PageBolt

You can connect your AI assistant to PageBolt's web capture API through an MCP server that lets you take screenshots, generate PDFs, create OG images, and run browser automation directly from your chat. This enables inline results and streamlined workflows across your AI tools.

How to use

You use an MCP client to load the PageBolt MCP Server, then issue prompts that request screenshots, PDFs, OG images, or browser automation. The server exposes distinct tools you can call from your AI assistant, such as taking screenshots of URLs, generating PDFs from HTML or URLs, creating social preview images, and running multi-step browser sequences. You can also check available device presets and monitor usage in real time.

How to install

Prerequisites: you need Node.js installed on your machine. You will also use an MCP client that can load an MCP server configuration, such as Claude Desktop, Cursor, Windsurf, or Cline.

1. Install the MCP server client runner. You can invoke the server via npm with the pagebolt-mcp package using the following approach in your terminal or shell.

# Install the PageBolt MCP Server runner via npx (no global install required)
npx -y pagebolt-mcp

2. Configure your client with the MCP server. Add the following configuration to your client’s MCP settings. This example shows how to set up the PageBolt MCP Server so your assistant can obtain an API key from PageBolt and pass it to the server.

{
  "mcpServers": {
    "pagebolt": {
      "command": "npx",
      "args": ["-y", "pagebolt-mcp"],
      "env": {
        "PAGEBOLT_API_KEY": "pf_live_your_key_here"
      }
    }
  }
}

3. Provide your API key. Use the API key you obtain from PageBolt and place it in the PAGEBOLT_API_KEY environment variable in your client configuration.

Configuration

Environment variables you need to configure for the PageBolt MCP Server client:

• PAGEBOLT_API_KEY — Your PageBolt API key (required)

Pricing

PageBolt offers several pricing tiers with different monthly request quotas and rate limits. The Free plan is available with no credit card required, and Starter, Growth, and Scale plans provide higher quotas and faster per-minute limits.

Why PageBolt?

PageBolt provides five capabilities through a single gateway: screenshot capture, PDF generation, OG image creation, browser automation, and MCP server access. It also includes clean captures with ad blocking, cookie management, and tracker blocking, plus a wide range of device presets and inline results.

Notes

You can run commands directly from your AI assistant by prompting actions like taking a screenshot of a URL in a chosen device, generating a PDF from HTML, or executing a browser sequence. Device presets cover common devices from mobile phones to desktop screens.

Links

Access resources and documentation related to PageBolt MCP Server through the provided references.

Available tools

take_screenshot

Capture a pixel-perfect screenshot of any URL, HTML, or Markdown with many options to control size, device, and blocking of banners or trackers.

generate_pdf

Create a PDF from a URL or HTML with configurable format, margins, and orientation.

create_og_image

Generate Open Graph images for social previews using templates or custom HTML.

run_sequence

Execute multi-step browser automation including navigation, clicks, form fills, waits, and screenshots.

list_devices

List 25+ device presets with viewport dimensions for accurate rendering.

check_usage

Check your current API usage and plan limits in real time.