Web Scraping AI MCP Server

A Model Context Protocol (MCP) server implementation that integrates with WebScraping.AI for web data extraction capabilities - Chromium JavaScript rendering, rotating datacenter/residential/stealth proxies, and AI-powered question answering and structured field extraction on any page. It runs locally over stdio via the published package.

People who work with Webscraping and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in JavaScript.

VERIFIED ACTIVE

LAST COMMIT 2026-09-27 · ★ 44 · #16 OF 97 MAINTAINED WEB SCRAPING · VERIFIED 2026-09-30

JavaScript servers · how we verify → /methodology

01 · Install Web Scraping AI

before you install - you'll need

Set WEBSCRAPING_AI_API_KEY before connecting. WEBSCRAPING_AI_CONCURRENCY_LIMIT, WEBSCRAPING_AI_ENABLE_CONTENT_SANDBOXING, WEBSCRAPING_AI_DEFAULT_PROXY_TYPE, WEBSCRAPING_AI_DEFAULT_JS_RENDERING, WEBSCRAPING_AI_DEFAULT_TIMEOUT, WEBSCRAPING_AI_DEFAULT_JS_TIMEOUT are optional or environment-specific per the README.

Claude Code

claude mcp add webscraping-ai-webscraping-ai-mcp-server -- npx -y webscraping-ai-mcp

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "webscraping-ai-webscraping-ai-mcp-server": {
      "command": "npx",
      "args": [
        "-y",
        "webscraping-ai-mcp"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license no standard license detected - usage rights unclear; check the repo before commercial use

npm package webscraping-ai-mcp - unscoped; check the name against the project README before installing

registry namespace io.github.webscraping-ai is GitHub-verified and matches the repo owner

03 · What Web Scraping AI can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

Latest releases

v1.2.2 · 2026-09-26

Every tool now declares a title and MCP annotations (readOnlyHint, destructiveHint: false, openWorldHint), and every description links its API docs section. Tools that had no description now carry the same descriptions…

v1.2.1 · 2026-09-26

Security · Dependency updates for open Dependabot alerts: @modelcontextprotocol/sdk 1.7 → 1.30.1 (ReDoS, DNS-rebinding default, request body size limits; pulls patched express/body-parser/qs/path-to-regexp) and axios…

v1.2.0 · 2026-09-25

Added · webscraping_ai_data tool for the new /data endpoint: structured JSON (request_parameters with provider/type, parse_status, data) for a page on a supported site, from its normal URL. Params url (required…

04 · Who maintains Web Scraping AI

WebScraping.AI is maintained by webscraping-ai. It's the only MCP server we track from this author; the repo dates to Apr 2025.

05 · Facts

repository: github.com/webscraping-ai/webscraping-ai-mcp-server
website: https://webscraping.ai/
category: web scraping - ranked #16 of 97 actively-maintained web scraping servers as of 2026-09-30.
release cadence: 6 releases in the last 90 days (latest 2026-09-26)
registry: io.github.webscraping-ai/webscraping-ai (active, first published 2026-07-24)
packages: npm:webscraping-ai-mcp

06 · Web Scraping AI FAQ

What is Web Scraping AI?

Is Web Scraping AI still maintained?

Yes - as of 2026-09-30, its last commit was 2026-09-27 and it shipped 6 releases in the last 90 days. We re-verify nightly.

How do I install Web Scraping AI?

Run `npx -y webscraping-ai-mcp`. The README documents 7 environment variables (WEBSCRAPING_AI_API_KEY, WEBSCRAPING_AI_CONCURRENCY_LIMIT, WEBSCRAPING_AI_ENABLE_CONTENT_SANDBOXING…) to set first. Set WEBSCRAPING_AI_API_KEY before connecting. WEBSCRAPING_AI_CONCURRENCY_LIMIT, WEBSCRAPING_AI_ENABLE_CONTENT_SANDBOXING, WEBSCRAPING_AI_DEFAULT_PROXY_TYPE, WEBSCRAPING_AI_DEFAULT_JS_RENDERING, WEBSCRAPING_AI_DEFAULT_TIMEOUT, WEBSCRAPING_AI_DEFAULT_JS_TIMEOUT are optional or environment-specific per the README. You can also paste the ready-made client config above.

Does Web Scraping AI run locally?

Yes - it's a stdio server: it runs on your machine (via npx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Web Scraping AI

Alternatives to Web Scraping AI

Maintained web scraping servers if Web Scraping AI isn't the fit.

Pairs well with

Servers that cover what Web Scraping AI doesn't - only shown when the pairing reason fits the companion.

More web scraping MCP servers · Wopee MCP · Crawlberg · Xquik MCP Server · AI-First Scraper · Zenrows MCP

More JavaScript MCP servers · eKYC Suite · Registry MCP Server · Aesthetic Computer · Fast News MCP · Work OS · see all