Wayback Machine MCP Server

This server provides access to the Internet Archive's Wayback Machine for retrieving historical web snapshots and searching archived content.

List snapshots: Get available archived versions of a URL with date range filtering (from, to), result limits, and match type control (exact, prefix, host, domain)
Fetch archived pages: Retrieve content from specific timestamps (YYYYMMDDHHMMSS format), with option to get original content without Wayback Machine's rewriting
Search archive items: Query Internet Archive's collection with advanced filters like media type, collection, field selection, sorting, and pagination
Resource access: Directly fetch archived content via wayback://{url}/{timestamp} resource URLs

Wayback Machine MCP Server (Python)

PyPI version Python versions License: MIT

A Model Context Protocol (MCP) server that provides access to the Internet Archive Wayback Machine: list snapshots and fetch archived pages. Inspired by the TypeScript server described in the LobeHub listing.

Reference: Wayback MCP (listing) — link
Reference: Internet Archive APIs — Wayback APIs index
Reference: MCP server quickstart — Build an MCP Server

Features

Tools
- get_snapshots(url, from, to, limit, match_type) via Wayback CDX API
- get_archived_page(url, timestamp, original) fetches archived content
- search_items(query, mediatype, collection, fields, sort, rows, page) searches archive.org items
Resource
- wayback://{url}/{timestamp} returns the archived page content

Install

python -m venv .venv source .venv/bin/activate pip install -r requirements.txt

Run (stdio)

python -m wayback_mcp.server

Install as CLI

pip install wayback-mcp wayback-mcp

Run with uvx (no install)

uvx wayback-mcp

Pin Python version:

uvx --python 3.12 wayback-mcp

Pin package version:

uvx --from wayback-mcp==0.1.1 wayback-mcp

Configure in MCP client

Claude Desktop settings (example):

{ "mcpServers": { "wayback-machine": { "command": "wayback-mcp", "args": [], "env": {}, "disabled": false, "autoApprove": [] } } }

Alternatively, using uvx (no install):

{ "mcpServers": { "wayback-machine": { "command": "uvx", "args": ["wayback-mcp"], "env": {}, "disabled": false, "autoApprove": [] } } }

Usage examples

Tool call (snapshots):

get_snapshots(url="example.com", from="20200101", to="20201231", limit=10)

Tool call (page):

get_archived_page(url="example.com", timestamp="20200101120000", original=true)

Tool call (items search):

search_items( query="title:(Wayback) AND creator:(Internet Archive)", mediatype="texts", fields=["identifier","title","creator","mediatype","publicdate"], sort=["publicdate desc"], rows=20, page=1 )

Resource fetch:

wayback://example.com/20200101120000

Notes

Snapshot data via CDX API: https://web.archive.org/cdx/search/cdx?url={url}&output=json
Page retrieval via Wayback: https://web.archive.org/web/{timestamp}/{url} (or id_ mode for original content)
Advanced item search endpoint: https://archive.org/advancedsearch.php (JSON output)

Wayback Machine MCP Server