Capture websites as screenshots or PDFs, extract structured content, and perform AI-driven webpage analysis.
Also known as capturekitdev/capturekit-mcp, capturekit-mcp, @capturekitdev/mcp
- Stars
- 0
- Tools
- 6
- Downloads, 30 days
- 309
- Latest version
- 0.1.0
- Last commit
- Nov 11, 2026
- License
- MIT
What is CaptureKit MCP?
CaptureKit is an MCP server. Capture websites as screenshots or PDFs, extract structured content, and perform AI-driven webpage analysis. It exposes 6 tools, such as analyze, capture, content.
Summary generated from the project's README
About CaptureKit MCP server
CaptureKit provides a way for developers to integrate web capture and analysis capabilities into AI-driven workflows. It allows clients like Claude, Cursor, Windsurf, and VS Code to interact with the CaptureKit API to transform websites into visual or structured formats. Users can capture pages as PNG, JPEG, WebP, or PDF files, or extract metadata, links, and Markdown content for automation and SEO tasks.
The server supports multiple connection methods including local stdio via npx and remote Streamable HTTP. To use the service, you must provide a CaptureKit API key through environment variables or HTTP headers. The server includes specialized tools such as analyze for generating AI insights, website_crawler for fetching raw HTML without rendering, and usage for monitoring account credit balances.
This tool is designed for developers building agents that need to see or read the web. It handles images as inline data and supports embedded resources like PDFs up to 4 MB. It also provides infrastructure health stats through the stats tool to monitor endpoint performance.
What you can do with it
- 1Automated Content ExtractionExtract structured data including links and Markdown from a webpage for indexing or SEO purposes.
- 2AI-Driven Site AnalysisAsk the AI to summarize a webpage's value proposition and features using the analyze tool.
- 3Account Credit MonitoringCheck your current credit balance and real-time usage statistics directly through the MCP client.
Written from the project's README. Every use case is checked against a quote from it.
How to install CaptureKit MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall CaptureKit MCP in Claude Code
$ claude mcp add --env 'CAPTUREKIT_API_KEY=<YOUR_CAPTUREKIT_API_KEY>' capturekit-mcp -- npx -y @capturekitdev/mcpInstall CaptureKit MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"capturekit-mcp": {
"command": "npx",
"args": [
"-y",
"@capturekitdev/mcp"
],
"env": {
"CAPTUREKIT_API_KEY": "<YOUR_CAPTUREKIT_API_KEY>"
}
}
}
}Install CaptureKit MCP in VS Code
.vscode/mcp.json
{
"servers": {
"capturekit-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@capturekitdev/mcp"
],
"env": {
"CAPTUREKIT_API_KEY": "<YOUR_CAPTUREKIT_API_KEY>"
}
}
}
}Install CaptureKit MCP in VS Code CLI
$ code --add-mcp '{"name":"capturekit-mcp","type":"stdio","command":"npx","args":["-y","@capturekitdev/mcp"],"env":{"CAPTUREKIT_API_KEY":"<YOUR_CAPTUREKIT_API_KEY>"}}'Install CaptureKit MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"capturekit-mcp": {
"command": "npx",
"args": [
"-y",
"@capturekitdev/mcp"
],
"env": {
"CAPTUREKIT_API_KEY": "<YOUR_CAPTUREKIT_API_KEY>"
}
}
}
}Install CaptureKit MCP in Codex
$ codex mcp add capturekit-mcp --env 'CAPTUREKIT_API_KEY=<YOUR_CAPTUREKIT_API_KEY>' -- npx -y @capturekitdev/mcpInstall CaptureKit MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.capturekit-mcp] command = "npx" args = ["-y", "@capturekitdev/mcp"] [mcp_servers.capturekit-mcp.env] CAPTUREKIT_API_KEY = "<YOUR_CAPTUREKIT_API_KEY>"
Install CaptureKit MCP in Gemini CLI
$ gemini mcp add -s user -e 'CAPTUREKIT_API_KEY=<YOUR_CAPTUREKIT_API_KEY>' capturekit-mcp npx -- -y @capturekitdev/mcpInstall CaptureKit MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"capturekit-mcp": {
"command": "npx",
"args": [
"-y",
"@capturekitdev/mcp"
],
"env": {
"CAPTUREKIT_API_KEY": "<YOUR_CAPTUREKIT_API_KEY>"
}
}
}
}CaptureKit MCP tools 6
Detected from the READMEanalyzecapturecontentstatsusagewebsite_crawler
| analyze | — | |
| capture | — | |
| content | — | |
| stats | — | |
| usage | — | |
| website_crawler | — |
Configuration
CAPTUREKIT_API_KEYRequiredSecretCaptureKit API key.
| Name | Description | |
|---|---|---|
| CAPTUREKIT_API_KEY | CaptureKit API key. | RequiredSecret |
Automated checks
Ran Nov 13, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablePass
- Open source license (OSI)Pass
- Commit or release in the last yearPass
- Package name not close to a popular packagePass
- Remote endpoint uses HTTPSPass
- Destructive tools are labelledPass
- No hidden instructions to the modelPass
- No critical advisory in the package or its dependenciesPass
README
View on GitHubCaptureKit 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
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.
claude mcp add --transport http capturekit https://mcp.capturekit.dev/ --header "x-api-key: YOUR_API_KEY"
{
"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
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…):
{
"mcpServers": {
"capturekit": {
"command": "npx",
"args": ["-y", "@capturekitdev/mcp"],
"env": {
"CAPTUREKIT_API_KEY": "YOUR_API_KEY"
}
}
}
}
VS Code
{
"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
docker build -t capturekit-mcp .
docker run -i --rm -e CAPTUREKIT_API_KEY=YOUR_API_KEY capturekit-mcp
Tools
| Tool | Description |
|---|---|
analyze |
AI Content API analyzes any webpage and returns AI insights summary, value proposition, features, categories, use cases, and optional contact signals. |
capture |
Browser-like Screenshot API that captures webpages as PNG/JPEG/WebP or PDF for previews, QA, reporting, monitoring, and archiving no headless setup. |
content |
CaptureKit Content API extracts structured webpage data, metadata, links, HTML/Markdown: in one request for SEO, monitoring, indexing and automation. |
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 CaptureKit account. |
website_crawler |
Website 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
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):
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
npm install
npm test
npm run build
npx @modelcontextprotocol/inspector node dist/stdio.js
Built on the SDK
The server uses the official Node.js SDK (@capturekitdev/sdk).
All CaptureKit SDKs
| SDK | Package | Install |
|---|---|---|
| Node.js | @capturekitdev/sdk |
npm install @capturekitdev/sdk |
| Python | capturekitdev |
pip install capturekitdev |
| Go | capturekit-go |
go get github.com/capturekitdev/capturekit-go |
| .NET | CaptureKit |
dotnet add package CaptureKit |
| Ruby | capturekitdev |
gem install capturekitdev |
| PHP | capturekitdev/sdk |
composer require capturekitdev/sdk |
| Java | capturekit-java |
build from source, see its README |
| CLI | @capturekitdev/cli |
npm install -g @capturekitdev/cli |
| MCP server | @capturekitdev/mcp |
npx -y @capturekitdev/mcp |
License
MIT — see LICENSE.
CaptureKit MCP questions
How do I add CaptureKit MCP to Claude Code?
Run claude mcp add --env 'CAPTUREKIT_API_KEY=<YOUR_CAPTUREKIT_API_KEY>' capturekit-mcp -- npx -y @capturekitdev/mcp in your terminal. Add --scope user to make it available in every project.
How do I add CaptureKit MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does CaptureKit MCP provide?
It exposes 6 tools, including analyze, capture, content, stats, usage.
What formats can I capture websites in?
You can capture webpages as PNG, JPEG, WebP, or PDF.
Can I run this server locally?
Yes, you can run it locally using npx, Docker, or by downloading the Claude Desktop extension.
What does the analyze tool do?
The analyze tool uses an AI Content API to provide summaries, value propositions, features, categories, and use cases for any webpage.