Wayback Machine
Let your agent query the Internet Archive Wayback Machine for historical pages, snapshots, and research without mandatory API keys.
Overview
mcp-wayback-machine is an MCP server for the Idea phase that lets agents query the Wayback Machine for historical web snapshots without required API keys.
What is this MCP server?
- MCP server and CLI for Wayback Machine access with no required API keys
- Anonymous mode works without credentials; optional WAYBACK_ACCESS_KEY and WAYBACK_SECRET_KEY raise SPN2 rate limits
- npm package mcp-wayback-machine v3.7.1 with npx runtime hint and stdio transport
- Useful for competitor page history, deprecated docs, and launch/SEO forensic research
- Registry version 3.7.1
- npm identifier mcp-wayback-machine with npx runtime hint
- No required API keys; optional WAYBACK_ACCESS_KEY and WAYBACK_SECRET_KEY for SPN2 limits
Community signal: 33 GitHub stars.
What problem does it solve?
You need archived competitor and reference pages in agent context but hate juggling the Wayback UI and broken live URLs during early research.
Who is it for?
Indie founders doing competitor research, content archaeology, or SEO forensics who want zero-key startup and optional IA credentials later.
Skip if: Teams that need guaranteed current-site scraping, bulk archival compliance, or non-Archive web automation.
What do I get? / Deliverables
After you add the server, your agent can fetch and reason over Wayback snapshots from chat or CLI with optional higher rate limits via IA keys.
- Agent-driven Wayback Machine queries and snapshot context
- CLI-capable archive lookups alongside MCP tools
- Research-grade historical URL evidence for positioning and SEO notes
Recommended MCP Servers
Journey fit
Idea / research is canonical because founders use archived web history for competitor forensics, messaging evolution, and proof of prior art before they build. Research subphase covers digging into past site versions, dead links, and historical claims during discovery and positioning work.
How it compares
Wayback archive MCP and CLI, not a general headless browser scraper or SEO rank tracker.
Common Questions / FAQ
Who is mcp-wayback-machine for?
It is for solo builders and researchers who want Claude Code, Cursor, or CLI workflows to query Internet Archive snapshots through MCP.
When should I use mcp-wayback-machine?
Use it during Idea research for competitor history, dead-link recovery, and prior messaging, and during Launch SEO work when you need historical page evidence.
How do I add mcp-wayback-machine to my agent?
Register mcp-wayback-machine via npx in stdio MCP config; optionally set WAYBACK_ACCESS_KEY and WAYBACK_SECRET_KEY for higher SPN2 limits.