Skip to main content
Glama
MCP File Preview Server

MCP File Preview Server

by seanivore

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

Related MCP server: polydoc-mcp

Installation

  1. Clone the repository:

git clone https://github.com/your-username/mcp-file-preview.git
cd mcp-file-preview
  1. Install dependencies:

npm install
  1. 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 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

  1. Install dependencies:

npm install @modelcontextprotocol/sdk puppeteer typescript @types/node @types/puppeteer
  1. Make changes in src/

  2. Build:

npm run build
  1. 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

  1. Use the MCP Inspector:

npx @modelcontextprotocol/inspector
  1. Connect with:

    • Transport Type: STDIO

    • Command: node

    • Arguments: /path/to/build/index.js

  2. Check Claude OS logs if tools don't appear in the dropdown

Contributing

Please read CONTRIBUTING.md for details on our code of conduct and the process for submitting pull requests.

License

This project is licensed under the MIT License - see the LICENSE file for details.

Available Tools

2 tools
analyze_contentC

Analyze HTML content structure

Inputs: filePath (required).

preview_fileB

Preview local HTML file and capture screenshot

Inputs: filePath (required), height, width.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    B3/5.0

    Scored across 2 tools

    Disambiguation5/5

    The two tools have clearly distinct purposes: analyze_content focuses on structural analysis of HTML content, while preview_file handles file preview and screenshot capture. There is no overlap in functionality, making it easy for an agent to select the appropriate tool without confusion.

    Naming Consistency5/5

    Both tools follow a consistent verb_noun naming pattern (analyze_content and preview_file), with clear, descriptive names that align with their functions. There are no deviations or mixed conventions, ensuring predictability and readability.

    Tool Count2/5

    With only two tools, the server feels thin for a 'File Preview Server' that might be expected to handle more file types or operations beyond HTML. While the tools are focused, the count is borderline too few for the apparent scope, limiting functionality.

    Completeness2/5

    The server is severely incomplete for file preview purposes, as it only supports HTML files with no coverage for other common formats (e.g., images, PDFs, text files). There are significant gaps in the tool surface that will likely cause agent failures when dealing with non-HTML content.

    Maintenance

    ActivityInactive
    ResponsivenessLimited data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      MCP server that converts HTML or URLs to PDF, captures screenshots, and generates EU-compliant e-invoices (Factur-X/ZUGFeRD).
      44 npm
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      A lightweight MCP server for parsing HTML, fetching URLs, rendering terminal-style screenshots, and executing JavaScript on static HTML without external dependencies.
      3
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Screenshot and HTML Rendering MCP Server for AI Agents. Capture screenshots, render HTML to images, and generate PDFs via simple API calls. Compatible with Claude, Cursor, and any MCP client.
      1
      MIT