL using ScrapingAnt and return the web page content as HTML.
Args:
url: The URL of the page to extract (scrape).
browser: Whether to use browser rendering. Default: True.
proxy_type: Ty... arguments: url, browser, proxy_type, proxy_country | com.scrapingant/mcp com.scrapingant |
| add_screenshotanswers Append a screenshot (with an optional note) to a review created by create_review. The image is stored durably in Cobalt — this is the way to persist screenshots that would otherwise be lost when they only pass through... arguments: claim_token, comment, image, image_url, review, source_url | com.cobaltcapture/cobalt com.cobaltcapture |
| render_html_imageanswers Render HTML/CSS to a PNG image via headless Chromium. Use this when the user explicitly asks to render HTML/CSS, provides HTML, or requests a deterministic, pixel-controlled layout assembled with web code.
Do not cho... arguments: html, width, height, inline_images, name, tags | Creative Claw co.creativeclaw |
| fetch_htmlanswers Fetch the fully rendered HTML of any web page through the ScrapeUnblocker API (https://docs.scrapeunblocker.com), bypassing anti-bot protection (Cloudflare, DataDome, PerimeterX, Akamai, Shape). Use when a normal fetc... arguments: url, proxy_country, wait_method, wait_value, sleep_seconds, steps | com.scrapeunblocker/scrapeunblocker-mcp-remote com.scrapeunblocker |
| screenshot_urlanswers Capture a screenshot image of a public web page or an inline HTML snippet, rendered in a real headless browser (JS, CSS, and web fonts execute). Returns a PNG/JPEG/WEBP image. Use this to visually preview a page, gene... arguments: url, html, width, height, fullPage, format | Skillforge Render API com.skillforge99 |
| scrapeanswers Scrape a URL and return content in your preferred format.
Supported output formats:
- markdown (default): Clean LLM-ready Markdown text
- screenshot: PNG/JPEG image of the page
- pdf: PDF document of ... arguments: url, output, wait_for_selector, timeout_ms, block_media, wait_strategy | X1-BaaS Scraping API com.tazpal |
| playwright__extract_tableanswers [Playwright Browser] Extract a standard HTML table as a list of row objects keyed by header. arguments: selector | com.thenextgennexus/enterprise-mcp-gateway com.thenextgennexus |
| update_htmlanswers Write an HTML surface's body. Pass any of `html` / `css` / `js`; omitted fields stay unchanged. Pass empty string to clear. The surface renders in a sandboxed iframe on a separate origin (`render.trydock.ai`) with no ... arguments: slug, surface_slug, html, css, js | Dock ai.trydock |
| screenshotanswers Render a page in a real browser and capture a PNG, returning its public URL. Use when the question is what the page looks like rather than what it says. arguments: url, fullPage, viewport, viewportWidth, viewportHeight, waitFor | Hydrafetch com.hydrafetch |
| scrape_urlanswers [Generic Amazon scrape — power-user escape hatch] Scrape pages the 5 purpose-built tools don't cover. Two input modes (pick one):
① content=bare fragment (keyword / nodeId / sellerId / ASIN) + site — backend builds a ... arguments: parserName, content, url, site, format, zipcode | com.pangolinfo/amazon-mcp com.pangolinfo |
| screenshot_urlanswers Render a URL in a headless browser and return a PNG screenshot at the size you ask for. Paid: call without x_payment to receive this call's exact terms (amount, asset, network), sign them, then call again with x_payme... arguments: url, width, height, full_page, x_payment | Professor Sausages — Web & Documents com.professorsausages |
| render_screenshotanswers PAID (x402): returns x402 payment instructions for a PNG screenshot of a publicly reachable URL, rendered via a real, robots-respecting headless browser. Use render_preview (free) first. Currently soft-skips 503 until... arguments: url, fullPage, width | agent-web — URL to LLM-ready markdown: a polite, robots-respecting web page reader (free) io.github.foomworks |
| screenshotanswers Take a screenshot of a web page rendered in a real browser and return it as
base64 image data (png by default, jpeg optional), with the final url and
pixel size. Consent overlays are hidden so the shot... arguments: url, api_key, full_page, width, height, format | Pagewatch dev.pagelens |
| render_htmlanswers Compile a Kamy template — or raw Handlebars source you pass inline — against a data payload and get the rendered HTML string back. No browser runs, no PDF is produced and no file is stored, so this is the tool for pip... arguments: template, html, data, direction | Kamy dev.kamy |
| scrape_knowledge_urlanswers Fetch a URL's content into the knowledge base. Server crawls the URL, stores the response body in R2, returns the new document ID. Failures store the row with status='failed'. Use for adding marketing pages, FAQ docs,... arguments: url | FavCRM io.favcrm |
| scrape_websiteanswers Fetch the readable text of a PUBLIC web page so you can use it as context when writing/editing messages (e.g. read a prospect's website or an article). Returns plain text (HTML stripped, truncated) plus any contact em... arguments: url, max_chars | LinkedIn MCP Server (Salesbot) cz.salesbot |
| crawler_block_testanswers What the domain's CDN really does, as opposed to what its robots.txt says. Sends each AI crawler's real user-agent at the homepage and compares the response against a browser: a site can allow GPTBot in robots.txt and... arguments: domain | Desvela Preflight — free MCP server desvela.dev |
| crawler_block_testanswers What the domain's CDN really does, as opposed to what its robots.txt says. Sends each AI crawler's real user-agent at the homepage and compares the response against a browser: a site can allow GPTBot in robots.txt and... arguments: domain | Desvela Preflight — free MCP server desvela.ai |
| html-to-pdfanswers HTMLをPDFに変換 (Browser-based tool) | JobDoneBot (deprecated - moved to com.jobdonebot/tools) io.github.acromoney888 |
| StartCrawleranswers Starts a crawl using the specified crawler, regardless of what is scheduled. If the crawler is already running, returns a <a href="https://docs.aws.amazon.com/glue/latest/dg/aws-glue-api-exceptions.html#aws-glue-api-e... | AWS Glue amazonaws.com |
| GetHTMLanswers Get the HTML code Retrieve the HTML code of the rendered page. This API call should be used when html=1 was specified in the screenshot request. Screenshot | Browshot API browshot.com |
| GET /translate/braille/htmlanswers Translate from English to Braille Image characters. This is probably what you want to use if you are displaying braille in a browser. Braille | FunTranslations Braille API funtranslations.com |
| filegraph_html_processing_docsanswers Docs for /html/to-text, /html/to-pdf, /html/to-image — extract html text, render to pdf, capture html screenshots. arguments: language, endpoint | ai.filegraph/document-processing ai.filegraph |
| web-scrape-linksanswers PAID MCP TOOL — $0.059 USDC per successful call via native x402. Discovery is free. Extracts all hyperlinks from any public webpage. Returns href URLs normalized to absolute URLs with visible link text. Filters out ja... arguments: url, same_domain_only, include_anchors, deduplicate, limit | The Stall ai.intuitek.the-stall |
| capture_full_page_screenshotanswers Capture a full-height PNG of a page in a real headless browser, scrolling first so lazy-loaded content renders. Returns a signed link to the image that expires in about 24 hours; download the bytes if you need to keep... arguments: url, refresh, runId | Superflow Free Tools ai.usesuperflow |
| screenshotanswers Capture a screenshot of the current browser page in an active session. Returns the screenshot as an inline image. Read-only. arguments: sessionId | WebRun Browser Automation ai.webrun |
| sonar_export_screenshotsanswers Render a screenshot set to store-ready PNGs SERVER-SIDE (no browser needed) and save them as one ZIP per locale in output_dir — ready for App Store Connect / Play Console upload. Rendering happens through the same eng... arguments: set_id, locales, all_locales, output_dir | app.trysonar/sonar app.trysonar |
| screenshotanswers Full-fidelity screenshot of any public web page, captured by a real Chrome browser. Viewport or full-page, configurable width. Returns a base64 PNG. JSON response. [Paid: $0.015 USDC per call via x402 on Base; the cal... arguments: url, full, width | Toolcall click.toolcall |
| screenshot_pageanswers Screenshot a page (real browser) as a base64 PNG/JPEG. (browser; $0.02/call in USDC via x402, 10 free/day). arguments: url, full_page | cloud.fetcher/fetcher cloud.fetcher |
| scrape_pageanswers Fetch a public http/https URL and return its rendered HTML, the links on the page, and page metadata (title/description/OpenGraph/canonical/favicon) — in one render. For clean Markdown use read_url instead. Private/in... arguments: url, formats | PreteWorks API com.preteworks |
| tariffmonkee-screenshotanswers Fetch a URL with a real rendered browser (JavaScript executed) and return a PNG screenshot of the full page. Not JSON -- the response body is the image itself. Results are cached for 24 hours per URL. Cache status and... arguments: url | com.tariffmonkee/mcp com.tariffmonkee |
| playwright__navigateanswers [Playwright Browser] Navigate the browser to a URL. Returns the final URL and page title. arguments: url, wait_until | com.thenextgennexus/enterprise-mcp-gateway com.thenextgennexus |
| playwright__clickanswers [Playwright Browser] Click an element matched by CSS selector or visible text. arguments: selector, text, button, double_click | com.thenextgennexus/enterprise-mcp-gateway com.thenextgennexus |
| playwright__type_textanswers [Playwright Browser] Type text into an input/textarea. Optionally clear first or press Enter after. arguments: selector, text, clear, press_enter | com.thenextgennexus/enterprise-mcp-gateway com.thenextgennexus |
| playwright__get_textanswers [Playwright Browser] Extract visible text from the page or a specific element. arguments: selector | com.thenextgennexus/enterprise-mcp-gateway com.thenextgennexus |
| playwright__evaluateanswers [Playwright Browser] Evaluate JavaScript in the page context. Use `return` for values or an expression. arguments: script | com.thenextgennexus/enterprise-mcp-gateway com.thenextgennexus |
| playwright__select_optionanswers [Playwright Browser] Choose an option from a <select> element by value or visible label. arguments: selector, value, label | com.thenextgennexus/enterprise-mcp-gateway com.thenextgennexus |
| playwright__scrollanswers [Playwright Browser] Scroll the page (or an element) in the given direction by `amount` pixels. arguments: direction, amount, selector | com.thenextgennexus/enterprise-mcp-gateway com.thenextgennexus |
| playwright__wait_foranswers [Playwright Browser] Wait until a selector reaches a given state (visible|hidden|attached|detached). arguments: selector, timeout, state | com.thenextgennexus/enterprise-mcp-gateway com.thenextgennexus |
| playwright__get_linksanswers [Playwright Browser] Collect all anchor hrefs, optionally filtered by regex. arguments: selector, pattern | com.thenextgennexus/enterprise-mcp-gateway com.thenextgennexus |
| playwright__page_pdfanswers [Playwright Browser] Render the current page as PDF (headless only). Returns base64 PDF. arguments: format_, landscape | com.thenextgennexus/enterprise-mcp-gateway com.thenextgennexus |
| playwright__fill_formanswers [Playwright Browser] Fill multiple form fields from a list of {selector, value} and optionally submit. arguments: fields, submit | com.thenextgennexus/enterprise-mcp-gateway com.thenextgennexus |
| playwright__get_cookiesanswers [Playwright Browser] Return all cookies for the current browser context. | com.thenextgennexus/enterprise-mcp-gateway com.thenextgennexus |
| playwright__set_cookiesanswers [Playwright Browser] Set cookies for the current browser context. arguments: cookies | com.thenextgennexus/enterprise-mcp-gateway com.thenextgennexus |
| create_screenshot_batchanswers Render a list of web pages in a real browser. Returns a batch id to poll. The first 10 screenshots each month are free, metered per network address rather than per key, so issuing another key does not reset them. Beyo... arguments: urls, name, format, full_page, width, height | url2image com.url2image |
| crawler_block_testanswers What the domain's CDN really does, as opposed to what its robots.txt says. Sends each AI crawler's real user-agent at the homepage and compares the response against a browser: a site can allow GPTBot in robots.txt and... arguments: domain | Desvela ARD Registry — free preflight(domain) dev.desvela |
| get_htmlanswers Read an HTML surface's body. HTML surfaces (Surface.kind="html") store mockup or full-page content as three text fields (html, css, js) rendered together inside a sandboxed iframe. Use `list_surfaces` to enumerate htm... arguments: slug, surface_slug | Dock ai.trydock |
| validate_htmlanswers Pre-flight check on html / css / js BEFORE writing via update_html. Returns { ok, errors, warnings, parsed } where parsed has byte counts per field and `dropped` (true if the sanitizer would strip anything from `html`... arguments: html, css, js | Dock ai.trydock |
| get_browsersauth required Get browser distribution — Chrome, Safari, Firefox, Edge, etc. arguments: websiteId, domain, startAt, endAt, timezone, limit | Flowsery com.flowsery |
| webScrapeanswers Scrape a webpage with custom options arguments: url, device, format, proxyMode, proxyCountry, renderJS | com.geekflare/mcp com.geekflare |
| metaScrapeanswers Scrape meta tags from a URL arguments: url, device, renderJS, format, proxyCountry, fileOutput | com.geekflare/mcp com.geekflare |
| screenshotanswers Capture a screenshot of a website arguments: url, device, type, theme, proxyCountry, selector | com.geekflare/mcp com.geekflare |
| generate_html_visualanswers Generate a small, self-contained HTML visual (comparison table, simple diagram, annotated list, mini-dashboard) as a throwaway artifact for the operator's screen — not a webpage, not persisted content. Use when a quic... arguments: companyId, prompt, title | com.getfreedomos/freedom-mcp com.getfreedomos |
| markdown_to_htmlanswers Turn Markdown into clean HTML, with a preview you can trust. A HelpySelf tool (helpyself.com). arguments: text, allowHtml, headingIds, breaks | HelpySelf com.helpyself |
https://neuronto.com/tools?q=..., or connect an agent to
https://neuronto.com/mcp and call find_tool. No key, no signup.