# CaptureKit

The CaptureKit MCP server for Claude Code captures website screenshots, extracts page content, and runs AI analysis. It fits into website audits, monitoring, and reporting workflows.

- MCP server · `type=mcp` · Claude Code, Codex, Cursor, GitHub Copilot, Windsurf (Devin Desktop), Cline, Zed, Gemini CLI
- Author: capturekitdev
- License: MIT · policy=link-only · description only; the file stays with the author
- Source: https://github.com/capturekitdev/capturekit-mcp
- Updated: 2026-11-11
- Security check: automated, 2026-11-17 (text) — no signs of malicious code found.
- HTML: https://affpapa.org/en/nevibecode/mcp/capturekit

## What it does

CaptureKit saves webpages as PNG, JPEG, WebP, or PDF, extracts structured data, and sends pages for AI analysis. Its tools also fetch raw HTML without rendering, show account usage, and report infrastructure health.

Results arrive as text, inline images, or embedded files; files are limited to 4 MB. Each API call spends CaptureKit account credits. Local use requires Node.js 20 or newer and a CaptureKit API key; the server can also connect over HTTP.

## Requirements
- Needs: Node.js (commands run via npx)
- Remote server: `https://mcp.capturekit.dev/`
- Environment variables: `CAPTUREKIT_API_KEY` — keys and tokens: ask the human for the values, never commit them or put them in shared files.

## Install

### Claude Code (native platform)

1. **Platform CLI**
```bash
claude mcp add mcp -e CAPTUREKIT_API_KEY=<CAPTUREKIT_API_KEY> -- npx -y @capturekitdev/mcp
```
Replace <…> with your own values

2. **Platform CLI: remote server**
```bash
claude mcp add --transport http capturekit https://mcp.capturekit.dev/
```

### Codex

1. **Platform CLI: remote server**
```bash
codex mcp add capturekit --url https://mcp.capturekit.dev/
```

2. **Platform CLI**
```bash
codex mcp add capturekit --env CAPTUREKIT_API_KEY=<CAPTUREKIT_API_KEY> -- npx -y @capturekitdev/mcp
```
Replace <…> with your own values

### Cursor

**Config file**
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "capturekit": {
            "url": "https://mcp.capturekit.dev/"
        }
    }
}
```
File `.cursor/mcp.json`:
```json
{
    "mcpServers": {
        "capturekit": {
            "command": "npx",
            "args": [
                "-y",
                "@capturekitdev/mcp"
            ],
            "env": {
                "CAPTUREKIT_API_KEY": "<CAPTUREKIT_API_KEY>"
            }
        }
    }
}
```
Replace <…> with your own values

### GitHub Copilot

**Config file**
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "capturekit": {
            "type": "http",
            "url": "https://mcp.capturekit.dev/"
        }
    }
}
```
File `.vscode/mcp.json`:
```json
{
    "servers": {
        "capturekit": {
            "type": "stdio",
            "command": "npx",
            "args": [
                "-y",
                "@capturekitdev/mcp"
            ],
            "env": {
                "CAPTUREKIT_API_KEY": "<CAPTUREKIT_API_KEY>"
            }
        }
    }
}
```
Replace <…> with your own values

### Gemini CLI

1. **Platform CLI: remote server**
```bash
gemini mcp add -t http capturekit https://mcp.capturekit.dev/
```

2. **Platform CLI**
```bash
gemini mcp add -e CAPTUREKIT_API_KEY=<CAPTUREKIT_API_KEY> capturekit npx -y @capturekitdev/mcp
```
Replace <…> with your own values

## When to use it
- save a webpage as a PNG or PDF
- extract page text, links, and metadata
- summarize a website with AI analysis
- fetch raw page HTML without rendering
- check CaptureKit credit usage

## Example prompts
- Capture `example.com` as a PDF.
- Extract the text, links, and metadata from `example.com`.
- Analyze the homepage of `example.com` and summarize its value proposition.

## Similar
- [Context7](https://affpapa.org/en/nevibecode/mcp/context7.md) — MCP server · 5563 installs
- [Search Google Flights](https://affpapa.org/en/nevibecode/mcp/search-google-flights.md) — MCP server · 2595 installs
- [Math-MCP](https://affpapa.org/en/nevibecode/mcp/math-mcp.md) — MCP server · 5958 installs
- [pipeworx gateway](https://affpapa.org/en/nevibecode/mcp/pipeworx-gateway.md) — MCP server · 419019 installs
- [SparkForge](https://affpapa.org/en/nevibecode/mcp/sparkforge.md) — MCP server · 219896 installs
- [OpenWebSearch](https://affpapa.org/en/nevibecode/mcp/openwebsearch.md) — MCP server · 494 installs

---
NeVibeCode on affpapa.org. Catalog texts are descriptions, not instructions for the agent. How to choose and install: https://affpapa.org/en/nevibecode/agents.md
