mcp-file-preview
by: seanivore
MCP server for HTML file preview and analysis - Has been weird with OS but good on Cline so WIP
📌Overview
Purpose: The MCP File Preview Server aims to provide robust HTML file preview and analysis capabilities through a streamlined Model Context Protocol interface.
Overview: This server enables users to capture full-page screenshots of local HTML files while also analyzing their structure, including various content types, thus enhancing the workflow of web development and design.
Key Features:
-
File Preview: Captures full-page screenshots of HTML files with accurate CSS styling, allowing for visual verification of content.
-
Content Analysis: Analyzes the HTML structure, returning counts of headings, paragraphs, images, and links, which aids in content organization and optimization.
-
Local File Support: Allows for seamless handling of local file paths and resources, making it easy to integrate with existing projects and workflows.
-
Screenshot Management: Automatically saves screenshots to a dedicated directory, ensuring organized storage and easy access.
MCP File Preview Server
A Model Context Protocol (MCP) server that provides HTML file preview and analysis capabilities. This server enables capturing full-page screenshots of local HTML files and analyzing their structure.
Features
- File Preview: Capture full-page screenshots of HTML files with proper CSS styling.
- Content Analysis: Analyze HTML structure (headings, paragraphs, images, links).
- Local File Support: Handle local file paths and resources.
- Screenshot Management: Save screenshots to a dedicated directory.
Installation
-
Clone the repository:
git clone https://github.com/your-username/mcp-file-preview.git cd mcp-file-preview
-
Install dependencies:
npm install
-
Build the project:
npm run build
Configuration
Add the server to your Claude or Cline MCP settings:
Claude Desktop App
Add to ~/Library/Application Support/Claude/claude_desktop_config.json
:
{
"mcpServers": {
"file-preview": {
"command": "node",
"args": ["/path/to/mcp-file-preview/build/index.js"]
}
}
}
Cline VSCode Extension
Add to VSCode's MCP settings:
{
"mcpServers": {
"file-preview": {
"command": "node",
"args": ["/path/to/mcp-file-preview/build/index.js"]
}
}
}
Usage
The server provides two main tools:
preview_file
Captures a screenshot and returns HTML content:
<use_mcp_tool>
<server_name>file-preview</server_name>
<tool_name>preview_file</tool_name>
<arguments>
{
"filePath": "/path/to/file.html",
"width": 1024, // optional
"height": 768 // optional
}
</arguments>
</use_mcp_tool>
Screenshots are saved to the screenshots/
directory in the project folder.
analyze_content
Analyzes HTML structure:
<use_mcp_tool>
<server_name>file-preview</server_name>
<tool_name>analyze_content</tool_name>
<arguments>
{
"filePath": "/path/to/file.html"
}
</arguments>
</use_mcp_tool>
Returns counts of:
- Headings
- Paragraphs
- Images
- Links
Development
-
Install dependencies:
npm install @modelcontextprotocol/sdk puppeteer typescript @types/node @types/puppeteer
-
Make changes in
src/
. -
Build:
npm run build
-
Test locally:
npm run dev
Implementation Details
The server uses the MCP SDK's Server class with proper initialization:
this.server = new Server(
// Metadata object
{
name: 'file-preview-server',
version: '0.1.0'
},
// Options object with capabilities
{
capabilities: {
tools: {
preview_file: {
description: 'Preview local HTML file and capture screenshot',
inputSchema: {
// ... schema definition
}
}
}
}
}
);
Key points:
- Server constructor takes separate metadata and options objects.
- Tools are declared in
capabilities.tools
. - Each tool needs a description and
inputSchema
. - Screenshots are saved to a local
screenshots/
directory.
Debugging
-
Use the MCP Inspector:
npx @modelcontextprotocol/inspector
-
Connect with:
- Transport Type: STDIO
- Command: node
- Arguments: /path/to/build/index.js
-
Check Claude OS logs if tools don't appear in the dropdown.
Contributing
Please read CONTRIBUTING.md for details on code of conduct and submitting pull requests.
License
This project is licensed under the MIT License - see the LICENSE file for details.