For researchers, developers & AI builders

GeoRanker
Web Scraping MCP

Turn public pages into useful answers.

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.

No GeoRanker signup for the trialNo API key to configure

Made for your everyday work

Make more of
every source.

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.

01

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.

02

Reach Cloudflare-protected public pages

Cloudflare bypass for JavaScript scraping helps your assistant retrieve content from supported public websites, so you can keep your research moving.

03

Turn page content into useful answers

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.

04

Compare what websites say

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.

YOUR CHOICEWeb Scraping MCP

Requirements: Node.js 22.22.2+ on the 22 release line, 24.15.0+ on the 24 release line, or 26.0.0+; npm (including npx). No GeoRanker signup or manually entered API key is required for the Beta trial.

Reviewed client 0.14.0 (2026-10-06). Install from npm ↗. Git and a TypeScript build are not required.

01

Install Web Scraping MCP.

Run this command in your terminal. Setup enrolls a local installation, saves its credentials and checks the hosted tools without running a data query.

Web Scraping MCP · client installation
npx --yes @georanker/[email protected] --setup

02

Add it to Codex.

Reconnect Codex, then use /mcp to check the connection.

Codex · Web Scraping MCP configuration
codex mcp add georanker-web-scraping -- npx --yes @georanker/[email protected]

If your host cannot find npx, use its absolute executable path and follow the host’s platform-specific launch instructions. These configuration guides do not certify every host or operating system.

03

Ask your first question.

Reconnect your assistant, enable the GeoRanker connection if prompted, and try this:

Copy your first prompt
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. The npm version pins the bootstrap package. Signed automatic updates can still select a newer worker; set GEORANKER_MCP_AUTO_UPDATE=0 in your host configuration to keep the selected version and manage future updates yourself. Read client privacy and data flow ↗

The local client is MIT-licensed ↗. Hosted GeoRanker service terms and allowances are separate.

Install from GitHub source (fallback)

This route also requires Git. Build the reviewed source and run its setup check:

Web Scraping MCP · source installation
git clone https://github.com/georanker/georanker-web-scraping-mcp.git
cd georanker-web-scraping-mcp
git checkout e68996d3e9726238768c8bfd076221760238b71a
npm ci
npm run build
node dist/src/cli.js --setup

In your host configuration, replace npx and its package arguments with node and the absolute path to georanker-web-scraping-mcp/dist/src/cli.js. When switching between source and npm, preserve your state directory, service origin and environment settings so the client reuses your existing installation credentials.

Your first useful result

Bring a question.
Keep the source.

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 SERP and SEO report work is still retrieved with its existing ID. WHOIS is synchronous; forceLive cannot replay unresolved work as another paid lookup, and the server handles failed-lookup refunds and accounting recovery. Provider generation time and cache storage time are different.

Try this with Web Scraping MCP
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

Connect with the facts.

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 · Web Scraping MCP 0.14.0 (2026-10-06). Documentation links below preserve each reviewed source version.

Can an agent read JavaScript-rendered or protected public pages?

Web 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 documentation
How do AI agents connect to GeoRanker MCP?

The 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 documentation
What does no API key to configure mean?

The 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 documentation
How do I request fresh data instead of a cached answer?

Pass forceLive: true to bypass eligible completed MCP cache reuse, which defaults to seven days and is configurable. Matching pending SERP and SEO report work keeps its existing ID. WHOIS is synchronous: forceLive cannot replay unresolved work as another paid lookup, and the server handles failed-lookup refunds and accounting recovery. 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 documentation
How should an agent handle pending results and parallel requests?

Independent 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 documentation
What data leaves my machine and what is stored locally?

The 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 documentation
How are MCP client versions and updates managed?

The reviewed public clients are SEO MCP 0.15.1 (2026-10-08); Web Scraping MCP 0.14.0 (2026-10-06); 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. The npm version pin selects the bootstrap package; signed automatic updates can still select a newer worker. Set GEORANKER_MCP_AUTO_UPDATE=0 in the host environment to keep the selected version and manage future releases yourself. Update downloads contact GitHub, npm and signature-verification services; the client privacy guide explains this data flow.

Reviewed first-party documentation
Can I install GeoRanker MCP with npx?

Yes. npm is the primary installation route: run npx --yes @georanker/[email protected] --setup or npx --yes @georanker/[email protected] --setup, then add the matching package to your assistant. 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 (including npx). Git is only needed for the source fallback. Both local clients are MIT-licensed; the hosted GeoRanker service has separate terms and allowances. Repository metadata is not an official MCP Registry submission.

Reviewed first-party documentation
How can I get more free MCP credits during Beta?

GeoRanker 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 policy

Set up GeoRanker MCPReview access and allowances

Better together

Need to discover the right pages?

Research SERPs, track rankings, review on-page SEO, find broken internal links, explore backlinks, compare keyword demand and look up domain WHOIS. Install both MCPs in the same assistant.

Explore SEO MCP