Browser Use
Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.
作者提供的说明(英文原文)
Live web access for agents: scrape, SERP search, crawl/map, 100+ collectors, datasets, proxies.
这三项永远不会合并成一个分数:意见、测量和人气是不同的东西。
我们还没有为它写通俗的介绍。下面是我们从注册中心读取到的事实。
选择你使用的 AI 应用,然后复制设置。
QUANTICDATA_API_KEY, Authorization标为机密的值是你账户的钥匙。千万不要分享给别人,也不要粘贴到聊天里。
你需要
你用的是哪个应用?
在上方选择你的应用。我们会记住它,下次按钮会显示“安装到 …”。
这个地址需要在请求的 header 中放入密钥,而添加连接器的菜单无法设置。请改用 Claude Code、Cursor 或 VS Code。
链接指向作者自己的文件;我们不托管也不重新打包它。打开文件后,Claude Desktop 会进行安装。
在终端中运行这条命令
claude mcp add --transport http quanticdata https://api.quanticdata.io/mcp --header 'Authorization: your-value'claude mcp add quanticdata --env QUANTICDATA_API_KEY=your-value -- npx -y quanticdata-mcp运行前请先填写空着的值。
粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"quanticdata": {
"url": "https://api.quanticdata.io/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"quanticdata": {
"command": "npx",
"args": [
"-y",
"quanticdata-mcp"
],
"env": {
"QUANTICDATA_API_KEY": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"quanticdata": {
"type": "http",
"url": "https://api.quanticdata.io/mcp",
"headers": {
"Authorization": "your-value"
}
}
}
}粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"quanticdata": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"quanticdata-mcp"
],
"env": {
"QUANTICDATA_API_KEY": "your-value"
}
}
}
}浏览器会先询问是否打开应用,然后应用会显示设置并请你确认。密钥的值会留空,由你自己填写。
这个地址需要在请求的 header 中放入密钥,而添加连接器的菜单无法设置。请改用 Claude Code、Cursor 或 VS Code。
你的选择通过 Cookie 保存在这台设备上,无需账户。
Authorization 机密 HTTP header这些设置是根据作者在注册中心的条目生成的。如果 README 的写法不同,请以 README 为准。
我们还没有读取这个服务器的工具列表;我们会轮流检查各个端点。
我们检查的是任何人都能看到的信息;我们没有阅读代码。不适用的检查项不计入总数。 · 检查于 2026年11月7日
注册名称已通过 GitHub 账户 quantumproxies 验证,该账户拥有此仓库
我们还没有从 GitHub 读取这个仓库
我们还没有从 GitHub 读取这个仓库
尚未检查;我们会轮流检查各个端点
尚未检查;我们会轮流检查各个端点
尚未检查;我们会在检查端点时读取工具列表
与注册中心里这个分类中所有活跃的服务器比较。只有当发布者拥有该仓库时,星标数才计入。
它在 1 项适用的基础检查中通过了 1 项。我们没有阅读代码。在添加密钥或令牌之前,请先看看这个服务器要求哪些权限,并使用只具备所需权限的密钥。
你需要填写:QUANTICDATA_API_KEY, Authorization
两种方式都可以:安装在你的电脑上,或者连接云端版本。
GitHub 仓库最后更新于–,最新版本(0.11.5)于34天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。它通过 URL 连接,所以接受远程 MCP 服务器的应用也可以使用,例如开启开发者模式的 ChatGPT。
同一分类中有:Browser Use, Chrome DevTools MCP, MCP Server Browser
同一分类中其他作者的服务器,按星标数排序。
如何看卡片:★ GitHub 星标i三大支柱:评价 · 检查 · 使用情况i更新 = 最新版本发布到注册中心的时间i
Browser agents and stealth cloud browsers for AI: run web tasks, fill forms, extract data.
MCP server for Chrome DevTools
MCP server for browser use access
按原文从作者的仓库复制。PopNx MCP 没有审查或背书其内容。HTML、图片和脚本已被移除。链接会离开本站。
Connect QuanticData to Claude, Cursor, and any MCP client. Gives an AI agent live web access — scrape, search, map, and crawl — through residential proxies with real-browser TLS fingerprints, so pages that block ordinary bots come back clean. It also hands the agent raw proxy endpoints of every type (residential, mobile, datacenter, ISP, IPv6) from your active plans, ready to plug into any HTTP client.
It calls the public QuanticData Scraper API with your own qd_live_ key, so there are no internal secrets and you run it locally.
| Tool | What it does |
|---|---|
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. |
unlock | Web Unlocker: replay any HTTP request (method, headers, body) through a residential exit with a real browser TLS fingerprint, retry on a fresh IP, escalate a blocked GET to a real browser. Returns the raw response (status, headers, body); a still-blocked page comes back flagged (blocked, blockClass, vendor), never as a silent 200. Interactive captchas are not solved (blockClass: "captcha"). |
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). |
ai_visibility | Can ChatGPT, Claude, Perplexity, Google AI Overview and Bing Copilot read and cite a page? On-page audit (24 AI crawlers in robots.txt, Content-Signal, a fetch as GPTBot, noindex/nosnippet/noai, text without JS, JSON-LD entities, answer-shaped copy, dates with age, author, sources) scored per pillar with blockers, evidence and fixes — plus an optional citation panel that asks the engines and reports cited / mentioned / rank, share of voice and who wins the questions you are absent from. |
search | Structured Google/Bing/DuckDuckGo results. Set render: true for Google AI Overview, PAA, Knowledge Graph and other JS enrichments. |
search_and_read | SERP → fetch top pages → numbered citation-ready sources and one token-bounded context string ready for an AI prompt. |
search_bulk / search_bulk_status | Async multi-page pagination with merged organic results and page-one AI/zero-click enrichments. |
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. |
crawl / crawl_status | Async BFS site crawl → Markdown per page; poll for progress. |
batch / batch_status | Scrape many URLs asynchronously; mode: summary for metadata-only items. Incremental polling via since cursor; page content only with include_content. |
create_dataset / dataset_status | Prompt-driven structured dataset collection with budget and row limits. |
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. |
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. |
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. |
proxy_locations | Valid geo-targeting values per plan type: countries, states, cities, ASNs, or the full location tree with ISP codes. |
whitelist_ip | Manage IP-auth whitelisting (add/list/remove) for plans that support it, including the Mobile V2 IP-auth proxy list. |
report | Send feedback to the team from inside the agent: a bug (wrong/empty result, error, blocked page), a missing feature or collector, a question. Works without an API key. |
No install needed — npx fetches quanticdata-mcp on demand (Node.js 18+).
Claude Code (one command):
claude mcp add quanticdata \
-e QUANTICDATA_API_KEY=qd_live_your_key_here \ -- npx -y quanticdata-mcp
Claude Desktop / Cursor / any MCP client (claude_desktop_config.json, .cursor/mcp.json, or .mcp.json):
{
"mcpServers": { "quanticdata": { "command": "npx", "args": ["-y", "quanticdata-mcp"], "env": { "QUANTICDATA_API_KEY": "qd_live_your_key_here" } } } }
The same server also runs as a hosted Streamable HTTP endpoint, for clients that prefer a URL over a local package:
https://api.quanticdata.io/mcp
The endpoint supports the MCP authorization spec (OAuth 2.1). In a client that supports it, add the URL above as a remote server and nothing else:
MCP · appears on the dashboard API keys page; delete it to disconnect the client.Under the hood: authorization server metadata at https://app.quanticdata.io/.well-known/oauth-authorization-server, protected resource metadata at https://api.quanticdata.io/.well-known/oauth-protected-resource/mcp, dynamic client registration (RFC 7591) and Client ID Metadata Documents, PKCE (S256) required, 1-hour access tokens with rotating refresh tokens, tokens bound to this endpoint (RFC 8707). Usage is billed to your balance like any key.
Clients that take a bearer token can skip OAuth: the key travels per request in the Authorization header (or X-Api-Key), nothing is stored server-side.
curl -X POST https://api.quanticdata.io/mcp \
-H "Authorization: Bearer qd_live_your_key_here" \ -H "Content-Type: application/json" \ -H "Accept: application/json, text/event-stream" \ -d '{"jsonrpc":"2.0","id":1,"method":"tools/list"}'
A request with neither a token nor a key gets 401 with a WWW-Authenticate header pointing at the metadata above: that is what makes OAuth-capable clients start the sign-in.
Self-hosting the endpoint is a second binary in this same package. With QUANTICDATA_API_KEY set it serves that one account to callers that send no credential:
QUANTICDATA_API_KEY=qd_live_… PORT=9310 npx -y quanticdata-mcp-remote
npm install
npm run build
Then point the client at the local build instead of npx:
{
"mcpServers": { "quanticdata": { "command": "node", "args": ["/absolute/path/to/scraper-mcp/dist/index.js"], "env": { "QUANTICDATA_API_KEY": "qd_live_your_key_here" } } } }
| Var | Default | Notes |
|---|---|---|
QUANTICDATA_API_KEY | — | Required. Your qd_live_ key. |
QUANTICDATA_API_BASE | https://api.quanticdata.io/v1 | Override for staging/self-host. |
QUANTICDATA_TOOLS | all 28 | Load only some tools: names (search,scrape) or a preset (lite, web, research, collectors, proxies). See below. |
Self-hosted remote endpoint only (quanticdata-mcp-remote), optional:
| Var | Default | Notes |
|---|---|---|
MCP_OAUTH_RESOURCE | https://api.quanticdata.io/mcp | This endpoint as an OAuth resource. |
MCP_OAUTH_ISSUER | https://app.quanticdata.io | Authorization server advertised in the resource metadata. |
MCP_OAUTH_INTROSPECT_URL | http://127.0.0.1:3090/api/v1/internal/oauth/introspect | Where OAuth access tokens are checked. |
MCP_INTERNAL_TOKEN | — | Secret for the introspection call. Unset = only API keys are accepted. |
The 28 tool definitions are about 14,000 tokens. A local model on Ollama's default 4K context cannot hold them, and a 32K context loses almost half its room before the first page. Load fewer tools:
| Preset | Tools | Definition tokens |
|---|---|---|
lite | search_and_read | ~360 |
web | search, search_and_read, scrape | ~4,200 |
research | web + map, batch, batch_status | ~5,100 |
collectors | list_collectors, run_collector, collector_run_status | ~830 |
proxies | list_proxies, generate_proxies, proxy_locations, whitelist_ip | ~1,800 |
Over stdio set QUANTICDATA_TOOLS=web. On the hosted endpoint add ?tools=web to the URL and send your API key as a Bearer header: https://api.quanticdata.io/mcp?tools=web. Names can be combined: ?tools=lite,collectors.
Full policy: https://quanticdata.io/privacy
What this server sends. It runs on your machine and talks only to the public QuanticData API at https://api.quanticdata.io/v1, authenticated with your own qd_live_ key. Each call carries the arguments you (or your agent) passed — the target URL or query, and any extraction prompt. Nothing else on your machine is read or transmitted: the server has no filesystem, shell or clipboard access.
What we collect. Account data you give us (name, email, billing details) and a request log kept for billing, abuse prevention and support: target URL or query, timestamp, response status, bytes transferred and the API key used. We do not retain scraped page content beyond what is needed to return your result.
Data you collect through the service. You decide what public web data to collect and you are the controller of that data — we process it on your behalf only to fulfil your request. You are responsible for using the service lawfully, for respecting the terms of the sites you access, and for any personal data you collect through it.
Sharing. We do not sell personal data. We share it only with the processors that run the service — payment providers, email delivery, hosting, CDN and analytics — under contracts that bind them to protect it, and with the upstream proxy networks that route your traffic (connection metadata only, never your account details). We may disclose data where required by law.
Retention. Account data for as long as the account exists; request logs on a rolling window for billing and abuse investigation. You can request deletion at any time.
Your key. Claude Desktop stores it in the OS keychain and passes it to this server as an environment variable. It is never written to the bundle and never sent anywhere except the QuanticData API. Revoke or rotate it at https://app.quanticdata.io/api-keys.
Contact.