ScrapelessSAFE
Scrapeless Mcp Server
Overview
From the repository's own README, as read at the audited commit. Badges and raw HTML are left out.
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
- 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.
- 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.
- 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`.
e3ffbf7f3c9fOBSERVED · 2026-10-06Connect
Built from this server's own package name, version and transport as found in its source — not copied from anyone's documentation, so it cannot drift against a page we do not control. Replace the environment placeholders with a token scoped to the least it needs.
claude mcp add scrapeless-mcp-server --env SCRAPELESS_API_KEY=${SCRAPELESS_API_KEY} -- npx -y [email protected]Exposed tools (22)
21 read · 1 write · 0 destructive.
| Tool | Risk | Description |
|---|---|---|
browser_click | read | Click a specific element on the page. Restrictions: Requires a valid CSS selector for the target element. Valid: Click the button with selector |
browser_close | read | Closes the current session by disconnecting the cloud browser. This will terminate the recording for the session. |
browser_create | write | Create or reuse a cloud browser session using Scrapeless. Updates the active session. |
browser_get_html | read | Get the full HTML of the current page. Restrictions: Returns the entire raw HTML source code. Valid: Get the HTML of the current page to parse its structure. Invalid: Get only the visible text (use |
browser_get_text | read | Get all visible text from the current page. Restrictions: Extracts only text content, ignoring HTML tags. Valid: Get the text content of the current page for summarization. Invalid: Get the page |
browser_go_back | read | Go back one step in browser history. Restrictions: Only works if a previous page exists in the session history. Valid: After navigating from page A to B, go back to A. Invalid: Attempting to go back on the first page of a session. |
browser_go_forward | read | Go forward one step in browser history. Restrictions: Only works after a |
browser_goto | read | Navigate browser to a specified URL. Restrictions: Only for direct URL navigation, not for searches. Valid: Go to https://google.com. Invalid: Search for |
browser_press_key | read | Simulate a key press. Restrictions: Must specify a valid key name; optional target selector. Valid: Press Enter in #search. Invalid: Press a key without specifying the key name. |
browser_screenshot | read | Capture a screenshot of the current page. Restrictions: Can capture either the full page or the visible viewport. Valid: Take a screenshot of the current browser view. Invalid: Capture a screenshot of a specific element (not supported). |
browser_scroll | read | Scroll the current page to a specific position. Restrictions: Requires pixel coordinates for scrolling. Valid: Scroll to the bottom of the page (e.g., { x: 0, y: 10000 }). Invalid: Scroll to |
browser_scroll_to | read | Scroll a specific element into view. Restrictions: Requires a valid CSS selector for the target element. Valid: Scroll to the element |
browser_snapshot | read | Capture the complete structure of a webpage, including DOM and resources, for inspection and analysis. |
browser_type | read | Type text into a specified input field. Restrictions: Requires a CSS selector for an input/textarea and the text to type. Valid: Type |
browser_wait | read | Pause execution for a fixed duration. Restrictions: Requires a duration in milliseconds. Should be used sparingly. Valid: Wait for 2000 milliseconds. Invalid: Wait for a page to finish loading (use |
browser_wait_for | read | Wait for a specific page element to appear. Restrictions: Requires a valid CSS selector for the element to wait for. Valid: Wait for the element |
crawl_cancel | read | Cancel an in-progress crawl job by its id (the id returned by crawl_start). Returns the cancelled status. |
google_search | read | Universal Information Search Engine.Retrieves any data information; Explanatory queries (why, how).Comparative analysis requests |
google_trends | read | Get trending search data from Google Trends. Restrictions: Activated for queries about trends, popularity, or interest over time. Valid: Find the search interest for |
scrape_html | read | Scrape a URL and return its full HTML content. Restrictions: Activated for URLs that require JavaScript rendering or bot protection. Valid: Get HTML from a dynamic, JS-heavy single-page application. Invalid: Fetching a simple static page (use a standard HTTP client). |
scrape_markdown | read | Scrape a URL and return its content as Markdown. Restrictions: Best for articles, blog posts, and other text-heavy pages. Valid: Scrape a news article to get its readable content. Invalid: Scrape a complex web application dashboard. |
scrape_screenshot | read | Capture a high-quality screenshot of any webpage. Restrictions: Bypasses bot detection and CAPTCHAs using residential proxies. Valid: Get a screenshot of a price-checker page protected by Cloudflare. Invalid: Taking a screenshot of the local browser (use browser_screenshot) |
Trust audit
SAFEgrade B · trust 89/100 Nothing in the source contradicts what it says it does. Grade A is reserved for packages that have also passed the behavioural sandbox.
| Layer | What it checks | Result |
|---|---|---|
| L0 | Provenance & inventory | PASS |
| L1 | Static analysis of the code | PASS |
| L2 | Instruction surface (what it tells the agent) | PASS |
| L3 | Class-specific surface | PASS |
| L4 | Behavioural (sandbox) | SKIPPED |
What the source does
- Filesystem
- declared (4 observation(s))
- Network
- declared (4 observation(s))
- Shell
- none-observed
- Dependencies
- not all pinned
- Secrets in source
- none-found
Findings (9)
import { BASE_URL } from "../../config.js";import { API_KEY, BASE_URL, API_KEY_NAME } from "../../config.js";import { Context } from "../../context.js";import { API_KEY, BASE_URL, API_KEY_NAME } from "../../config.js";@chatmcp/sdk, @modelcontextprotocol/sdk, @scrapeless-ai/sdk, agents, axios, express, nanoid, puppeteer-core
assets/mcp-1.gif
assets/mcp-2.gif
assets/mcp-3.gif
assets/mcp-4.gif
Gates applied: no_behavioural_pass.
e3ffbf7f3c9ffull audit observations/trust-audit/mcp-server/scrapeless-ai__scrapeless.json · Report an issue / request a re-scanAudit history
Every audit this server has had. A grade with a past is a grade somebody is still checking.
| Date | Source | Verdict | Grade | Score | Change |
|---|---|---|---|---|---|
| 2026-10-06 | e3ffbf7f3c9f | SAFE | B | 89 | first audit |
Questions
What is the Scrapeless MCP server?
Scrapeless Mcp Server
What tools does Scrapeless expose?
22 in total: 21 read-only, 1 that write, and 0 that can delete or overwrite. Every one is listed on this page with its risk.
Is Scrapeless safe to connect to an agent?
The audit found nothing in the source that contradicts what it says it does, and graded it B (89/100). Grade A is held back for packages that have also passed a sandboxed behavioural run, which is why a clean server reads B.
What credentials does Scrapeless need?
It reads SCRAPELESS_API_KEY and SCRAPELESS_KEY from the environment. Give it a token scoped to the least it needs — an agent that can be talked into calling a tool can be talked into calling it with your credentials.
How does Scrapeless run?
It speaks sse, stdio and streamable-http, so it runs as a local process your client starts. It is published on npm as scrapeless-mcp-server at 0.6.3.
How current is this page?
The grade is for one exact copy of the source (e3ffbf7f3c9f), read on 2026-10-06. The repository is watched and re-audited when it changes.