Mcp Webpage Timestamps

by Fabien-desablens

242 downloads
Not rated
GitHub

About

MCP server for extracting webpage creation, modification, and publication timestamps

Details

Author
Fabien-desablens
Downloads
242
Categories
Automation

- Extracts timestamps from HTML meta tags, HTTP headers, JSON-LD, microdata, and heuristics.
- Provides confidence scoring (high, medium, low) based on source reliability.
- Supports configurable timeouts and retry logic.
- Offers batch processing for multiple URLs simultaneously.
- TypeScript implementation with full type safety.
- Returns detailed source information per timestamp.

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Mcp Webpage Timestamps
    Command (node, npx, python, etc.) npx
    Arguments
    • Argument 1 mcp-webpage-timestamps

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Install globally via npm install -g mcp-webpage-timestamps, then add to your MCP client configuration using npx mcp-webpage-timestamps as the command. Use the extract_timestamps tool for single URLs or batch_extract_timestamps for multiple URLs simultaneously.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "mcp webpage timestamps": {
            "command": "npx",
            "args": [
                "mcp-webpage-timestamps"
            ]
        }
    }
}

Command

"npx"

Args

[
    "mcp-webpage-timestamps"
]

What is MCP Webpage Timestamps?

MCP Webpage Timestamps is a specialized Model Context Protocol server that extracts creation,
modification, and publication timestamps from web pages. It's perfect for content freshness
analysis, temporal web scraping, and understanding the lifecycle of web content.

Why Use This Server?

🎯 Comprehensive Data Sources

Unlike simple scrapers, this server checks multiple sources:
- HTML meta tags (OpenGraph, Dublin Core, custom tags)
- HTTP response headers
- JSON-LD structured data
- Microdata markup
- Heuristic text analysis

πŸ” Confidence Scoring

Each extracted timestamp comes with a confidence level:
- High: Found in multiple reliable sources
- Medium: Single reliable source
- Low: Heuristic detection only

⚑ Performance & Reliability

- Configurable timeouts and retry logic
- Batch processing for multiple URLs
- Comprehensive error handling
- TypeScript implementation with full type safety

Available Tools

extract_timestamps

Extract timestamps from a single webpage with detailed source information.

Example:
{
"name": "extract_timestamps",
"arguments": {
"url": "https://example.com/article",
"config": {
"timeout": 10000,
"enableHeuristics": true
}
}
}

batch_extract_timestamps

Process multiple URLs simultaneously for efficient bulk analysis.

Example:
{
"name": "batch_extract_timestamps",
"arguments": {
"urls": [
"https://example.com/article1",
"https://example.com/article2"
]
}
}

Use Cases

- Content Freshness Analysis: Evaluate how recent web content is
- SEO Research: Analyze publication patterns and content updates
- Web Scraping: Add temporal context to scraped data
- Academic Research: Study temporal aspects of web content
- Content Management: Track content lifecycle and updates

Installation & Setup

Global Installation

npm install -g mcp-webpage-timestamps

MCP Configuration

Add to your MCP client configuration:

{
"mcpServers": {
"webpage-timestamps": {
"command": "npx",
"args": ["mcp-webpage-timestamps"]
}
}
}

Development Setup

git clone https://github.com/Fabien-desablens/mcp-webpage-timestamps.git
cd mcp-webpage-timestamps
npm install
npm run build
npm start

Response Format

{
url: string;
createdAt?: Date;
modifiedAt?: Date;
publishedAt?: Date;
sources: TimestampSource[];
confidence: 'high' | 'medium' | 'low';
errors?: string[];
}

Links

- GitHub: https://github.com/Fabien-desablens/mcp-webpage-timestamps
- npm: https://www.npmjs.com/package/mcp-webpage-timestamps
- Author: Fabien Desablens

No reviews yet β€” be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.