Geonode MCP: extract, crawl and search the web from your AI app

Wire Geonode into Claude, ChatGPT or Cursor

1. 1Click Connect Geonode free. There's no sign-in, so its tools are ready at once.
2. 2`crawl` and `batch` start jobs that fetch many pages at a time. If your AI app should only read single pages with `extract`, switch those two off along with their status and cancel tools.
3. 3Add ContextGate to your AI app as a connector or MCP server. The steps for each app are on the Works with page.
4. 4Ask your AI app to extract a pricing page as Markdown with Geonode, then open Activity to see the `extract` call.

Web data jobs your AI app can run

• Pull one page as HTML or Markdown with `extract`, with optional JavaScript rendering and proxy geo-targeting.
• Crawl a site breadth-first from a seed URL with `crawl`, setting depth and page limits.
• Discover the URLs under a base URL from its sitemap and links using `map`.
• Run a web search with locale targeting through `search`.

Rein in crawling

• Switch off `crawl` and `batch` to stop large multi-page jobs; they're hidden from AI apps and refused if called.
• A policy can block a call that carries a secret, such as a token inside a URL.
• Activity keeps each extract, crawl and search on record.

What you get with Geonode and ContextGate

• Your AI apps can use GeonodeClaude, Cursor, ChatGPT and other AI apps reach Geonode through the one ContextGate connection you add to them.
• You choose which tools they can useSwitch off any Geonode tool you don't want used. It's hidden from your AI apps and refused if called.
• Every call is checked and recordedYour policies check each call (for example, personal data is hidden and secrets are blocked), and Activity keeps a record of it.

ContextGate sees only the tool calls that go through it, not your AI app's built-in tools or your chats.

Geonode tools

Examples of what your AI apps can do in Geonode. You'll see the exact list of tools after you connect it.

• extractExtract content from a web page. Supports HTML and Markdown output formats, optional JavaScript rendering via headless browser, proxy geo-targeting, custom HTTP
• jobRetrieve the result of an asynchronous extraction job by its job ID. Returns the current status (pending, running, completed, or failed) and, once completed, th
• jobsList extraction jobs with optional filters. Filter by job ID, URL, status (pending, running, completed, failed), output format, or date range. Results are pagin
• statisticsRetrieve aggregated extraction statistics for the authenticated user. Returns metrics such as total jobs, success and failure counts, and usage breakdowns over
• batchStart an asynchronous batch extraction job from an explicit list of URLs. Supports HTML and Markdown output formats, optional JavaScript rendering, proxy settin
• batch_statusRetrieve the status and paginated results of a batch extraction job by its job ID. Returns item counts, invalid URLs, and the current page of per-URL extraction
• cancel_batchCancel a batch job by its job ID. Stops scheduling new batch items while allowing in-flight child extractions to drain. Requires a Geonode API key, sent as the
• crawlStart a website crawl job from a seed URL. Crawls pages breadth-first (BFS) up to the 'depth' parameter (BFS levels from the seed) and the 'limit' parameter (ma
• crawl_statusRetrieve the status and results of a crawl job by its job ID. Returns the current status (queued, running, completed, or failed), page counts, and once complete
• cancel_crawlCancel a crawl job by its job ID. Stops scheduling new crawl pages while allowing in-flight page work to drain. Requires a Geonode API key, sent as the X-Api-Ke
• mapDiscover all URLs under a base URL by combining sitemap parsing with HTML link extraction from the seed page. By default discovery is scoped to the exact seed h
• map_jobsList map jobs for the authenticated user with optional filters. Filter by base URL (partial match), status (pending, running, completed, failed), or date range.
• map_jobRetrieve the full details and discovered links for a map job by its job ID. Returns the current status and, once completed, the discovered links and their sourc
• searchRun a web search and return ranked results. Supports locale targeting (a language code like 'en', a language-region tag like 'en-US', or 'all'), pagination via
• search_jobsList search jobs for the authenticated user with optional filters. Filter by query (partial match), status (pending, running, completed, failed), or date range.
• search_jobRetrieve the full details and results for a search job by its job ID. Returns the current status and, once completed, the search results, suggestions, and any s