ScrapeUnblocker Remote MCP Server
OfficialProvides a tool to run Google searches and retrieve organic results as JSON, bypassing anti-bot measures via ScrapeUnblocker.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ScrapeUnblocker Remote MCP Serversearch Google for latest AI news"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
ScrapeUnblocker remote MCP server
A hosted (HTTP) Model Context Protocol server for ScrapeUnblocker, deployed as a Vercel serverless function. It lets claude.ai (web and mobile), Claude Desktop, Claude Code, and any other MCP client fetch any web page's HTML - or AI-parsed JSON, or Google results - through ScrapeUnblocker's anti-bot API, using your own API key.
Prefer a local install with no hosting? Use the stdio package instead:
scrapeunblocker-mcp.
Endpoint
https://mcp.scrapeunblocker.com/mcp?key=YOUR_API_KEYGet your key at https://app.scrapeunblocker.com. Auth is dual-mode:
A. Bring your own key (custom connector) - the key can be supplied three ways:
?key=YOUR_KEY(or?token=YOUR_KEY) in the URL - simplest for claude.ai.Authorization: Bearer YOUR_KEYheader (a non-JWT value).x-scrapeunblocker-key: YOUR_KEYheader.
B. OAuth 2.1 (for the claude.ai Connectors Directory) - the server is an OAuth
Resource Server (MCP auth spec rev 2025-11-25) backed by Auth0 as the Authorization
Server. Claude runs the OAuth flow, sends an Auth0 JWT as Authorization: Bearer, and
the server resolves that user's ScrapeUnblocker key server-side (the token is never
passed through to the backend, per RFC 8707). OAuth activates only when the env vars
below are set; without them the server is static-key only.
OAuth configuration (maintainers)
Env var | Purpose |
| Auth0 issuer URL, e.g. |
| Canonical MCP URI = the Auth0 API Identifier, |
| Optional namespaced claim carrying the user's email (set by an Auth0 Post-Login Action), e.g. |
| Optional override for the RFC 9728 metadata URL advertised in |
| utils-api base for the |
| IAM creds (SigV4, |
Discovery endpoints served (via vercel.json rewrites):
/.well-known/oauth-protected-resource and /.well-known/oauth-protected-resource/mcp.
Related MCP server: pure.md MCP Server
Add it to claude.ai
Settings → Connectors → Add custom connector.
Paste your personalised URL:
https://mcp.scrapeunblocker.com/mcp?key=YOUR_API_KEYSave. The tools appear across claude.ai web, mobile, and Claude Desktop.
Add it to Claude Code
claude mcp add --transport http scrapeunblocker "https://mcp.scrapeunblocker.com/mcp?key=YOUR_API_KEY"Tools
Tool | What it does |
| Fetch the fully rendered HTML of a URL. |
| Fetch a page and return AI-parsed structured JSON. |
| Run a Google search and return organic results as JSON. |
Deploy (maintainers)
This is a standard Vercel project - no build step, the function lives in api/mcp.ts.
vercel # preview
vercel --prod # productionThen point the mcp.scrapeunblocker.com domain at the Vercel project. Scraping calls
can be slow, so the function's maxDuration is set to 60s (raise it on a paid Vercel
plan if you hit timeouts on heavy pages).
License
MIT
This server cannot be installed
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/ScrapeUnblocker/scrapeunblocker-mcp-remote'
If you have feedback or need assistance with the MCP directory API, please join our Discord server