Skip to content
Agentmart
Submit a tool

Webscrape MCP

Fetch any URL and get clean Markdown.

Connector by carrasquelalex1 · GitHub account verified by the MCP Registry

IndexedLicense unknownRemote (HTTP)★ 2
Write a review

Install

Works with Claude Code, VS Code, Cursor, Windsurf. Read the repository before you give any tool access to your data.

npx agentmarket install connector/carrasquelalex1-webscrape-mcp

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Remote endpoint

  • https://webscrape-mcp.onrender.com Remote (HTTP)

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

We use your email only for this newsletter. Privacy

About

Fetch any URL and get clean Markdown. Web scraping for AI agents.

Reviews

Write a review

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools
4 read · 0 write · 0 deleteRead-only
Secrets
None asked for
Install scripts
Nothing to install (hosted)
Runs as
Hosted (remote endpoint)

Tools by what they do 4

Read from the source code; the running server may list different tools.

Read 4 · Look things up without changing anything.

  • webscrape_batch_fetch
  • webscrape_fetch_url
  • webscrape_screenshot
  • webscrape_search

Network hosts it talks to 1

  • webscrape-mcp.onrender.com · found in remote endpoint, install command

Tools (4)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

  • webscrape_batch_fetchFetch Multiple Web Pagesread-only

    Fetch multiple web pages in parallel and return their content. Efficiently scrapes up to 5 URLs simultaneously. Each page is cleaned and converted to Markdown. Results are separated by page. Supports PDF text extraction (auto-detected). Args: params: Validated input containing: - urls: Array of URLs to fetch (1-5) - response_format: 'markdown' or 'json' (default: markdown) - max_chars_per_url: Max chars per URL (default 5000) - js_render: Enable JS rendering for all URLs - extract_schema: Extract structured data from each page

  • webscrape_fetch_urlFetch Web Page Contentread-only

    Fetch a web page and return its content as clean Markdown. Extracts the main content from any public URL, removes clutter (nav, ads, scripts), and converts to clean Markdown formatted for LLM consumption. Supports: - Regular HTML pages converted to clean Markdown - PDF files: text extraction with PyMuPDF (auto-detected by URL or content-type) - Readability mode: uses Mozilla Readability for article-focused extraction - JS rendering: uses Playwright headless browser for SPAs/dynamic content - Structured data: extracts JSON-LD, Open Graph, Twitter Cards, meta tags Args: params: Validated …

  • webscrape_screenshotCapture Web Page Screenshotread-only

    Capture a screenshot of any web page and return it as a base64-encoded image. Uses a headless Chromium browser (Playwright) to render the page, including JavaScript-heavy sites, SPAs, and dynamic content. Returns the image embedded in the MCP response for AI agents to analyze visually. Args: params: Validated input containing: - url: URL to screenshot (required) - width: Viewport width (default 1280, range 320-3840) - height: Viewport height (default 720, range 240-2160) - full_page: Capture full scrollable page (default False) - format: Image form…

  • webscrape_searchSearch Web and Scrape Resultsread-only

    Search the web for a query and scrape the top results into clean Markdown. Combines DuckDuckGo search with content scraping in one step. Falls back to Google and Bing if DDGS is unavailable. Returns search result snippets plus the full page content of each result. Args: params: Validated input containing: - query: Search query (e.g., 'latest AI news 2026') - max_results: Number of results to scrape (1-10, default 5) - max_chars_per_result: Max chars per scraped page (default 3000) - response_format: 'markdown' or 'json' - js_render: Enable JS rende…

Signals

Stars
2
Forks
0
Open issues
0
Last commit
Jun 28, 2026 (4 months ago)
Last release
Jun 7, 2026 (4 months ago)

From GitHub (fetched Oct 24, 2026).

Details

Registry name
io.github.carrasquelalex1/webscrape-mcp
Version
1.0.0
Auth
Auth not stated
License
License unknown
Repository
github.com/carrasquelalex1/webscrape-mcp
First seen
Oct 24, 2026
Last checked
Oct 25, 2026
Source
Official MCP Registrygithub-graphql

More from carrasquelalex1

Cite this page

Webscrape MCP. Agent Mart. https://agentmart.dev/connectors/carrasquelalex1-webscrape-mcp (last updated 2026-10-25)