Read pages that load with JavaScript
Bring content that appears after a page loads into your assistant. JavaScript rendering helps you research dynamic product pages, listings and other public sources.
For researchers, developers & AI builders
GeoRanker Web Scraping MCP is a Beta connector for AI agents, researchers and developers to retrieve supported public pages as text or HTML, including supported JavaScript-rendered and Cloudflare-protected sources.
Made for your everyday work
Bring dynamic page content into your research with JavaScript rendering and Cloudflare bypass for supported public sources. Then ask your assistant to summarize, compare and organize it.
Bring content that appears after a page loads into your assistant. JavaScript rendering helps you research dynamic product pages, listings and other public sources.
Cloudflare bypass for JavaScript scraping helps your assistant retrieve content from supported public websites, so you can keep your research moving.
Ask your assistant to summarize a source, organize product details or build a research brief from the available text or HTML. Keep the source link and available freshness information with your notes.
Bring in selected pages so your assistant can compare messaging, product information or documentation across the sources you choose.
Read one supported public page per request as text or HTML, capped at 50,000 characters with truncation disclosed. JavaScript rendering and Cloudflare handling depend on the source; rendering or access to every website is not guaranteed. Your assistant creates summaries and tables from the returned content. Signed-in pages, structured field extraction and site-wide crawling are outside this MCP’s scope.
Requirements: Node.js 22.22.2+ on the 22 release line, 24.15.0+ on the 24 release line, or 26.0.0+; npm and Git. No GeoRanker signup or manually entered API key is required for the Beta trial.
Reviewed client 0.13.1 (2026-09-18). Install from GitHub source; the npm package is unpublished.
Run these commands in your terminal. Setup enrolls a local installation, saves its credentials and checks the hosted tools without running a data query.
git clone https://github.com/georanker/georanker-web-scraping-mcp.git
cd georanker-web-scraping-mcp
npm ci
npm run build
node dist/src/cli.js --setupRun this from the client folder above. Reconnect Codex, then use /mcp to check the connection.
codex mcp add georanker-web-scraping -- node "$PWD/dist/src/cli.js"Reconnect your assistant, enable the GeoRanker connection if prompted, and try this:
Read the public product-page URL I provide, including content rendered with JavaScript. If it is protected by Cloudflare, use the supported bypass. Summarize the price, availability and key specifications, and include the source link. Flag any details you cannot retrieve.The local stdio client connects to GeoRanker over HTTPS. It checks for verified client updates automatically; set GEORANKER_MCP_AUTO_UPDATE=0 in your host configuration to manage versions yourself. Read client privacy and data flow ↗
Your first useful result
Matching completed results can be reused for seven days by default, subject to service configuration. Ask for forceLive: true to bypass completed MCP cache reuse; matching pending work is still retrieved with its existing ID. Provider generation time and cache storage time are different.
Read the public product-page URL I provide, including content rendered with JavaScript. If it is protected by Cloudflare, use the supported bypass. Summarize the price, availability and key specifications, and include the source link. Flag any details you cannot retrieve.For agent builders
Local MCP clients connect your agent to GeoRanker’s search and public-page tools. Check the contracts, data flow and result limits before building your workflow.
Public Beta · Client 0.13.1 reviewed . Documentation links below preserve the reviewed source version.
GeoRanker Web Scraping MCP is a Beta connector for AI agents, researchers and developers to retrieve supported public pages as text or HTML, including supported JavaScript-rendered and Cloudflare-protected sources.
fetch_pageget_fetch_resultWeb Scraping MCP retrieves one supported public page per fetch_page request, including supported JavaScript-rendered and Cloudflare-protected sources. It returns readable text or HTML, capped at 50,000 characters with truncation disclosed. Source access and rendering are not guaranteed. The assistant interprets the content; the MCP does not provide structured field extraction, authenticated browsing or batch site crawling.
Reviewed first-party documentationThe documented integration is a local stdio MCP client launched by your assistant. That client connects over HTTPS to GeoRanker's hosted service. Use a host that can launch local Node.js processes and follow its configuration guide. A cloud-only connector needs a separately supported remote authentication flow; entering a hosted endpoint URL alone is not the documented installation path.
Reviewed first-party documentationThe client enrolls automatically and stores an installation credential and signing identity locally. You do not enter a reusable provider API key or create a GeoRanker account for the Beta trial. The two clients share installation state for the same service origin. This enrollment is not OAuth. The setup check verifies enrollment and tool contracts without submitting a data query; subsequent tool calls use the configured allowance.
Reviewed first-party documentationPass forceLive: true to bypass eligible completed MCP cache reuse, which defaults to seven days and is configurable. Matching pending or uncertain work keeps its existing ID. This does not bypass the upstream provider's processing rules or create a background refresh schedule. Preserve cached, cachedAt and generatedAt when supplied; cache storage time is not observation time.
Reviewed first-party documentationIndependent tasks may run in parallel within shared and per-installation service limits. For pending SERPs, retain jobId and call get_serp_result; for pending web pages, call get_fetch_result with the same jobId. SEO report families use their own reportId and matching get tool. Retrieval does not create a new data job. Follow returned nextAction and retry information, preserve pending, unknown and failed states, and avoid duplicate creation. Cancelling or timing out a call does not prove that submitted work stopped.
Reviewed first-party documentationThe client sends requested search arguments or the public URL, an installation identifier, a revocable token and a persisted device signal to GeoRanker over HTTPS. GeoRanker uses its upstream infrastructure to process the request. Local identity and credentials normally live under ~/.config/georanker-search-mcp/client/; GEORANKER_STATE_DIR can change that location. Keep this state private. Shared result caching follows service isolation rules, so avoid secret URLs or sensitive content. Removing the host configuration does not revoke the installation or erase its saved credentials.
Reviewed first-party documentationThe public clients reviewed on 2026-09-18 are version 0.13.1; the website presents both products as Beta. The launcher checks for verified GitHub release packages at startup and every five minutes. It verifies release provenance and installs locked production dependencies without lifecycle scripts. Compatible worker updates apply during an idle period; calls are not replayed. Set GEORANKER_MCP_AUTO_UPDATE=0 in the host environment to review and manage releases yourself. Update downloads contact GitHub, npm and signature-verification services; the client privacy guide explains this data flow.
Reviewed first-party documentationThe reviewed release uses a GitHub source installation: clone, install dependencies, build, run the setup check and configure your host. Its npm packages are unpublished, so an npx command is not available for this release. Requirements are Node.js 22.22.2+ on the 22 release line, 24.15.0+ on the 24 release line, or 26.0.0+; npm and Git. Public source availability does not imply an open-source license; the packages are marked UNLICENSED. Repository metadata is not an official MCP Registry submission.
Reviewed first-party documentationGeoRanker MCP is in Beta. Request more free Beta credits through the website chat powered by Tidio, or use the contact page. Tell the team which MCP you use, what you are building and the workload you need. Our team reviews your request and confirms the allowance. The hosted service controls shared and per-installation allowances and concurrency, so follow returned limit and retry information. API calculator estimates do not define MCP Beta allowances or report admission units.
MCP Beta credit policyBetter together
Research SERPs, track rankings, review on-page SEO, find broken internal links, explore backlinks and compare keyword demand. Install both MCPs in the same assistant.