QuanticData MCP server
Provides AI agents live web access through scraping, multi-engine search, site mapping, crawling, SEO audits, and 31 data collectors via natural language tool calls.
README
QuanticData MCP server — give Claude, Cursor and any MCP client live web access
A single-file, zero-dependency MCP server that puts the QuanticData Data APIs in front of an AI agent: scrape a page, run a Google/Bing/DuckDuckGo/Yandex search, map or crawl a site, audit a URL for SEO, and run any of the 31 ready-made Collectors with a semantic input.
No SDK, no build step, no node_modules. Node.js 18+ and one file.
git clone https://github.com/quantumproxies/quanticdata-mcp-server
cd quanticdata-mcp-server
QUANTICDATA_API_KEY=qd_live_your_key_here node server.mjs
Get a key at app.quanticdata.io — there is a free monthly allowance and no card is required; see the pricing on quanticdata.io for the current figure.
Install it in your client
Claude Code
claude mcp add quanticdata \
-e QUANTICDATA_API_KEY=qd_live_your_key_here \
-- node /absolute/path/to/quanticdata-mcp-server/server.mjs
Claude Desktop — claude_desktop_config.json
{
"mcpServers": {
"quanticdata": {
"command": "node",
"args": ["/absolute/path/to/quanticdata-mcp-server/server.mjs"],
"env": { "QUANTICDATA_API_KEY": "qd_live_your_key_here" }
}
}
}
Cursor — .cursor/mcp.json, same shape as above.
Any client that speaks stdio MCP works: the server implements initialize, tools/list,
tools/call and ping, which is the complete surface for a tools-only server.
Tools
| Tool | What the agent gets | Price |
|---|---|---|
scrape |
one URL → Markdown / HTML / text, CSS or AI extraction, optional render | $0.0002 |
search |
organic results + related searches, 4 engines, 18 verticals | from $0.0005 |
map |
every URL of a site from sitemaps + homepage links, with totals | $0.0005 |
crawl / crawl_status |
async BFS crawl → Markdown per page | $0.0003/page |
seo_audit |
no-JS vs rendered view of a URL, diffed, plus bot-facing meta | $0.0012 |
list_collectors |
the catalogue: schemas, examples, health, your unit price | free |
run_collector |
run one Collector on a semantic input | from $0.0004/row |
collector_run_status |
one run and its delivered rows | free |
Everything is pay-per-success: a call that fails costs nothing.
Try it without a client
node smoke-test.mjs # handshake + tools/list, no API key needed
Or drive it by hand — it is newline-delimited JSON-RPC on stdin:
printf '%s\n' \
'{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2025-06-18","capabilities":{},"clientInfo":{"name":"cli","version":"1"}}}' \
'{"jsonrpc":"2.0","id":2,"method":"tools/list"}' \
| node server.mjs
Prompts that work well
- "Map quanticdata.io, then scrape the five most recent blog posts and summarise the themes."
- "Search for
serp api pricingin the US and Germany and tell me how the top ten differ." - "Run an SEO audit on our pricing page — is it indexable without JavaScript?"
- "Use
list_collectors, then pull 40 dental clinics in Austin withlocal_business_leads."
The last one is the pattern worth internalising: let the agent read the catalogue first, then pick the collector. The schemas are published precisely so a model can choose correctly.
Configuration
| Variable | Default | Notes |
|---|---|---|
QUANTICDATA_API_KEY |
— | required; keys look like qd_live_… |
QUANTICDATA_API_BASE |
https://api.quanticdata.io/v1 |
point it elsewhere for a proxy or a staging host |
Errors from the API come back as tool results with isError: true rather than protocol errors,
so the model can read the message and correct itself instead of the conversation dying.
Related
- MCP server page · Documentation
- How MCP servers work · Is an MCP server like an API?
- How to create an MCP server · How to use MCP in Cursor
- Web Data API for AI · Browser AI agents
MIT licensed.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.