oto.cx
zeendoc

zeendoc

zeendoc.

Zeendoc document management (GED), read-only: the binders of the cabinet

add to otoauth : —prefix : zeendoc_*

setup & usage

⚠ a zeendoc user and the cabinet id

Zeendoc has no API key: the connector signs in as a Zeendoc user (the email and password of the web application) on a cabinet, whose id is the segment after armoires.zeendoc.com/ in the address bar (armoires.zeendoc.com/<cabinet id>/). A Zeendoc administrator creates a user dedicated to oto, with read rights on the binders to serve; the three values are pasted into oto.

  • byo-only: no shared oto account — these are your documents, each organization sets its own
  • the user's rights bound what is visible: a binder the user cannot search is refused
  • read-only: the connector never uploads, re-indexes or deletes a document
  • the "test connection" button signs in and lists the user's binders: no side effect
    • ▸ find, count and read documents
  • "which binders and fields are there" → zeendoc(op="binders")
  • "the exact spelling of a supplier" → zeendoc(op="values", binder="coll_2", field="custom_t2", term="acm")
  • "this supplier's invoices since January" → zeendoc(op="search", binder="coll_2", criteria=[{"field": "custom_t2", "operator": "EQUALS", "value": "ACME"}, {"field": "custom_d4", "operator": "ABOVE", "value": "2026-01-01"}])
  • "how many documents mention plasterboard" → zeendoc(op="count", binder="coll_2", criteria=[{"field": "Plain_Text", "operator": "CONTAINS", "value": "plasterboard"}])
  • "the lines and prices of this invoice" → zeendoc(op="text", binder="coll_2", res_id=1234)
  • "the PDF of this invoice" → zeendoc(op="file", binder="coll_2", res_id=1234)
    • · fields, pages, what is not served
  • field names (custom_t2) come from op="binders", labels are the cabinet's own; a list field (site code, document type) is filtered by the id of its choice
  • a search returns at most 50 documents per page: page with offset up to nbDocs; stats sums the amount fields over every match, not only the page
  • text is Zeendoc's own extraction (OCR), laid out as on the page; file returns the PDF as its extracted text plus a short-lived link to the file
  • not served: upload, index updates, deletion, saved searches, document history
    • ⚙ multiple comptes

    this connector accepts multiple comptes: each stored credential becomes a named account (one name per compte), at your level, your team's or your org's.

  • the first one doesn't need a name; from the second on, each one carries its own (the first then takes the name "principal", renamable)
  • without specification, the agent takes the only stored compte, otherwise the one marked as default; otherwise the call is refused, naming the available comptes — never a random choice
  • target a compte for a call: _account="<name>" on the tool; list them: oto_identity(op='list', connector='zeendoc') (scope='org' or scope='group' for the org's or team's)
  • set the default: oto_identity(op='set', connector='zeendoc', identity_id='<name>'); rename: op='rename' with new_name
  • ⚠️ no tool walks through the comptes on its own: a total across several comptes is obtained by calling each one (_account) and adding up

    • outils

    chargement…

    usage

    claude code — install the oto plugin — claude plugin marketplace add otomata-tech/oto-plugin — mcp + skill configured.
    claude.ai — add mcp.oto.cx/mcp as a custom connector (guide)
    cli — pipx install oto-cli then oto zeendoc …
    ← tous les connecteurscatalogue mcp →