CaptureKit

dev.capturekit由 capturekit.dev 發布官方發布者v0.1.0更新於 Nov 7, 2026

Capture websites as PNG, JPEG, WebP or PDF, extract their content, or analyse them with AI.

已驗證Streamable HTTP可網頁執行網頁搜尋與抓取瀏覽器自動化媒體與設計

概覽

AI 產生的概覽

CaptureKit 官方 MCP 伺服器:將網頁擷取為 PNG、JPEG、WebP 或 PDF,擷取頁面內容、抓取 HTML,並以 AI 分析網站。

可以做什麼
  • 將網頁擷取為 PNG、JPEG、WebP 或 PDF,用於預覽、品保、報告與歸檔
  • 一次請求擷取結構化頁面資料、中繼資料、連結以及 HTML 或 Markdown
  • 不經渲染直接抓取原始 HTML,用於快速爬取、稽核與監控
  • 以 AI 分析網頁,回傳摘要、價值主張、功能、分類與使用情境
  • 查詢帳戶用量與點數餘額,以及引擎或端點最近一小時的運作狀況
適用情境
當助理需要即時網站的截圖、PDF 或擷取的頁面內容,或需要快速取得網頁的 AI 摘要,又不想自行架設無頭瀏覽器時適用。也適合 SEO、監控、索引與歸檔類工作流程。
執行需求
需要 CaptureKit 帳戶與 API 金鑰:託管端點透過 x-api-key 標頭傳送,本機 stdio 套件則以 CAPTUREKIT_API_KEY 環境變數提供。本機套件需 Node.js 20 或更新版本(或 Docker);託管伺服器無需安裝。需要能連線至 CaptureKit 的網路。
安裝前請注意
所有呼叫 API 的工具都會消耗付費點數,用量工具會顯示你的餘額。API 金鑰屬於機密,請避免寫入共用設定或日誌。抓取到的網站內容不可信,可能含有注入指令。stats 工具不受限於你的帳戶,且可能未開通(回傳 HTTP 403)。自架 HTTP 模式在對外開放前應置於 TLS 之後。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 CaptureKit,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/dev.capturekit%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": {
    "capturekit": {
      "type": "http",
      "url": "https://mcp.capturekit.dev/"
    }
  }
}

README

CaptureKit MCP Server

Official Model Context Protocol server for the CaptureKit screenshot API.

Capture websites as PNG, JPEG, WebP or PDF, extract their content, or analyse them with AI.

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 CaptureKit API key — sign up, then copy it from the dashboard

Hosted server (recommended)

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

sh
claude mcp add --transport http capturekit https://mcp.capturekit.dev/ --header "x-api-key: YOUR_API_KEY"
json
{  "mcpServers": {    "capturekit": {      "url": "https://mcp.capturekit.dev/",      "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 capturekit --env CAPTUREKIT_API_KEY=YOUR_API_KEY -- npx -y @capturekitdev/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": {    "capturekit": {      "command": "npx",      "args": ["-y", "@capturekitdev/mcp"],      "env": {        "CAPTUREKIT_API_KEY": "YOUR_API_KEY"      }    }  }}

VS Code

json
{  "servers": {    "capturekit": {      "type": "stdio",      "command": "npx",      "args": ["-y", "@capturekitdev/mcp"],      "env": {        "CAPTUREKIT_API_KEY": "${input:capturekit-api-key}"      }    }  },  "inputs": [    {      "type": "promptString",      "id": "capturekit-api-key",      "description": "CaptureKit 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 capturekit-mcp .docker run -i --rm -e CAPTUREKIT_API_KEY=YOUR_API_KEY capturekit-mcp

Tools

ToolDescription
analyzeAI Content API analyzes any webpage and returns AI insights summary, value proposition, features, categories, use cases, and optional contact signals.
captureBrowser-like Screenshot API that captures webpages as PNG/JPEG/WebP or PDF for previews, QA, reporting, monitoring, and archiving no headless setup.
contentCaptureKit Content API extracts structured webpage data, metadata, links, HTML/Markdown: in one request for SEO, monitoring, indexing and automation.
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 CaptureKit account.
website_crawlerWebsite Crawler API fetches raw HTML from any webpage in request mode (no rendering) for fast scraping, audits, monitoring, and link/metadata extraction.

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 @capturekitdev/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 "@capturekitdev/mcp";
export default { fetch: createHttpHandler({ allowedOrigins: [] }) };

Security

  • The API key is read from CAPTUREKIT_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 (@capturekitdev/sdk).

All CaptureKit SDKs

SDKPackageInstall
Node.js@capturekitdev/sdknpm install @capturekitdev/sdk
Pythoncapturekitdevpip install capturekitdev
Gocapturekit-gogo get github.com/capturekitdev/capturekit-go
.NETCaptureKitdotnet add package CaptureKit
Rubycapturekitdevgem install capturekitdev
PHPcapturekitdev/sdkcomposer require capturekitdev/sdk
Javacapturekit-javabuild from source, see its README
CLI@capturekitdev/clinpm install -g @capturekitdev/cli
MCP server@capturekitdev/mcpnpx -y @capturekitdev/mcp

License

MIT — see LICENSE.

來源:README.md,提交 d77503f

工具

0
該伺服器需要登入,因此 SourceWeft 無法在沒有帳號的情況下讀取其工具,也未收錄。已連接帳號所能看到的內容可能因帳號及其權限而異。

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 85%

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

    請讓伺服器在無憑證時回應 tools/list,或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分