All servers / Web / Webcrawl MCP server
Webcrawl MCP server
MCP server for Webcrawl Anything: search, scrape, map, crawl, parse and monitor the web from your agent. Runs locally with no API key, or on webcrawl.app cloud.
Tested by ConnectATDScore 84 out of 100. Tested 2026-11-19 on package version 1.4.8. Package: @webcrawl/mcp · source
Score breakdown
| Runs | 18 / 20 | |
|---|---|---|
| Tool descriptions | 18 / 20 | |
| Package safety | 20 / 20 | |
| Maintenance | 20 / 20 | |
| Adoption | 8 / 20 |
What we saw
- Starts and answers the MCP handshake: yes (11.1 seconds including download)
- Tools offered: 10
- Last published: 2026-11-15
- Weekly downloads (npm): 975
- License: MIT · Direct dependencies: 11
Want this server set up for your team?
ConnectATD builds AI automation and wires up MCP servers like this one. Tell us what you are trying to do.
Talk to ConnectATDTools and how they are described
Agents choose tools from these descriptions. Under each name you can see how many of its parameters are explained.
web_search7 of 8 parameters describedSearch the web. Use `category` for structured results (flights, hotels, real-estate, shopping with prices, news, local business, security: CVE records with CVSS, affected and fixed versions). Results are localised to the user unless a place is given.
web_read1 of 2 parameters describedFetch one URL and return the full page as markdown by default. Set onlyMainContent to trim header, footer, nav, and aside.
web_parse4 of 5 parameters describedRead a PDF, Word/Excel/PowerPoint file, image, or audio/video file at a URL and return Markdown. Scanned PDF pages are OCR'd; audio/video is transcribed with timestamps. Pages it could not read are listed, never guessed.
web_parse_status0 of 1 parameter describedCheck a background web_parse run and return its Markdown when it has finished.
web_map1 of 3 parameters describedList the URLs on a website (sitemap, robots and links). Use before scraping to pick the right pages.
web_crawl1 of 2 parameters describedRead several pages starting from a URL and return each as markdown. Capped at 25 pages.
web_extract1 of 3 parameters describedPull structured JSON from one URL. Describe what you want with `prompt`, or pass a JSON `schema`.
web_rerank0 of 3 parameters describedOrder your own documents by relevance to a query. Returns the best matches first.
web_monitor12 of 12 parameters describedWatch a single page, a list of URLs, or a whole website section on a schedule. Supports natural-language `watch_for` focus, explicit `condition` rules (e.g. `price < 50`, `content contains "In Stock"`, `added_urls_count > 0`), and email or webhook notifications.
search_categoriesno parametersList the search categories, subcategories and filters web_search supports.
Tested in a sandbox with an empty environment: no API keys, a throwaway folder, nothing from a real account. A passing test shows the server runs and responds. It is not a security audit.