MCP Wayback Machine Server

Build Status

Release Status

An MCP (Model Context Protocol) server and CLI tool for interacting with the Internet Archive's Wayback Machine without requiring API keys.

Built with: MCP TypeScript Template

Overview

This tool can be used in two ways:

1. As an MCP server - Integrate with Claude Desktop for AI-powered interactions

2. As a CLI tool - Use directly from the command line with npx or global installation

Features:

• Save web pages to the Wayback Machine

• Retrieve archived versions of web pages

• Check archive status and statistics

• Search the Wayback Machine CDX API for available snapshots

Features

• 🔐 No API keys required - Uses public Wayback Machine endpoints

• 💾 Save pages - Archive any publicly accessible URL

• 🔄 Retrieve archives - Get archived versions with optional timestamps

• 📊 Archive statistics - Get capture counts and yearly statistics

• 🔍 Search archives - Query available snapshots with date filtering

• ⏱️ Rate limiting - Built-in rate limiting to respect service limits

• 💻 Dual mode - Use as MCP server or standalone CLI tool

• 🎨 Rich CLI output - Colorized output with progress indicators

• 🔒 TypeScript - Full type safety with Zod validation

Tools

1. save_url

Archive a URL to the Wayback Machine.

• Input: url (required) - The URL to save

• Output: Success status, archived URL, and timestamp

• Handles rate limiting automatically

2. get_archived_url

Retrieve an archived version of a URL.

• Input:

  • url (required) - The URL to retrieve

  • timestamp (optional) - Specific timestamp (YYYYMMDDhhmmss) or "latest"

• Output: Archived URL, timestamp, and availability status

3. search_archives

Search for all archived versions of a URL.

• Input:

  • url (required) - The URL to search for

  • from (optional) - Start date (YYYY-MM-DD)

  • to (optional) - End date (YYYY-MM-DD)

  • limit (optional) - Maximum results (default: 10)

• Output: List of snapshots with dates, URLs, status codes, and mime types

4. check_archive_status

Check archival statistics for a URL.

• Input: url (required) - The URL to check

• Output: Archive status, first/last capture dates, total captures, yearly statistics

Technical Details

• Transport: Stdio (for Claude Desktop integration)

• HTTP Client: Built-in fetch with timeout support

• Rate Limiting: 15 requests per minute (conservative limit)

• Error Handling: Graceful handling with detailed error messages

• Validation: URL and timestamp validation

• TypeScript: Full type safety with Zod schema validation

API Endpoints (No Keys Required)

• Save Page Now: https://web.archive.org/save/{url} - Archive pages on demand

  • Documentation

• Availability API: http://archive.org/wayback/available?url={url} - Check archive status

  • Documentation

• CDX Server API: http://web.archive.org/cdx/search/cdx?url={url} - Advanced search and filtering

  • Documentation

• TimeMap API: http://web.archive.org/web/timemap/link/{url} - Get all timestamps for a URL

  • Memento Protocol

• Metadata API: https://archive.org/metadata/{identifier} - Get Internet Archive item metadata

  • Documentation

• Search API: https://archive.org/advancedsearch.php?q={query}&output=json - Search collections

  • Documentation

Project Structure

Installation

As a CLI Tool (Quick Start)

Use directly with npx (no installation needed):

Or install globally:

As an MCP Server

Install for use with Claude Desktop:

From Source

Usage

CLI Usage

The tool provides a wayback command (or use npx mcp-wayback-machine):

Save a URL

Get an archived version

Search archives

Check archive status

Get help

Claude Desktop Configuration

Add to your Claude Desktop settings:

Using npm installation

Using local installation

For development (without building)

Development

Available Commands

Testing

The project uses Vitest for testing with the following features:

• Unit tests for all tools and utilities

• Integration tests for CLI commands

• Coverage reporting with c8

• Tests located alongside source files (.test.ts)

Run tests:

Examples

Using with Claude Desktop

Once configured, you can ask Claude to:

• "Save https://example.com to the Wayback Machine"

• "Find archived versions of https://example.com from 2023"

• "Check if https://example.com has been archived"

• "Get the latest archived version of https://example.com"

CLI Script Examples

Troubleshooting

Common Issues

1. "URL not found in archive": The URL may not have been archived yet. Try saving it first.

2. Rate limit errors: Add delays between requests or reduce request frequency.

3. Connection timeouts: Check your internet connection and try again.

4. Invalid timestamp format: Use YYYYMMDDhhmmss format (e.g., 20231225120000).

Debug Mode

Resources

Official Documentation

• Wayback Machine APIs Overview

• Internet Archive API Documentation

• CDX Server Documentation

• Save Page Now 2 (SPN2) API

• Memento Protocol Guide

Rate Limits & Best Practices

• No hard rate limits for public APIs

• Be respectful - add delays between requests

• Use specific date ranges to reduce CDX result sets

• Cache responses when possible

• Include descriptive User-Agent header

Community

• MCP Discord - Get help and share your experience

• Internet Archive Forum - Wayback Machine discussions

Authenticated APIs (Not Implemented)

For completeness, here are Internet Archive APIs that require authentication but are not included in this MCP server:

S3-Compatible API (IAS3)

• Authentication: S3-style access keys from https://archive.org/account/s3.php

• Features: Upload files, modify metadata, create items, manage collections

• Documentation:

  • Internet Archive Python Library

  • IAS3 API Documentation

  • Metadata Schema

Authenticated Search API

• Authentication: S3 credentials

• Features: Advanced search capabilities, higher rate limits

• Access: Requires Internet Archive account

• Documentation:

  • Advanced Search API

  • Search API Examples

Save Page Now 2 (SPN2) - Enhanced Features

• Authentication: Partnership agreement typically required

• Features: Bulk captures, priority processing, higher rate limits

• Documentation:

  • SPN2 API Guide

  • Save Page Now Overview

Partner/Bulk Access APIs

• Authentication: Special partnership agreement

• Features: Bulk downloads, custom data exports, direct database access

• Access: Contact Internet Archive directly

• Documentation:

  • Researcher Services

  • Bulk Access Information

Getting API Keys

1. Create account at archive.org

2. Visit S3 API page (requires login)

3. Generate Access Key and Secret Key pair

4. Configure using ia configure command or manual configuration

Note: This MCP server focuses on public, keyless APIs to maintain simplicity and avoid credential management.

License

This project is licensed under the Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.

You are free to:

• Share — copy and redistribute the material in any medium or format

• Adapt — remix, transform, and build upon the material

Under the following terms:

• Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made

• NonCommercial — You may not use the material for commercial purposes

• ShareAlike — If you remix, transform, or build upon the material, you must distribute your contributions under the same license

For commercial use or licensing inquiries, please contact the copyright holder.