Give Claude Code, Claude Desktop, Cursor or any MCP client live web access: scrape a page, run a search, map or crawl a site, audit a URL, and run 31 ready-made collectors.
Server (single file, zero dependencies): quanticdata-mcp-server · product page: quanticdata.io/mcp-server
git clone https://github.com/quantumproxies/quanticdata-mcp-serverGet a key at app.quanticdata.io.
claude mcp add quanticdata \
-e QUANTICDATA_API_KEY=qd_live_your_key_here \
-- node /absolute/path/to/quanticdata-mcp-server/server.mjsSee claude_desktop_config.json in this gist.
See cursor-mcp.json in this gist. Guide:
how to use MCP in Cursor.
scrape · search · map · crawl + crawl_status · seo_audit ·
list_collectors · run_collector · collector_run_status
- "Map quanticdata.io, then read the five newest blog posts and summarise the themes."
- "Search
serp api pricingin the US and Germany and tell me how the top ten differ." - "Is our pricing page indexable without JavaScript?"
- "Use list_collectors, then pull 40 dental clinics in Austin with local_business_leads."
Let the agent read the catalogue before it picks a collector — the schemas are published so a model can choose correctly.
Background: how MCP servers work · is an MCP server like an API?