Archive.org for AI agents

Archive.org, the Internet Archive, hosts a huge library of digitized books, media, and web history including the Wayback Machine, used by researchers and archivists to search and manage items. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.

Connect Archive.org See the 26 actions ↓

Files and storageAPI keyMCP + RESTarchive.org

AUDIT LOG · ARCHIVE.ORGPOLICY: acme-support

09:41:07 · claude · u_8f2read

archive_org.list_tasks

List Archive.org Tasks✓ allowed · 212ms

09:41:08 · claude · u_8f2read

archive_org.get_task_log

Get Archive.org Task Log✓ allowed · 164ms

09:41:09 · claude · u_8f2write

archive_org.update_item_metadata

Update Item Metadata✓ approved · approved by user

09:41:12 · claude · u_8f2destructive

archive_org.delete_item_file

Delete Item File✕ blocked · policy: deny

EVERY ARCHIVE.ORG CALL, ON THE RECORD

01 · USE CASES

What agents do in Archive.org.

Search the Internet Archive for an item

Search archive.org items by keyword to find a specific document or recording.

Find a Wayback Machine snapshot

Look up archived snapshots of a URL captured over time by the Wayback Machine.

Confirm before deleting an item file

Removing a file from an archived item is destructive and should be confirmed first.

02 · ACTIONS

26 Archive.org actions, graded by risk.

Every Archive.org action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.

read

Look things up. Allowed by default.

archive_org.list_tasks
List Archive.org Tasks
archive_org.get_task_log
Get Archive.org Task Log
archive_org.search_items
Search Archive.org Items
archive_org.get_my_review
Get My Review
archive_org.get_iiif_manifest
Get IIIF Manifest
archive_org.get_item_metadata
Get Item Metadata
archive_org.get_connected_user
Get Connected Archive.org User
archive_org.get_detailed_views
Get Detailed Archive.org Views
archive_org.get_iiif_image_info
Get IIIF Image Info
archive_org.get_item_view_counts
Get Item View Counts
archive_org.get_task_rate_limits
Get Task Rate Limits
archive_org.get_item_view_history
Get Item View History
archive_org.list_wayback_captures
List Wayback Captures
archive_org.find_wayback_snapshots
Find Wayback Snapshots
archive_org.check_upload_limit
Check Archive.org Upload Limit
archive_org.download_item_file
Download Item File

+ 1 MORE

write

Create and change things. Allow, or ask the user first.

archive_org.update_item_metadata
Update Item Metadata
archive_org.derive_item
Derive Archive.org Item
archive_org.copy_item_file
Copy Item File
archive_org.upload_item_file
Upload Item File
archive_org.upsert_my_review
Upsert My Archive.org Review
archive_org.render_iiif_image
Render IIIF Image
archive_org.advanced_search_items
Advanced Search Archive.org Items

destructive

Delete, cancel or archive. Ask first, or deny outright.

archive_org.delete_item_file
Delete Item File
archive_org.delete_my_review
Delete My Archive.org Review

03 · HOW IT WORKS

Archive.org in three steps.

01Your users connect Archive.orgThey add their Archive.org api key on Arc0 Connect, under your brand. It goes straight into the vault.
02You set the rulesReads run, writes like “update Item Metadata” can wait for the user, and “delete Item File” can be denied outright.
03Any agent can actYour agent calls Archive.org through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.

POLICY.TS

await arc0.policies.set('archive_org', {
  read: 'allow',
  write: 'ask',        // update_item_metadata
  destructive: 'deny',  // delete_item_file
})

# Claude Code: the same connection, one URL
$ claude mcp add --transport http arc0 \
    https://mcp.arc0.ai/u/u_8f2

04 · AUTH AND DATA

How Archive.org connects.

Users add their Archive.org api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

The same Archive.org connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →

AUTH: API key
CREDENTIALS: Per-tenant encrypted vault
MODEL SEES: Results only, never credentials
AUDIT LOG: Every call, on every plan

05 · WORKS WITH

Use Archive.org from any agent.

Claude

ChatGPT

Cursor

Codex

VS Code

OpenAI Agents SDK

Claude Agent SDK

Vercel AI SDK

Mastra

LangGraph

06 · RELATED

More files and storage apps.

Google Drive104 actions

WordPress.com10 actions

ALL FILES AND STORAGE APPS →

07 · FAQ

Archive.org and Arc0, answered.

Q01

Can I use Archive.org with Claude, ChatGPT or Cursor?

Yes. Connect Archive.org to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Archive.org actions you allow.

Q02

How do users connect Archive.org?

Users add their Archive.org api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.

Q03

Which Archive.org actions can my agent take?

26 in total: 17 read, 7 write and 2 destructive, such as “update Item Metadata”. Your policies decide which of them each agent may call.

Q04

Can I stop my agent from deleting things in Archive.org?

Yes. Actions like “delete Item File” are graded destructive. Set destructive actions to deny, or to ask so the user approves each one, and blocked calls still show up on the audit log.

Q05

Can my own backend call Archive.org too?

Yes. The same Archive.org connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.

Get started

Plug Archive.org into your agent.

Your users connect Archive.org once, under your brand. Your agent gets 26 actions behind your policies, with every call on the record.

Connect Archive.org Browse all apps →

Free to build · MCP + REST · Audit log on every plan