BrowserSolver

com.browsersolver由 browsersolver.com 發布官方發布者v0.1.0更新於 Nov 7, 2026

Unlock, render, crawl and screenshot any website — anti-bot bypass and technology detection through…

已驗證Streamable HTTP可網頁執行網頁搜尋與抓取瀏覽器自動化安全與監控

概覽

AI 產生的概覽

BrowserSolver 官方 MCP 伺服器,讓助理透過付費 API 抓取、渲染、爬取並截圖公開網站,可繞過反機器人保護。

可以做什麼
  • 抓取公開頁面:快速 HTTP 爬取、腳本執行後的託管瀏覽器渲染,以及針對白名單主機的最高階解鎖抓取
  • 將頁面截取為 PNG、JPEG、WebP 或 PDF,無須自行維運瀏覽器環境
  • 分析網站:辨識 URL 前方的反機器人廠商,並盤點 CMS、框架、分析、CDN 與安全工具
  • 查詢帳戶用量、點數餘額以及引擎或端點的運作狀況
適用情境
當助理需要一般抓取拿不到的頁面內容(例如大量依賴 JavaScript 的頁面,或帶有反機器人挑戰的網站),或希望在不自行架設瀏覽器基礎設施的情況下,取得公開網址的截圖、PDF 與技術指紋時適用。
執行需求
需要 BrowserSolver 帳戶與 API 金鑰。託管方式:連線遠端 Streamable HTTP 端點,並在 x-api-key 標頭中送出金鑰。本機方式:Node.js 20 或更新版本及 npm 套件,金鑰放在 BROWSERSOLVER_API_KEY 中。需要可連線 BrowserSolver API 的網路。
安裝前請注意
每次呼叫都會消耗帳戶點數,依工具不同為每次 1 至 3 點。API 金鑰是可計費的機密,請勿寫入共用設定。抓取到的網頁內容不可信,可能夾帶注入指令。stats 工具不受你的帳戶範圍限制,可能需要聯絡支援開通。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 BrowserSolver,將其新增到工作區。
  2. 連接 所需的 憑證。它們會被私密儲存,絕不會在公開頁面上展示。
  3. 為需要使用其工具的對話啟用該服務。

Web executable,透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式,或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南,先向你展示發布者、端點和登入方式,經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/com.browsersolver%2Fmcp/install.md,並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前,先告訴我它的發布者、端點和登入方式,等我確認。不要把 API 金鑰寫進命令或我會提交的檔案;問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。 客戶端會在首次連接時完成 OAuth 登入。

{
  "mcpServers": {
    "browsersolver": {
      "type": "http",
      "url": "https://mcp.browsersolver.com/"
    }
  }
}

README

BrowserSolver MCP Server

Official Model Context Protocol server for the BrowserSolver web unlocker API.

Unlock, render, crawl and screenshot any website — anti-bot bypass and technology detection through one API.

It lets Claude, Cursor, VS Code, Windsurf and any MCP client call the API as tools. Runs over stdio (local) or Streamable HTTP (self-hosted).

Requirements

  • Node.js 20 or newer
  • a BrowserSolver API key — sign up, then copy it from the dashboard

Hosted server (recommended)

BrowserSolver runs this server for you at https://mcp.browsersolver.com/ (Streamable HTTP). Send your API key in the x-api-key header; nothing to install.

sh
claude mcp add --transport http browsersolver https://mcp.browsersolver.com/ --header "x-api-key: YOUR_API_KEY"
json
{  "mcpServers": {    "browsersolver": {      "url": "https://mcp.browsersolver.com/",      "headers": {        "x-api-key": "YOUR_API_KEY"      }    }  }}

The hosted server and this package expose the same API; run the package locally when you want stdio, your own network egress, or to self-host it.

Run it locally

Claude Code

sh
claude mcp add browsersolver --env BROWSERSOLVER_API_KEY=YOUR_API_KEY -- npx -y @browsersolver/mcp

Claude Desktop, Cursor, Windsurf and other clients

Add the server to the client's MCP configuration (claude_desktop_config.json, .cursor/mcp.json…):

json
{  "mcpServers": {    "browsersolver": {      "command": "npx",      "args": ["-y", "@browsersolver/mcp"],      "env": {        "BROWSERSOLVER_API_KEY": "YOUR_API_KEY"      }    }  }}

VS Code

json
{  "servers": {    "browsersolver": {      "type": "stdio",      "command": "npx",      "args": ["-y", "@browsersolver/mcp"],      "env": {        "BROWSERSOLVER_API_KEY": "${input:browsersolver-api-key}"      }    }  },  "inputs": [    {      "type": "promptString",      "id": "browsersolver-api-key",      "description": "BrowserSolver API key",      "password": true    }  ]}

Claude Desktop extension

Download the .mcpb bundle from the releases page and open it; Claude Desktop asks for your API key.

Docker

sh
docker build -t browsersolver-mcp .docker run -i --rm -e BROWSERSOLVER_API_KEY=YOUR_API_KEY browsersolver-mcp

Tools

ToolDescription
statsInfrastructure health for an engine or endpoint over the last hour. Not scoped to your account or tenant. Enabled per account: HTTP 403 means contact support to activate it.
usageRetrieve real-time usage statistics and credit balance for your BrowserSolver account.
website_antibotSingle-pass scan that names the bot-protection vendor in front of a URL so you can choose the right BrowserSolver fetch tier next.
website_crawlerFast HTTP pull of public HTML with no browser session. Ideal when the first response already contains the content you need.
website_renderingRun a managed browser session against a public URL and collect the HTML after client-side scripts finish. Prefer Crawler for static markup; escalate to WebUnlocker on approved hosts when challenges p…
website_screenshotTurn any public URL into a PNG, JPEG, WebP, or PDF asset rendered by BrowserSolver. No local Chromium fleet to operate.
website_technologyMap CMS, frameworks, analytics, CDN, and security tooling exposed by a public URL. Choose simple lists or expert metadata with confidence scores.
website_webunlockerBrowserSolver's highest HTML fetch tier for retail and marketplace hosts on your account whitelist. Solves persistent bot challenges that still block Rendering.

Every tool that calls the API consumes credits. JSON results are returned as text; images are returned inline and other files (PDF…) as embedded resources, up to 4 MB.

Streamable HTTP

sh
npx @browsersolver/mcp --http --port 3000

The endpoint is POST /mcp (stateless, JSON responses). Each client sends its own key in the x-api-key header (or Authorization: Bearer <key>); the server never uses a key of its own. It binds to 127.0.0.1 by default and rejects browser origins unless you allow them — put it behind TLS before exposing it.

createHttpHandler() is exported for Fetch-compatible runtimes (Cloudflare Workers, Deno, Bun):

ts
import { createHttpHandler } from "@browsersolver/mcp";
export default { fetch: createHttpHandler({ allowedOrigins: [] }) };

Security

  • The API key is read from BROWSERSOLVER_API_KEY (stdio) or the request headers (HTTP) and removed from error messages.
  • Content fetched from websites is untrusted: the server instructions tell the model to treat it as data, not instructions.
  • See SECURITY.md to report a vulnerability.

Development

sh
npm installnpm testnpm run buildnpx @modelcontextprotocol/inspector node dist/stdio.js

Built on the SDK

The server uses the official Node.js SDK (@browsersolver/sdk).

All BrowserSolver SDKs

SDKPackageInstall
Node.js@browsersolver/sdknpm install @browsersolver/sdk
Pythonbrowsersolverpip install browsersolver
Gobrowsersolver-gogo get github.com/browsersolver/browsersolver-go
.NETBrowserSolverdotnet add package BrowserSolver
Rubybrowsersolvergem install browsersolver
PHPbrowsersolver/sdkcomposer require browsersolver/sdk
Javabrowsersolver-javabuild from source, see its README
CLI@browsersolver/clinpm install -g @browsersolver/cli
MCP server@browsersolver/mcpnpx -y @browsersolver/mcp

License

MIT — see LICENSE.

來源:README.md,提交 ca8a0fc

工具

8

stats

Stats

Stats. Infrastructure health for an engine or endpoint over the last hour. Not scoped to your account or tenant. Enabled per account: HTTP 403 means contact support to activate it.

輸入參數pathengine

usage

Usage

Usage. Retrieve real-time usage statistics and credit balance for your BrowserSolver account.

無需輸入參數。

website_antibot

Website Antibot

Website Antibot. Single-pass scan that names the bot-protection vendor in front of a URL so you can choose the right BrowserSolver fetch tier next. Credit cost: 1 credit per call.

輸入參數query必填fieldstimeout

website_crawler

Website Crawler

Website Crawler. Fast HTTP pull of public HTML with no browser session. Ideal when the first response already contains the content you need. Credit cost: 1 credit per call.

輸入參數query必填fieldsallow_redirectsreturn_page_source

website_rendering

Website Rendering

Website Rendering. Run a managed browser session against a public URL and collect the HTML after client-side scripts finish. Prefer Crawler for static markup; escalate to WebUnlocker on approved hosts when challenges persist. Credit cost: 2 credits per call.

輸入參數query必填fieldstimeoutwait_forblock_adswait_in_seconds

website_screenshot

Website Screenshot

Website Screenshot. Turn any public URL into a PNG, JPEG, WebP, or PDF asset rendered by BrowserSolver. No local Chromium fleet to operate. Credit cost: 2 credits per call.

輸入參數url必填cachedelayproxydevicefieldsformats3_urlselectorcache_ttlfull_pages3_bucket另有 18 個

website_technology

Website Technology

Website Technology. Map CMS, frameworks, analytics, CDN, and security tooling exposed by a public URL. Choose simple lists or expert metadata with confidence scores. Credit cost: 1 credit per call.

輸入參數modequery必填fields

website_webunlocker

Website WebUnlocker

Website WebUnlocker. BrowserSolver's highest HTML fetch tier for retail and marketplace hosts on your account whitelist. Solves persistent bot challenges that still block Rendering. Credit cost: 3 credits per call.

輸入參數query必填fieldsallow_redirectsreturn_page_source

版本歷史

1
  1. v0.1.0最新Nov 7, 2026

評分

已滿足適用檢查項的 100%

該評分衡量此收錄條目的完整程度,依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價,也不表示伺服器安全或目前可用:可連通性是帶日期的檢查結果,評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具15 分
  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分