ScrapeUnblocker MCP Server
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SCRAPEUNBLOCKER_KEY | Yes | Your ScrapeUnblocker API key |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| fetch_htmlA | Fetch the fully rendered HTML of any web page through ScrapeUnblocker, bypassing anti-bot protection (Cloudflare, DataDome, PerimeterX, Akamai, Shape). Use this when a normal fetch is blocked (403/429, captcha, 'access denied') or when the page needs a real browser to render. Returns the raw HTML as text. For pages that need interaction (accept a cookie banner, click a tab, type into a search box, scroll to trigger lazy loading) pass |
| list_elementsA | Load a page through ScrapeUnblocker and return a JSON list of its notable elements (links, inputs, buttons, selects, etc.) with a ready-to-use |
| fetch_parsedA | Fetch a web page through ScrapeUnblocker and return AI-parsed structured JSON instead of raw HTML (e.g. product details, article content). Best for extracting fields from product, listing or article pages without writing your own HTML parsing. |
| google_searchA | Run a Google search through ScrapeUnblocker and return the organic results as structured JSON. Use this to discover URLs before fetching them. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 4 tools
The four tools have mostly distinct purposes: fetch_html retrieves raw HTML with optional interaction, list_elements extracts selectable elements, fetch_parsed returns structured JSON, and google_search performs web searches. However, fetch_html and fetch_parsed could be confused since both fetch pages; the distinction (raw HTML vs. parsed JSON) is clear from descriptions but could still cause misselection if an agent needs structured data but picks fetch_html.
Tool names follow a consistent verb_noun pattern: fetch_html, list_elements, fetch_parsed, google_search. All start with a verb (fetch, list, google) followed by a noun. Minor inconsistency: 'google_search' mixes a brand (google) with the action, but the pattern is clear and predictable.
With 4 tools, the server is well-scoped for its purpose of scraping and unblocking web pages. Each tool serves a distinct function: fetching raw HTML, discovering elements, getting parsed data, and searching. This is a tight, purposeful set without redundancy.
The set covers the core scraping workflow: discover URLs (google_search), inspect page structure (list_elements), fetch with or without interaction (fetch_html), and extract structured data (fetch_parsed). However, there is no tool to handle common post-fetch actions like saving results or managing sessions, and no tool for custom parsing beyond fetch_parsed's AI output. The fetch_html tool includes browser steps, but there is no tool for handling cookies or persistent sessions. Still, for a minimal scraping server, the workflow is complete.