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, find Archive in the directory and select Connect. In Codex, add the endpoint below. Then sign in to Archive to authorize your connection. You do not need to create an API token.

    Use this endpoint for Codex. ChatGPT’s directory connection does not require you to enter it.

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

    Set up your client

    Choose your client below. It can read data in your authorized workspaces. It can make changes only if you grant write access and the client permits writes.

    Use Archive in a regular chat. Its tools include searchItems, searchCreators, and getWorkspaces. These are different from the search/fetch tools used by ChatGPT’s read-only deep research connections.

    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’s authorization endpoints and registers itself. You sign in and approve the permissions on Archive’s 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 using Dynamic Client Registration.
    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. ChatGPT and Codex connections are separate, so revoking one leaves the other working. To change permissions, disconnect Archive and authorize it again. In Codex, remove and re-add the server, then run codex mcp login archive.

    Verify it works

    @-mention Archive in ChatGPT and ask it to list your workspaces. If the connection works, it calls getWorkspaces and returns your workspace names and IDs. In Codex, /mcp lists the connected servers and their tools. If no tools appear or calls return 401, authorize the connection again. Disconnect and reconnect Archive in ChatGPT, or run codex mcp login archive in Codex.

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

    For an agent you run on your own server, use an API bearer token from the Integration tab. It grants write access and must be kept secret. See Connect a client for setup instructions.