Scrapeless Mcp Server

io.github.scrapeless-aiPublished by GitHub account scrapeless-aiv0.6.4Updated Oct 24, 2026

Web search, browser automation, scraping, crawling and CAPTCHA solving for AI agents.

VerifiedStreamable HTTPWeb executableWeb Search & ScrapingBrowser Automation

Overview

AI-generated overview

Scrapeless MCP server lets an assistant search Google, run a cloud browser, scrape and crawl pages, and create AI scraper tasks through Scrapeless.

What you can do
Search Google and read Google Trends data for keywords and interest over time. Drive a cloud browser session: navigate, click, type, press keys, scroll, wait, take screenshots, and read page HTML or visible text. Scrape a single URL as HTML, Markdown, or a screenshot. Start, poll, and cancel asynchronous crawl jobs that follow links across a site. Create AI Scraper tasks for engines such as ChatGPT, Gemini, Perplexity, Copilot, Grok, or Google AI Mode.
When to use it
Useful when an assistant needs live web data, JavaScript-heavy pages, search results, or multi-page crawling, and you want managed browser sessions and anti-blocking handled by a hosted service rather than local tooling.
Requirements
A Scrapeless account and API key, passed as SCRAPELESS_API_KEY for the local npm package (npx scrapeless-mcp-server) or as the x-api-token header for the hosted endpoint. Network access to the Scrapeless service. Optional browser profile and session timeout settings via environment variables or headers.
Before you install
The API key is a billable service credential; a free trial is mentioned but usage may cost money. Browser and scraping tools send target URLs and page data to Scrapeless. Scraped web content is untrusted and can carry prompt injection, so avoid feeding raw HTML into prompts and validate user-supplied URLs and selectors. Browser sessions can persist cookies and local storage if enabled.

Installation

In SourceWeft

  1. Open Scrapeless Mcp Server in the dashboard and add it to a workspace.
  2. Connect x-api-token credentials. They are stored privately and never shown on public pages.
  3. Enable the server for the chats that should use its tools.

Web executable via Streamable HTTP. Remote servers run from the web runtime once configured in a workspace.

Use with an agent

Paste this prompt into Claude Code, Codex, Cursor or another agent — or into SourceWeft chat. The agent reads this server's install guide, shows you its publisher, endpoint and sign-in, and adds it to your client once you agree. Keys never go into a command.

Read https://sourceweft.com/mcp/io.github.scrapeless-ai%2Fscrapeless-mcp-server/install.md and connect the MCP server it describes to my client. Before changing any config, show me its publisher, endpoint and sign-in method and wait for my OK. Never put an API key in a command or in a file I would commit; ask me where it should come from.

Read the install guide the agent follows

Other MCP clients

Add this to your client's mcpServers config.

{
  "mcpServers": {
    "scrapeless": {
      "type": "http",
      "url": "https://api.scrapeless.com/mcp",
      "headers": {
        "x-api-token": "<YOUR_API_KEY>"
      }
    }
  }
}

README

[preview]

Scrapeless MCP Server

Welcome to the official Scrapeless Model Context Protocol (MCP) Server — a powerful integration layer that empowers LLMs, AI Agents, and AI applications to interact with the web in real time.

Built on the open MCP standard, Scrapeless MCP Server seamlessly connects models like ChatGPT, Claude, and tools like Cursor and Windsurf to a wide range of external capabilities, including:

  • Google services integration (Search, Trends)
  • Browser automation for page-level navigation and interaction
  • Scrape dynamic, JS-heavy sites—export as HTML, Markdown, or screenshots
  • Crawl entire websites by following links and capture each page in multiple formats
  • AI Scraper Create an AI Scraper task for ChatGPT, Gemini, Perplexity, Copilot, Google AI Mode, Google AI Overview, Grok, or Alexa

Whether you're building an AI research assistant, a coding copilot, or autonomous web agents, this server provides the dynamic context and real-world data your workflows need—without getting blocked.

Usage Examples

  1. Automated Web Interaction and Data Extraction with Claude

Using Scrapeless MCP Browser, Claude can perform complex tasks such as web navigation, clicking, scrolling, and scraping through conversational commands, with real-time preview of web interaction results via live sessions.

[preview]

  1. Bypassing Cloudflare to Retrieve Target Page Content

Using the Scrapeless MCP Browser service, the Cloudflare page is automatically accessed, and after the process is completed, the page content is extracted and returned in Markdown format.

[preview]

  1. Extracting Dynamically Rendered Page Content and Writing to File

Using the Scrapeless MCP Universal API, the JavaScript-rendered content of the target page above is scraped, exported in Markdown format, and finally written to a local file named text.md.

[preview]

  1. Automated SERP Scraping

Using the Scrapeless MCP Server, query the keyword “web scraping” on Google Search, retrieve the first 10 search results (including title, link, and summary), and write the content to the file named serp.text.

[preview]

Here are some additional examples of how to use these servers:

Example
Search scrapeless by Google search.
Find the search interest for "AI" over the last year.
Use a browser to visit chatgpt.com, search for "What's the weather like today?", and summarize the results.
Scrape the HTML content of scrapeless.com page.
Scrape the Markdown content of scrapeless.com page.
Get screenshots of scrapeless.com.

Setup Guide

  1. Get Scrapeless Key
  • Log in to the Scrapeless Dashboard（Free trial available）
  • Then click "Setting" on the left -> select "API Key Management" -> click "Create API Key". Finally, click the API Key you created to copy it.

[preview]

  1. Configure Your MCP Client

Scrapeless MCP Server supports both Stdio and Streamable HTTP transport modes.

🖥️ Stdio (Local Execution)

JSON
{  "mcpServers": {    "Scrapeless MCP Server": {      "command": "npx",      "args": ["-y", "scrapeless-mcp-server"],      "env": {        "SCRAPELESS_API_KEY": "YOUR_SCRAPELESS_KEY"      }    }  }}

🌐 Streamable HTTP (Hosted API Mode)

JSON
{  "mcpServers": {    "Scrapeless MCP Server": {      "type": "streamable-http",      "url": "https://api.scrapeless.com/mcp",      "headers": {        "x-api-token": "YOUR_SCRAPELESS_KEY"      },      "disabled": false,      "alwaysAllow": []    }  }}
Advanced Options

Customize browser session behavior with optional parameters. These can be set via environment variables (for Stdio) or HTTP headers (for Streamable HTTP):

Stdio (Env Var)Streamable HTTP (HTTP Header)Description
BROWSER_PROFILE_IDx-browser-profile-idSpecifies a reusable browser profile ID for session continuity.
BROWSER_PROFILE_PERSISTx-browser-profile-persistEnables persistent storage for cookies, local storage, etc.
BROWSER_SESSION_TTLx-browser-session-ttlDefines the maximum session timeout in seconds. The session will automatically expire after this duration of inactivity.

Integration with Claude Desktop

  1. Open Claude Desktop
  2. Navigate to: Settings → Tools → MCP Servers
  3. Click "Add MCP Server"
  4. Paste either the Stdio or Streamable HTTP config above
  5. Save and enable the server
  6. Claude will now be able to issue web queries, extract content, and interact with pages using Scrapeless

Integration with Cursor IDE

  1. Open Cursor
  2. Press Cmd + Shift + P and search for: Configure MCP Servers
  3. Add the Scrapeless MCP config using the format above
  4. Save the file and restart Cursor (if needed)
  5. Now you can ask Cursor things like:
    1. "Search StackOverflow for a solution to this error"
    2. "Scrape the HTML from this page"
  6. And it will use Scrapeless in the background.

Supported MCP Tools

NameDescription
google_searchUniversal information search engine.
google_trendsGet trending search data from Google Trends.
browser_createCreate or reuse a cloud browser session using Scrapeless.
browser_closeCloses the current session by disconnecting the cloud browser.
browser_gotoNavigate browser to a specified URL.
browser_go_backGo back one step in browser history.
browser_go_forwardGo forward one step in browser history.
browser_clickClick a specific element on the page.
browser_typeType text into a specified input field.
browser_press_keySimulate a key press.
browser_wait_forWait for a specific page element to appear.
browser_waitPause execution for a fixed duration.
browser_screenshotCapture a screenshot of the current page.
browser_get_htmlGet the full HTML of the current page.
browser_get_textGet all visible text from the current page.
browser_scrollScroll to the bottom of the page.
browser_scroll_toScroll a specific element into view.
scrape_htmlScrape a URL and return its full HTML content.
scrape_markdownScrape a URL and return its content as Markdown.
scrape_screenshotCapture a high-quality screenshot of any webpage.
crawl_startStart an asynchronous crawl job from a base URL and return its job id.
crawl_cancelCancel an in-progress crawl job by its id.
crawl_resultPoll a crawl job by its id until it completes and return the crawled data.
ai_scraperCreate an AI Scraper task for ChatGPT, Gemini, Perplexity, Copilot, Google AI Mode, Google AI Overview, Grok, or Alexa.

Security Best Practices

When using Scrapeless MCP Server with LLMs (like ChatGPT, Claude, or Cursor), it's critical to handle all scraped or extracted web content with care. Web data is untrusted by default, and improper handling may expose your application to prompt injection or other security vulnerabilities.

✅ Recommended Practices
  • Never pass raw scraped content directly into LLM prompts. Raw HTML, JavaScript, or user-generated text may contain hidden injection payloads.
  • Sanitize and validate all extracted content. Strip or escape potentially harmful tags and scripts before using content in downstream logic or AI models.
  • Prefer structured extraction to free-form text. Use tools like scrape_html, scrape_markdown, or targeted browser_get_text with known-safe selectors to extract only the content you trust.
  • Apply domain or selector whitelisting when scraping dynamically generated pages, to restrict data flow to known and trusted sources.
  • Log and monitor all outbound requests made via browser or scraping tools, especially if you're handling sensitive data, tokens, or internal network access.
🚫 Avoid
  • Injecting scraped HTML directly into prompts
  • Letting users specify arbitrary URLs or CSS selectors without validation
  • Storing unfiltered scraped content for future prompt usage

Community

Contact Us

For questions, suggestions, or collaboration inquiries, feel free to contact us via:

Source: README.md at commit c5e0964

Tools

0
This server asks for a credential such as an API key, so SourceWeft could not read its tools without one and has not indexed them.

Version history

1
  1. v0.6.4LatestSep 16, 2026

Score

85% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 daysRequired25 pts
  • Auth declaredRequired10 pts
  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts