Wayback Mcp

io.github.mrfentmenv1.0.0Updated Oct 1, 2026

MCP server for the Wayback Machine, snapshot history, page availability, and dead site recovery.

VerifiedSTDIODesktop onlyWeb Search & Scraping

Overview

AI-generated overview

Lets an assistant query the Wayback Machine for archived snapshots, page availability, and recovery of dead sites.

What it does
This MCP server connects an assistant to the Internet Archive's Wayback Machine. Based on its description, it covers snapshot history, checking whether a page is available, and recovering content from sites that are no longer online. It runs locally over stdio and exposes its capabilities as tools to the assistant.
When to use it
Useful when you need to look up how a web page looked at an earlier date, verify whether an archived copy exists, or retrieve content from a site that has gone offline. It fits research, citation checking, and historical web lookups.
Requirements
Runs as a local process on the user's machine, installed from the npm package wayback-mcp over stdio. Desktop only; no web-hosted version. No authentication, environment variables, or headers are declared, so no credentials are needed.
Before you install
The server queries the Internet Archive, so the pages and URLs you look up are sent to that third party. Archived content may be incomplete, outdated, or missing, and results should be verified before being relied on.

Installation

In SourceWeft

  1. Open Wayback Mcp in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

This repository has no README.

Tools

0
Tool metadata has not been indexed yet.

Version history

1
  1. v1.0.0LatestOct 1, 2026