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)
Web infrastructure for AI agents: scrape, crawl and search the web, run browsers and agents.
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。
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 …”。
适用于网页版、桌面版和手机版 Claude:
https://api.outcrawl.ai/mcp在终端中运行这条命令
claude mcp add --transport http outcrawl https://api.outcrawl.ai/mcp粘贴到项目中的 .cursor/mcp.json,或 ~/.cursor/mcp.json
{
"mcpServers": {
"outcrawl": {
"url": "https://api.outcrawl.ai/mcp"
}
}
}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": {
"outcrawl": {
"type": "http",
"url": "https://api.outcrawl.ai/mcp"
}
}
}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。
ChatGPT 只能连接互联网上的服务器:
https://api.outcrawl.ai/mcp菜单名称可能因套餐和版本不同而略有差异。
你的选择通过 Cookie 保存在这台设备上,无需账户。
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 GitHub 账户 outcrawlai 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
在 476 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。
注册中心没有列出必需的密钥,不过有些服务器会在首次使用时要求你登录。
它在作者的云端运行。通过互联网连接,无需安装,但你发送的内容会经过作者的服务器。
GitHub 仓库最后更新于–,最新版本(1.0.1)于4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。
Give your AI agent the web. Outcrawl is web infrastructure for AI agents: connect it once, then ask in plain words. Your agent reads any page as clean markdown or JSON, crawls a whole site, searches the web with the results already read, watches pages for changes, and hands a multi-step task (a login, a form, a flow across pages) to an agent working in a real browser.
https://api.outcrawl.ai/mcp (streamable HTTP)The server is hosted by Outcrawl. There is no local package to install or run. You pick one workspace when you sign in, every call spends that workspace's credits, and every result reports what it cost. The Free plan has 1,000 credits a month; a page load is 1 credit. Pricing
claude mcp add --transport http outcrawl https://api.outcrawl.ai/mcp
The first tool call opens a browser to sign in and pick a workspace.
Or install the plugin, which adds the server and a skill that teaches Claude which tool to reach for:
/plugin marketplace add outcrawlai/outcrawl-mcp
/plugin install outcrawl@outcrawl
Or add it in Cursor's MCP settings (~/.cursor/mcp.json):
{ "mcpServers": { "outcrawl": { "url": "https://api.outcrawl.ai/mcp" } } }
codex mcp add outcrawl --url https://api.outcrawl.ai/mcp
codex mcp login outcrawl
Or in ~/.codex/config.toml:
[mcp_servers.outcrawl]
url = "https://api.outcrawl.ai/mcp"
gemini extensions install https://github.com/outcrawlai/outcrawl-mcp
Give the client the URL https://api.outcrawl.ai/mcp and choose OAuth. It registers itself and signs you in through your browser on first use:
{ "mcpServers": { "outcrawl": { "url": "https://api.outcrawl.ai/mcp" } } }
A client with no OAuth support
Create an API key in the console at https://outcrawl.ai/console/keys and send it as a header:
{
"mcpServers": { "outcrawl": { "url": "https://api.outcrawl.ai/mcp", "headers": { "Authorization": "Bearer ock_YOUR_KEY_ID.YOUR_SECRET" } } } }
This is the one place an API key belongs in an MCP config; every client above signs in instead.
| Group | Tools | What they do |
|---|---|---|
| Read the web | outcrawl_scrape, outcrawl_crawl, outcrawl_search | One known URL to markdown, HTML, links, a screenshot or JSON; a whole site from a seed URL; a web search with every hit read in full |
| Agents | outcrawl_agent and 9 more | Give a task to an agent in a real browser under caps you set, follow its steps, read its records as they land, cancel it, hand its browser to a person, pass it a file, list its downloads |
| Monitors | outcrawl_monitor_create, outcrawl_monitor_list, outcrawl_monitor_delete | Watch a URL on a schedule and notify Discord, Slack or a webhook when it really changes |
| Profiles | outcrawl_profile_create, outcrawl_profile_list, outcrawl_profile_get, outcrawl_profile_delete | Keep cookies and site storage so a login survives across runs, optionally pinned to a country, region and city |
| Sessions | outcrawl_sessions_list, outcrawl_sessions_get, outcrawl_session_network, outcrawl_session_request, outcrawl_session_downloads, outcrawl_session_delete | Every session is recorded: its replay URL, network and console digest, any request in full, its downloads |
| Account | outcrawl_usage, outcrawl_credits, outcrawl_rules_get, outcrawl_rules_set | Usage over a date range, the credit pool, and workspace rules written in plain sentences |
Pick the cheapest tool that answers: a scrape to read a page you know, a search to find pages, a crawl to cover a site, and an agent only when the answer is behind a login, a form or a multi-step flow. An agent run costs far more than a scrape for the same text.
Read https://outcrawl.ai/pricing and list the plans with their prices.
Search for the latest Model Context Protocol changes and summarize the top three.
Crawl the docs at https://outcrawl.ai/docs, at most 20 pages, and list the page titles.
Watch https://example.com/changelog every hour and post to my Slack webhook when it changes.
| File | For |
|---|---|
.claude-plugin/ and .mcp.json | Claude Code plugin and marketplace |
plugin.json and mcp.json | Agent Plugins package (Cursor, ChatGPT, Codex) |
.cursor-plugin/plugin.json | Cursor Marketplace |
gemini-extension.json | Gemini CLI extension |
server.json | The official MCP registry entry, io.github.outcrawlai/outcrawl |
skills/outcrawl/SKILL.md | The skill every package ships: which tool answers which question, and how to keep spend down |
This repo only packages the connection; the server is hosted by Outcrawl.
MIT licensed.