UpRock
Fetch pages, search the web and search video from real devices in chosen countries
- Pricing
- Paid
- Platforms
- API, CLI
- Runs
- Remotely
- Version
- 0.5.5
- Listing updated
- 3 days ago
About UpRock
UpRock is a paid MCP server for web search and scraping. It runs as a hosted remote server, so there is nothing to install locally.
Instead of data-centre proxies, UpRock routes each request through a real browser on a device owned by a community member in the country you pick. The site describes thousands of devices in 60+ countries, so an agent sees local prices, search results and region-locked content as a person there would. A crawl runs the page's JavaScript and returns markdown, takes 5 to 20 seconds, and nothing is cached.
The tools cover crawling (including from a mobile device), multi-engine web research that merges several search engines, a search across a shared index of public video down to the second, and a verify check that tests a site from several regions with status, screenshot and load speed. The MCP example shows crawl_fetch taking a url, country and device_type. A CLI (npm i -g uprock) and a REST endpoint do the same jobs.
There is no free tier beyond a few key-less test crawls a day. Everything spends prepaid credits bought by card or USDC; paying with the project's UPT token is 20% cheaper. Failed requests are not billed.
Install
Run in a terminal
claude mcp add --transport http mcp https://mcp.uprock.ai/mcpAdd to Settings → Connectors → Add custom connector
https://mcp.uprock.ai/mcpAdd to ~/.cursor/mcp.json
{
"mcpServers": {
"mcp": {
"url": "https://mcp.uprock.ai/mcp"
}
}
}Add to .vscode/mcp.json
{
"servers": {
"mcp": {
"type": "http",
"url": "https://mcp.uprock.ai/mcp"
}
}
}Add to ~/.codeium/windsurf/mcp_config.json
{
"mcpServers": {
"mcp": {
"serverUrl": "https://mcp.uprock.ai/mcp"
}
}
}Add to your client's MCP settings (most use this shape)
{
"mcpServers": {
"mcp": {
"type": "http",
"url": "https://mcp.uprock.ai/mcp"
}
}
}Tools this server provides (1)
Taken from the project documentation; the running server may differ.
- crawl_fetch
- Fetches a URL from a real device in a chosen country as markdown
What it does
- Real-device crawling
- Fetches rendered pages as markdown from a real browser on a device in your chosen country.
- Multi-engine research
- One query fans out across several search engines and merges results.
- Video search
- Searches a shared index of public video, down to the second.
- Site verification
- Checks a site from several regions, returning status, screenshot and load speed.
- Mobile crawling
- Optionally fetches from a real phone at a higher price.
- Prepaid credits
- Credits never expire and failed requests are not billed.
Good for
- Check local prices on a competitor page in Germany
- Compare search results across countries
- Fetch pages that block data-centre crawlers
- Search inside public video for a spoken phrase
- Verify a site loads from several regions
Pricing
Paid
Prepaid credits: crawl from $0.50 per 1,000 pages; UPT payment is 20% cheaper
Prices change. Check uprock.ai before you buy.
UpRock FAQ
How much does it cost?
Crawl is $0.50 per 1,000 pages, mobile crawl $0.75, web research and video search $1 per 1,000 queries, verify $1.50 per 1,000 checks.
Is there a free tier?
No. The site offers only a few test crawls a day without a key.
How slow is a crawl?
5 to 20 seconds, because a real browser loads the page and nothing is cached.
How do I authenticate?
Send a Bearer UPROCK_API_KEY header to the MCP server.
Is UpRock free?
No. UpRock is a paid product.
How do I add UpRock to Claude Code?
Run this command in your terminal: claude mcp add --transport http mcp https://mcp.uprock.ai/mcp
What are the best alternatives to UpRock?
The closest alternatives to UpRock are Scrapling MCP Server, Firecrawl MCP Server, SearXNG Search, NeuralVerge and AI-Powered directory.
Alternatives to UpRock

Scrapling MCP Server
MCP serverMCP server for AI clients to scrape sites with HTTP and stealth browser sessions
Runs locally- 17 tools
- Open source
- 104K GitHub stars
- Web search and scraping

Firecrawl MCP Server
MCP serverMCP server that lets AI agents search, scrape and interact with web pages
- 3 tools
- Remote
- Freemium
- 7.8K GitHub stars
- Web search and scraping

SearXNG Search
MCP serverMCP server for web search and page reading through a SearXNG instance
Runs locally- 3 tools
- Open source
- 1.4K GitHub stars
- Web search and scraping

NeuralVerge
MCP serverStructured, source-tagged business and people data from 300+ sources for agents
- 200 tools
- Remote
- Free trial
- 1 GitHub star
- Web search and scraping

AI-Powered directory
MCP serverSearch AI tools, agents and MCP servers and get install configs from inside your AI assistant.
- 4 tools
- Remote
- Free
- Developer tools

Shopify MCP Server (any store)
MCP serverHosted MCP server that returns any Shopify store's products, prices and stock
Not checked yet- 4 tools
- Remote
- Paid
- E-commerce