Archive API docs
esc
    Jump to
    Getting started Token, first query, response Explorer Run queries in the browser items The connection most integrations start with Changelog Additions and deprecations

    Narrow by kind with a prefix — q: queries, m: mutations, t: types, g: guides, f: fields and arguments.

    Use with ChatGPT

    Connect Archive to ChatGPT or Codex to search captured content, look up creators, and manage saved views from a conversation. In ChatGPT, Archive is listed in the directory — find it, connect, and sign in. In Codex, the endpoint URL is all you need: no client ID, no token to copy, and nothing to install.

    Codex and any other client that connects by URL use this endpoint. A ChatGPT install never asks for it.

    Endpoint 
    POST https://app.archive.com/api/v2/mcp

    Set up your client

    Follow the instructions for your client. After you authorize the connection, the client can read — and if you granted write access, update — content in the workspaces you can already access.

    Archive is listed in the ChatGPT directory, so there is nothing to configure by hand. ChatGPT’s deep research is read-only — it drives a search/fetch tool pair and never writes or modifies anything — and Archive’s tools are named for the product surface instead: searchItems, searchCreators, getWorkspaces.

    1. Open the ChatGPT directory at chatgpt.com/plugins — it is also reachable from Settings → Plugins and from the sidebar.
    2. Find Archive and select Connect.
    3. Sign in to Archive when the consent screen opens, and choose whether to grant the optional write scope.
    4. Back in a chat, bring Archive in with an @ mention or from the tools menu (+).

    What happens during authorization

    ChatGPT and Codex both authorize over OAuth 2.1, and neither needs an API token. The client discovers Archive and registers itself; your only step is the consent screen.

    1. The client’s first call gets HTTP 401 with a WWW-Authenticate challenge naming Archive’s protected-resource metadata.
    2. It fetches the authorization-server metadata and registers itself via Dynamic Client Registration — nothing to configure on Archive’s side.
    3. You log in at Archive’s consent screen and choose the scopes to grant. Without the optional write scope the connection is read-only.
    4. The client exchanges the authorization code for an opaque, Archive-issued access token scoped to what you approved.

    Each person authorizes their own connection, and ChatGPT and Codex authorize separately, so revoking one leaves the others working. Scopes are chosen at consent time only, so to change them, disconnect Archive and connect it again — in ChatGPT, or with codex mcp login archive after removing and re-adding the server in Codex.

    Verify it works

    @-mention Archive in ChatGPT and ask it to list your workspaces. If the connection works, it calls getWorkspaces and returns your actual workspace names and IDs. In Codex, /mcp lists the connected servers and the tools they expose. If the tool list is empty or every call returns 401, authorization didn’t complete — disconnect Archive and connect it again in ChatGPT, or re-run codex mcp login archive.

    See Example prompts for more starting points, or Troubleshooting if something isn’t working.

    Running a server-side agent instead? A bearer token from the Integration tab also works, but it is a write-capable, server-side secret rather than a per-person authorization. See Connect a client for when to use which.