> ## Documentation Index
> Fetch the complete documentation index at: https://docs.gc.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Get vault documents
> Read a vault's table: one row per document, with the value GC AI extracted for every column.
The MCP server is in public beta. It is open to use and still being refined, so tools and behavior may change.
**Tool** `get_vault_documents` ยท **Behavior** Read-only
Read a vault's table: one row per document, with the value GC AI extracted for every column. This is the tool for questions the table can answer directly, such as which contracts expire this quarter, which name a counterparty, or which are missing a value. Narrow with `filters` and `sort` rather than paging everything. `values` is keyed by column `field_key`; read the keys, labels, and types from `get_vault_columns` first. A value is a string, and structured columns carry JSON in it: a currency holds `{"amount","currency"}`, a date holds `YYYY-MM-DD`, a multi-select holds a JSON array. `null` means the scan found no value. A document appears here once its first scan writes values, a few minutes after upload, so a row missing right after `upload_file` is not lost. To answer from the text inside the documents rather than the extracted columns, use `ask_gcai` with this vault instead.
## Input parameters
The vault to read, from `get_vaults`.
Fetch one row by its `document_id`. Provide either `document_id` or a list query (`q`/`filters`/`sort`/`cursor`), not both.
Case-insensitive substring of the document name. This searches names only, not the text inside the documents. To answer a question from the contents, use `ask_gcai` with this `vault_id` instead.
Rules combined with AND. A rule naming an unknown column, or an operator that column cannot use, is an error rather than a rule that is quietly dropped, so a count is never silently wrong.
Column key, from `get_vault_columns`.
One of: contains, equals, in, date\_range, is\_before, is\_after, number\_range, boolean, list\_length, equals\_only, party\_contains, not\_contains, not\_equals, is\_empty, is\_not\_empty.
Shape depends on the operator: a string for `contains`, an array for `in`, `{from,to}` for `date_range`, `{min,max}` for `number_range`, omitted for `is_empty`/`is_not_empty`.
Sort by a column key, or by `fileName`, `extractedAt`, or `sourceName`.
Opaque pagination cursor from a previous response's `next_cursor`. Omit for the first page; repeat any filters (e.g. `q`) alongside it.
Max items to return (default 25, max 100). Defaults to `25`.
## Response