Agent-Native Calendar
Agent-Native Google Calendar - manage events, sync, and public booking
作者提供的说明(英文原文)
Website screenshots, URL/HTML to PDF, scrolling videos, and web scraping via ScreenshotAPI.
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。
SCREENSHOTAPI_TOKEN, SCREENSHOTAPI_REQUEST_TIMEOUT_MS, SCREENSHOTAPI_MAX_INLINE_IMAGE_BYTES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 …”。
打开 Claude Desktop → Settings → Developer → Edit Config,把下面的内容粘贴到 claude_desktop_config.json
{
"mcpServers": {
"screenshot": {
"command": "npx",
"args": [
"-y",
"@screenshotapinet/mcp"
],
"env": {
"SCREENSHOTAPI_TOKEN": "your-value",
"SCREENSHOTAPI_REQUEST_TIMEOUT_MS": "your-value",
"SCREENSHOTAPI_MAX_INLINE_IMAGE_BYTES": "your-value"
}
}
}
}在终端中运行这条命令
claude mcp add screenshot --env SCREENSHOTAPI_TOKEN=your-value --env SCREENSHOTAPI_REQUEST_TIMEOUT_MS=your-value --env SCREENSHOTAPI_MAX_INLINE_IMAGE_BYTES=your-value -- npx -y @screenshotapinet/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": {
"screenshot": {
"command": "npx",
"args": [
"-y",
"@screenshotapinet/mcp"
],
"env": {
"SCREENSHOTAPI_TOKEN": "your-value",
"SCREENSHOTAPI_REQUEST_TIMEOUT_MS": "your-value",
"SCREENSHOTAPI_MAX_INLINE_IMAGE_BYTES": "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": {
"screenshot": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@screenshotapinet/mcp"
],
"env": {
"SCREENSHOTAPI_TOKEN": "your-value",
"SCREENSHOTAPI_REQUEST_TIMEOUT_MS": "your-value",
"SCREENSHOTAPI_MAX_INLINE_IMAGE_BYTES": "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。
这个服务器在你的电脑上运行,而 ChatGPT 只能连接互联网上的服务器。请选择其他应用。
你的选择通过 Cookie 保存在这台设备上,无需账户。
SCREENSHOTAPI_REQUEST_TIMEOUT_MS envSCREENSHOTAPI_MAX_INLINE_IMAGE_BYTES env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。
它在你的电脑上运行;安装后,工具列表会显示在你的 AI 应用中。
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 Screenshot-API 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
它在你的电脑上运行,没有互联网端点
在你的电脑上运行,改用本地设置
它在你的电脑上运行;我们只能读取互联网端点的工具列表
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:SCREENSHOTAPI_TOKEN
它在你的电脑上运行。你的 AI 应用会在需要时启动它,数据不会经过作者的服务器(除非它自己调用在线服务)。
GitHub 仓库最后更新于–,最新版本(1.0.2)于11天前进入注册中心。
支持 MCP 的应用,例如 Claude Desktop、Claude Code、Cursor 和 VS Code。你的电脑上还需要有 Node.js。
同一分类中有:Agent-Native Calendar, Excel MCP Server, MCP Server for Excel
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
Agent-Native Google Calendar - manage events, sync, and public booking
Create and edit Excel files with AI: charts, PivotTables, formulas. No Excel needed.
Excel automation for AI - Sheets, Power Query, DAX, VBA, Tables, Ranges and more. Windows only.
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 MCP server for ScreenshotAPI. It gives your AI assistant 8 tools for website screenshots, URL and HTML to PDF, scrolling videos, JavaScript-aware web scraping (Markdown, text, HTML), and bulk captures. You ask in plain English and the server makes the API calls. Your assistant also gets the screenshot back as an image, so it can see the page it captured.
Works with Claude Desktop, Claude Code, Cursor, Windsurf, VS Code, Cline, Codex, and any other MCP-compatible client.
| Item | Value |
|---|---|
| Package | @screenshotapinet/mcp |
| Transport | stdio |
| Node.js | >=18 |
{
"mcpServers": { "screenshotapi": { "command": "npx", "args": ["-y", "@screenshotapinet/mcp"], "env": { "SCREENSHOTAPI_TOKEN": " " } } } }
npx available in your terminalAdd to claude_desktop_config.json (Settings → Developer → Edit Config):
{
"mcpServers": { "screenshotapi": { "command": "npx", "args": ["-y", "@screenshotapinet/mcp"], "env": { "SCREENSHOTAPI_TOKEN": " " } } } }
Restart Claude Desktop after saving.
claude mcp add screenshotapi --env SCREENSHOTAPI_TOKEN=<YOUR_API_KEY> -- npx -y @screenshotapinet/mcp
Start a new Claude Code session after adding the server.
One-click install:
Or add to .cursor/mcp.json manually:
{
"mcpServers": { "screenshotapi": { "command": "npx", "args": ["-y", "@screenshotapinet/mcp"], "env": { "SCREENSHOTAPI_TOKEN": " " } } } }
Restart Cursor after saving.
Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": { "screenshotapi": { "command": "npx", "args": ["-y", "@screenshotapinet/mcp"], "env": { "SCREENSHOTAPI_TOKEN": " " } } } }
Restart Windsurf after saving.
Add to your VS Code settings.json:
{
"mcp": { "servers": { "screenshotapi": { "command": "npx", "args": ["-y", "@screenshotapinet/mcp"], "env": { "SCREENSHOTAPI_TOKEN": " " } } } } }
Restart VS Code after saving.
Open MCP Servers panel → Configure → Advanced MCP Settings. Add to cline_mcp_settings.json:
{
"mcpServers": { "screenshotapi": { "command": "npx", "args": ["-y", "@screenshotapinet/mcp"], "env": { "SCREENSHOTAPI_TOKEN": " " } } } }
Restart Cline after saving.
codex mcp add screenshotapi --env SCREENSHOTAPI_TOKEN=<YOUR_API_KEY> -- npx -y @screenshotapinet/mcp
codex mcp list
Start a new Codex session after adding the server.
Use this config:
{
"command": "npx", "args": ["-y", "@screenshotapinet/mcp"], "env": { "SCREENSHOTAPI_TOKEN": " " } }
Try these after setup:
| Prompt | Expected tool |
|---|---|
| Take a screenshot of https://example.com | take_screenshot |
| Screenshot stripe.com on an iPhone-sized screen in dark mode | take_screenshot with width, dark_mode |
| Capture the full page of https://news.ycombinator.com without ads | take_screenshot with full_page, block |
| Save https://example.com/invoice as an A4 PDF to ./invoice.pdf | generate_pdf with format, save_path |
| Read https://react.dev/learn and summarize it | scrape_page |
| Make a 10-second scrolling GIF of https://apple.com | record_scrolling_video |
| Screenshot these 5 competitor homepages | bulk_screenshots |
| Is bulk job 1f2e... done yet? | get_bulk_status |
All 8 tools wrap the ScreenshotAPI REST API. The render tools (take_screenshot, generate_pdf, scrape_page, record_scrolling_video) call GET https://shot.screenshotapi.net/v3/screenshot with output=json and share the page preparation options below. Each takes either url or custom_html.
| Group | Parameters |
|---|---|
| Viewport | width (default 1680, max 7680), height (default 876, max 4320) |
| Timing | delay, wait_for_event (load / domcontentloaded / networkidle), lazy_load, scroll_delay, timeout |
| Page manipulation | css, css_url, js, js_url, remove_selector, blur_selector, selector_to_click, click_recursion, scroll_to_element, adjust_top |
| Blocking | block (list: ads, tracking, cookie_banners, chat_widgets, javascript, stylesheets, images, media, fonts, text_tracks, xhr, fetch, event_source, websockets, manifest), block_specific_requests |
| Emulation | dark_mode, grayscale (0-100), enable_incognito, user_agent, accept_languages, headers, cookies, template_id, proxy, latitude, longitude, timezone |
| Caching | fresh, enable_caching, ttl (screenshot and PDF only) |
| Storage | result_file_name, byob, storage_service, bucket_name (screenshot and PDF only) |
Captures a page as an image and returns the hosted image URL. The image is also returned inline so the assistant can see it. Full-page captures are the exception, since they are usually too tall to view; pass include_image=true to get them inline anyway.
| Parameter | Required | Description |
|---|---|---|
url | One of | URL to capture |
custom_html | One of | Raw HTML to render instead of a URL |
file_type | No | png (default), jpg, webp |
full_page | No | Capture the whole scrollable page. Default false |
retina | No | 2x pixel density. Default false |
image_quality | No | JPEG quality 0-100. Default 80 |
omit_background | No | Transparent background for plain-background pages (PNG only) |
thumbnail_width | No | Resize output to this width, keeping aspect ratio |
selector | No | Capture a single element by CSS selector |
clip | No | Capture a rectangle: { x, y, width, height } |
sizes | No | Capture at several viewport sizes in one request: [{ width, height }, ...] |
include_image | No | Return the image inline. Default true, or false when full_page is set |
save_path | No | Also save the file locally |
Plus all shared render options.
Converts a URL or raw HTML to PDF and returns the hosted PDF URL. With no format (and no width/height), the whole page becomes one continuous PDF page.
| Parameter | Required | Description |
|---|---|---|
url | One of | URL to convert |
custom_html | One of | Raw HTML to convert |
format | No | A0–A6, Letter, Legal, Tabloid, Ledger |
landscape | No | Landscape orientation. Default false |
page_range | No | Keep only these pages, e.g. 1-3 |
print_background | No | Include background colors and images |
media | No | print or screen CSS |
save_path | No | Also save the PDF locally |
Plus all shared render options.
Renders the page in a real browser, so JavaScript runs first, then extracts its content. The server downloads the extracted files and return
只显示了开头部分;其余内容请在仓库中阅读