{
  "markdown": "# QuanticData MCP Server\n\nConnect [QuanticData](https://quanticdata.io) to Claude, Cursor, Cline, and any\nMCP client. Gives an AI agent live web access — scrape, search, map, and crawl —\nthrough residential proxies with real-browser TLS fingerprints, so pages that\nblock ordinary bots come back clean. It also hands the agent raw proxy\nendpoints of every type (residential, mobile, datacenter, ISP, IPv6) from your\nactive plans, ready to plug into any HTTP client.\n\nIt calls the **public** QuanticData Scraper API with your own `qd_live_` key,\nso there are no internal secrets and you run it locally.\n\n## Tools\n\n| Tool | What it does |\n|------|--------------|\n| `scrape` | Scrape one URL → Markdown/HTML/text, including PDF/Office documents. Supports multi-format output, absolute link collection, JSON-LD metadata, structured CSS extraction, AI prompt/JSON-schema extraction, and `mode: summary`. |\n| `seo_audit` | Fetch a URL as a no-JS bot **and** fully rendered, return both SEO views + the diff (JS-only content, changed title/description, missing canonical) and bot-facing meta (robots, OG, JSON-LD). |\n| `search` | Structured Google/Bing/DuckDuckGo results. Set `render: true` for Google AI Overview, PAA, Knowledge Graph and other JS enrichments. |\n| `search_and_read` | SERP → fetch top pages → numbered citation-ready sources and one token-bounded context string ready for an AI prompt. |\n| `search_bulk` / `search_bulk_status` | Async multi-page pagination with merged organic results and page-one AI/zero-click enrichments. |\n| `map` | Fast URL discovery (sitemaps + homepage links), no full crawl. Compact by default: up to `limit` URLs (100) plus site-wide `total` and per-section `summary`; `group_by: path` for the path tree. |\n| `crawl` / `crawl_status` | Async BFS site crawl → Markdown per page; poll for progress. |\n| `batch` / `batch_status` | Scrape many URLs asynchronously; `mode: summary` for metadata-only items. Incremental polling via `since` cursor; page content only with `include_content`. |\n| `create_dataset` / `dataset_status` | Prompt-driven structured dataset collection with budget and row limits. |\n| `list_collectors` / `run_collector` / `collector_run_status` | Ready-made Collectors: run a versioned scraper with a semantic input (keyword + location, place id, product id, domain…) instead of URLs — Google Maps places, place reviews, Google Jobs/News/Shopping, product offers, hotels, local business leads, site contacts, company profile. Priced per delivered row; async runs poll by `run_id`, rows exportable as CSV. |\n| `list_proxies` | List your proxy services of every type — Residential Basic/Premium/Private, Mobile, Mobile V2, Datacenter, ISP, IPv6 — with bandwidth left, expiry and the `orderId` used to generate. |\n| `generate_proxies` | Ready-to-use proxy strings (credentials included) from any active plan: geo targeting (country/state/city/ISP/ASN), rotating or sticky sessions, HTTP or SOCKS5, several output formats. |\n| `proxy_locations` | Valid geo-targeting values per plan type: countries, states, cities, ASNs, or the full location tree with ISP codes. |\n| `whitelist_ip` | Manage IP-auth whitelisting (add/list/remove) for plans that support it, including the Mobile V2 IP-auth proxy list. |\n\n## Quick start\n\nNo install needed — `npx` fetches [quanticdata-mcp](https://www.npmjs.com/package/quanticdata-mcp) on demand (Node.js 18+).\n\n**Claude Code** (one command):\n\n```bash\nclaude mcp add quanticdata \\\n  -e QUANTICDATA_API_KEY=qd_live_your_key_here \\\n  -- npx -y quanticdata-mcp\n```\n\n**Claude Desktop / Cursor / Cline / any MCP client** (`claude_desktop_config.json`, `.cursor/mcp.json`, Cline's MCP settings, or `.mcp.json`):\n\n```json\n{\n  \"mcpServers\": {\n    \"quanticdata\": {\n      \"command\": \"npx\",\n      \"args\": [\"-y\", \"quanticdata-mcp\"],\n      \"env\": { \"QUANTICDATA_API_KEY\": \"qd_live_your_key_here\" }\n    }\n  }\n}\n```\n\n## Hosted endpoint (remote MCP)\n\nThe same server also runs as a hosted **Streamable HTTP** endpoint, for clients\nthat prefer a URL over a local package:\n\n```\nhttps://api.quanticdata.io/mcp\n```\n\nYour key travels per request in the `Authorization` header, so nothing is\nstored server-side and one endpoint serves every account:\n\n```bash\ncurl -X POST https://api.quanticdata.io/mcp \\\n  -H \"Authorization: Bearer qd_live_your_key_here\" \\\n  -H \"Content-Type: application/json\" \\\n  -H \"Accept: application/json, text/event-stream\" \\\n  -d '{\"jsonrpc\":\"2.0\",\"id\":1,\"method\":\"tools/list\"}'\n```\n\nThe endpoint accepts either header — `Authorization: Bearer qd_live_your_key_here`\n(preferred) or `X-Api-Key: qd_live_your_key_here` — so clients that can't set an\n`Authorization` header can send the key directly.\n\nIn a client that supports remote MCP servers, add it as an HTTP server with that\nURL and your key. For **Cline** (and any client that defaults to legacy SSE),\nset the transport type explicitly to `streamableHttp`:\n\n```json\n{\n  \"mcpServers\": {\n    \"quanticdata\": {\n      \"type\": \"streamableHttp\",\n      \"url\": \"https://api.quanticdata.io/mcp\",\n      \"headers\": { \"Authorization\": \"Bearer qd_live_your_key_here\" }\n    }\n  }\n}\n```\n\n`initialize` and `tools/list` answer without a key so directories and inspectors\ncan introspect the server; tool calls need one.\n\nSelf-hosting the endpoint is a second binary in this same package:\n\n```bash\nQUANTICDATA_API_KEY=qd_live_… PORT=9310 npx -y quanticdata-mcp-remote\n```\n\n## Run from source (development)\n\n```bash\nnpm install\nnpm run build\n```\n\nThen point the client at the local build instead of npx:\n\n```json\n{\n  \"mcpServers\": {\n    \"quanticdata\": {\n      \"command\": \"node\",\n      \"args\": [\"/absolute/path/to/quanticdata-mcp-server/dist/index.js\"],\n      \"env\": {\n        \"QUANTICDATA_API_KEY\": \"qd_live_your_key_here\"\n      }\n    }\n  }\n}\n```\n\n## Env\n\n| Var | Default | Notes |\n|-----|---------|-------|\n| `QUANTICDATA_API_KEY` | — | **Required.** Your `qd_live_` key. |\n| `QUANTICDATA_API_BASE` | `https://api.quanticdata.io/v1` | Override for staging/self-host. |\n\n## Example prompts\n\n- \"Scrape the pricing page at example.com and give me the plans and prices.\"\n- \"Search Google Shopping for 'nintendo switch oled' in the US and list the cheapest 5.\"\n- \"Map docs.example.com, then crawl only the /guides/ pages and summarize them.\"\n- \"List my proxy plans and generate 5 sticky US residential proxies as socks5 URLs.\"\n- \"Get me a rotating mobile proxy in Germany and whitelist my server IP 203.0.113.7.\"\n\n## Privacy Policy\n\nFull policy: <https://quanticdata.io/privacy>\n\n**What this server sends.** It runs on your machine and talks only to the public\nQuanticData API at `https://api.quanticdata.io/v1`, authenticated with\nyour own `qd_live_` key. Each call carries the arguments you (or your agent)\npassed — the target URL or query, and any extraction prompt. Nothing else on your\nmachine is read or transmitted: the server has no filesystem, shell or clipboard\naccess.\n\n**What we collect.** Account data you give us (name, email, billing details) and\na request log kept for billing, abuse prevention and support: target URL or\nquery, timestamp, response status, bytes transferred and the API key used. We do\n**not** retain scraped page content beyond what is needed to return your result.\n\n**Data you collect through the service.** You decide what public web data to\ncollect and **you are the controller of that data** — we process it on your\nbehalf only to fulfil your request. You are responsible for using the service\nlawfully, for respecting the terms of the sites you access, and for any personal\ndata you collect through it.\n\n**Sharing.** We do not sell personal data. We share it only with the processors\nthat run the service — payment providers, email delivery, hosting, CDN and\nanalytics — under contracts that bind them to protect it, and with the upstream\nproxy networks that route your traffic (connection metadata only, never your\naccount details). We may disclose data where required by law.\n\n**Retention.** Account data for as long as the account exists; request logs on a\nrolling window for billing and abuse investigation. You can request deletion at\nany time.\n\n**Your key.** Claude Desktop stores it in the OS keychain and passes it to this\nserver as an environment variable. It is never written to the bundle and never\nsent anywhere except the QuanticData API. Revoke or rotate it at\n<https://app.quanticdata.io/api-keys>.\n\n**Contact.** <support@quanticdata.io>\n",
  "bytes": 8412,
  "sha": "a7a691b262387cd39a0eea38581dc5fb54c4dae52c70e6aceea500667a57ae0b",
  "repo_slug": "quantumproxies/quanticdata-mcp-server",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_quantumproxies_quanticdata_mcp_d0c0891c/readme"
}