A
licenseNot graded
qualityB
maintenanceEnables AI agents to retrieve the closest archived snapshot of a web page, list historical captures over a date range, and count or bound when a URL was first and last archived.
217 npm
MIT
Wayback Machine
Server Details
Wayback Machine for agents: closest archived copy of a URL with its text, and full capture history
The last two health checks of this connector failed. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
- Status
- Unhealthy
- Uptime
- 27.3% over 59 days
- Last Tested
- Transport
- Streamable HTTP
- URL
- Repository
- superbot-helper/wayback-machine-mcp
- GitHub Stars
- 1
- Server Listing
- wayback-machine
TDQS
A4.2/5.0
Scored across 2 tools
Disambiguation5/5
The two tools have clearly distinct purposes: archived_copy retrieves a specific snapshot, while capture_history enumerates the available snapshots. There is no overlap or ambiguity between them.
Naming Consistency4/5
Both names are two-word noun phrases using snake_case, which is consistent and readable. They could be more actionable as verb-led commands like get_archived_copy and list_capture_history, but the current convention is uniform.
Tool Count4/5
Two tools is minimal, but the server's scope is narrowly focused on reading the Wayback Machine: fetching one capture and exploring the full capture index. Each tool earns its place, though the set feels slightly thin.
Completeness5/5
For a read-only archive access tool, the surface is complete: you can find the closest snapshot with content extraction and query the full capture history with filtering and paging. The raw-bytes URL bridges the two tools effectively.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
2 tool updates
- First observed
archived_copy - First observed
capture_history
Related MCP Connectors
Shared copies of public web pages for AI agents. Search stored pages or fetch a URL.
URL reality check for agents: status, content hash, classification, wayback fallback.
Pages, crawls and URL batches as clean Markdown and JSON for AI agents, with an Evidence Record.
Web search and page fetch for AI agents. Results come from a shared cache; cached calls cost less.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables searching Common Crawl's web archive for crawl history of any URL since 2008. It also retrieves the exact captured page bytes from the archived records.442 npmMIT
- AlicenseNot gradedqualityCmaintenanceEnables capturing web evidence, freezing content-addressed snapshots, and comparing research agents on the same sources with traceable access and quotations.1MIT
- FlicenseNot gradedqualityBmaintenanceArchives live web pages for offline replay with full interactivity, enabling AI agents to analyze page structure and behavior.1-
Try in Browser
Let your AI agent see the webWeb-to-screenshot MCP for Claude, Cursor and Codex. No cookie banners. Free to start.snap-render.comAd
Glama MCP Gateway
Add one secure layer between your agents and this server.