Lists the organization's context documents (Settings → Profile: presentations, price lists, briefs that MB Suite's AI reads as context about the organization; at most 20 per organization, counted together with Brand Voice's), newest first, paginated by cursor: file name, MIME type, size, processing status (processing, ready, or error with error_message), the AI indexing status (embedding_status, chunk_count; read but not indexed for lack of AI credits is status ready with embedding_status error and embedding_error ai_credits_exhausted, ai_personal_limit or payment_required), the AI summary of older uploads when there is one, who uploaded it and when. Brand Voice's documents are not listed here (social_brand_voice.documents.list). status filters the page read and Brand Voice's documents are dropped from it, so a page can bring fewer than limit while has_more is true: follow next_cursor. The text comes with profile.documents.get. Files are uploaded from the screen. Requires view access to the Profile module.
Scope
profile:read
Permission
View the module
MCP tool
profile_documents_listOn the full surface; on the compact one, mb_execute_operation with id: "profile.documents.list".
Declared cost: up to 202 reads and 0 writes per call (they count against the daily quota).
Parameters
limitintegerqueryoptional
How many items this page brings at most (see the maximum and the default in the schema).
Default: 50
cursorstringqueryoptional
The next_cursor of the previous page, exactly as it came (only for the same list and filters); without it, the first page.
statusenumqueryoptional
Only documents in this processing status (filtered on the page read).
Returns one context document of the organization profile with the text MB Suite extracted from it (extracted_text, up to 50,000 characters; empty while it is processing or when extraction failed): the text the AI reads as context about the organization. Not found (context_document_not_found) when the id does not exist or is a Brand Voice document. The file itself is downloaded from the screen. Requires view access to the Profile module.
Scope
profile:read
Permission
View the module
MCP tool
profile_documents_getOn the full surface; on the compact one, mb_execute_operation with id: "profile.documents.get".
Declared cost: up to 1 reads and 0 writes per call (they count against the daily quota).
Parameters
document_idstringpathrequired
Id of a context document (from profile.documents.list).
Response
idstring
file_namestring
mime_typestring
size_bytesnumber
statusenum
Values: processing, ready, error
uploaded_bystring
uploaded_atnumber
updated_atnumber
error_messagestring
embedding_statusenum
Values: pending, processing, ready, error
embedding_errorstring
chunk_countnumber
Fragments indexed for the AI (retrieval).
summarystring
Short AI summary kept from older uploads (new documents have none).
extracted_textstring
Text extracted from the file (only in profile.documents.get).
Deletes a context document of the organization profile for good: the file, its extracted text and its AI fragments, so MB Suite's AI stops using it. Brand Voice's documents are not reachable here (social_brand_voice.documents.delete). It does not go to the trash and cannot be undone: outside the screen it always needs a dry run (which says how many AI fragments go) and its confirm_token, and a credential allowed to delete. Returns how many fragments were removed. Requires edit access to the Profile module.
Needs confirmation: first dry_run: true (preview and confirm_token, valid 10 minutes and for one run), then the same body with confirm_token. In a few operations only with certain data: the description says when. Why and how: Dry run and confirm_token.
Scope
profile:writeand “Allow deletions” (profile:delete in OAuth)
Permission
Edit in the module
MCP tool
profile_documents_deleteOn the full surface; on the compact one, mb_execute_operation with id: "profile.documents.delete".
Declared cost: up to 45 reads and 45 writes per call (they count against the daily quota).
Parameters
document_idstringpathrequired
Id of a context document (from profile.documents.list).