MCP server for the Wayback Machine, snapshot history, page availability, and dead site recovery.
Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.
Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.
Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.
get_snapshotsList the Wayback Machine snapshot history for a URL, optionally limited to a date range.List the Wayback Machine snapshot history for a URL, optionally limited to a date range.
No input schema was published for this tool.
domain_snapshotsList archived pages across a whole domain (every path), not just one exact URL.List archived pages across a whole domain (every path), not just one exact URL.
No input schema was published for this tool.
site_historyFirst and last capture of a URL, plus which years it was archived in.First and last capture of a URL, plus which years it was archived in.
No input schema was published for this tool.
get_availabilityCheck whether a page is archived and get its closest snapshot.Check whether a page is archived and get its closest snapshot.
No input schema was published for this tool.
read_snapshotRead the text content of an archived page — useful for reading dead or changed sites.Read the text content of an archived page — useful for reading dead or changed sites.
No input schema was published for this tool.
compare_yearsRead the same URL as it looked in several different years, to see how a page changed.Read the same URL as it looked in several different years, to see how a page changed.
No input schema was published for this tool.
status_historyOne row per archived month with the HTTP status recorded then, so a page that started redirecting or failing can be dated.One row per archived month with the HTTP status recorded then, so a page that started redirecting or failing can be dated.
No input schema was published for this tool.
capture_gapsHow much of a period is actually archived for a URL: captured months, missing months, coverage percent and the longest gap.How much of a period is actually archived for a URL: captured months, missing months, coverage percent and the longest gap.
No input schema was published for this tool.
snapshot_diffCompare the same page in two archived years and list the wording that appeared and the wording that vanished.Compare the same page in two archived years and list the wording that appeared and the wording that vanished.
No input schema was published for this tool.
broken_pagesArchived captures across a domain that were not HTTP 200 - redirects and dead pages, which is what link rot looks like.Archived captures across a domain that were not HTTP 200 - redirects and dead pages, which is what link rot looks like.
No input schema was published for this tool.
content_profileWhat a domain's archive is made of rather than when it was captured: every capture grouped into pages, stylesheets, scripts, images, PDFs and the rest, with each family's share, the top mime types, status-code spread and the busiest path prefixes.What a domain's archive is made of rather than when it was captured: every capture grouped into pages, stylesheets, scripts, images, PDFs and the rest, with each family's share, the top mime types, status-code spread and the busiest path prefixes.
No input schema was published for this tool.
prefix_inventoryWhat lives under a path: the archived URLs beneath a domain prefix, how many there are, the years they span, the sections one level down ranked by size, and the status and content mix. Answers the inventory question behind 'what did this part of the site contain'.What lives under a path: the archived URLs beneath a domain prefix, how many there are, the years they span, the sections one level down ranked by size, and the status and content mix. Answers the inventory question behind 'what did this part of the site contain'.
No input schema was published for this tool.
12 of 12 tools published a description.
Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.
MCP server for the Wayback Machine, snapshot history, page availability, and dead site recovery.
Linked names open Forge’s index of every entry observed exposing that tool. Browse all indexed tools.
The crawl stopped at the depth-4 limit. Anything below that level was never resolved.
The crawl stopped at the 60-package limit. The rest of the tree was never resolved.
36 more resolved packages are not drawn here (display cap: 24). Every dependency carrying an advisory is drawn regardless of the cap. Full inventory (CycloneDX SBOM)
54 declared dependencies never landed in the tree. They are missing from Forge's resolution, not from the package.
+42 more not listed. The counts by reason above cover all of them.
Not followed: peerDependencies. This tree covers runtime dependencies only, so anything those pull in was never resolved.