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)
Unlock, render, crawl and screenshot any website — anti-bot bypass and technology detection through…
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。
BROWSERSOLVER_API_KEY, x-api-key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。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"browsersolver": {
"command": "npx",
"args": [
"-y",
"@browsersolver/mcp"
],
"env": {
"BROWSERSOLVER_API_KEY": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add --transport http browsersolver https://mcp.browsersolver.com/ --header 'x-api-key: your-value'claude mcp add browsersolver --env BROWSERSOLVER_API_KEY=your-value -- npx -y @browsersolver/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": {
"browsersolver": {
"url": "https://mcp.browsersolver.com/",
"headers": {
"x-api-key": "your-value"
}
}
}
}粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"browsersolver": {
"command": "npx",
"args": [
"-y",
"@browsersolver/mcp"
],
"env": {
"BROWSERSOLVER_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": {
"browsersolver": {
"type": "http",
"url": "https://mcp.browsersolver.com/",
"headers": {
"x-api-key": "your-value"
}
}
}
}粘贴到项目中的 .vscode/mcp.json
{
"servers": {
"browsersolver": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@browsersolver/mcp"
],
"env": {
"BROWSERSOLVER_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。
x-api-key 机密 必填 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。
服务器要求先登录,才会列出它的工具。
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
注册名称已通过域名 browsersolver.com 验证(注册中心会核实域名所有权)
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
在 753 毫秒内响应(HTTP 401)
声明支持 OAuth 登录,你的 AI 应用可以带你去登录
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 3 项适用的基础检查中通过了 3 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:BROWSERSOLVER_API_KEY, x-api-key
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(0.1.0)于今天进入注册中心。
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。
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).
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.
claude mcp add --transport http browsersolver https://mcp.browsersolver.com/ --header "x-api-key: YOUR_API_KEY"
{
"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.
claude mcp add browsersolver --env BROWSERSOLVER_API_KEY=YOUR_API_KEY -- npx -y @browsersolver/mcp
Add the server to the client's MCP configuration (claude_desktop_config.json, .cursor/mcp.json…):
{
"mcpServers": { "browsersolver": { "command": "npx", "args": ["-y", "@browsersolver/mcp"], "env": { "BROWSERSOLVER_API_KEY": "YOUR_API_KEY" } } } }
{
"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 } ] }
Download the .mcpb bundle from the releases page and open it; Claude Desktop asks for your API key.
docker build -t browsersolver-mcp .
docker run -i --rm -e BROWSERSOLVER_API_KEY=YOUR_API_KEY browsersolver-mcp
| Tool | Description |
|---|---|
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. |
usage | Retrieve real-time usage statistics and credit balance for your BrowserSolver account. |
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. |
website_crawler | Fast HTTP pull of public HTML with no browser session. Ideal when the first response already contains the content you need. |
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 p… |
website_screenshot | Turn any public URL into a PNG, JPEG, WebP, or PDF asset rendered by BrowserSolver. No local Chromium fleet to operate. |
website_technology | Map CMS, frameworks, analytics, CDN, and security tooling exposed by a public URL. Choose simple lists or expert metadata with confidence scores. |
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. |
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.
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 ); 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):
import { createHttpHandler } from "@browsersolver/mcp";
export default { fetch: createHttpHandler({ allowedOrigins: [] }) };
BROWSERSOLVER_API_KEY (stdio) or the request headers (HTTP) and removed from error messages.npm install
npm test npm run build npx @modelcontextprotocol/inspector node dist/stdio.js
The server uses the official Node.js SDK (@browsersolver/sdk).
| SDK | Package | Install |
|---|---|---|
| Node.js | @browsersolver/sdk | npm install @browsersolver/sdk |
| Python | browsersolver | pip install browsersolver |
| Go | browsersolver-go | go get github.com/browsersolver/browsersolver-go |
| .NET | BrowserSolver | dotnet add package BrowserSolver |
| Ruby | browsersolver | gem install browsersolver |
| PHP | browsersolver/sdk | composer require browsersolver/sdk |
| Java | browsersolver-java | build from source, see its README |
| CLI | @browsersolver/cli | npm install -g @browsersolver/cli |
| MCP server | @browsersolver/mcp | npx -y @browsersolver/mcp |
MIT — see LICENSE.