What it does
manage_data_store lets an agent shape the schema of a data store
(a structured knowledge base): create tables, add or alter columns, add indexes,
create views, and inspect the current schema. Changes apply to the store’s own
isolated Postgres database.
create_storecreates a brand-new data store (name+ optionaldescription) — noknowledge_base_idneeded. Use it when work deserves its own store rather than adding unrelated tables to an existing one. Creation only: deleting stores stays withmanage_knowledge_bases.
For an overview of structured data stores — what they are and when to use one —
see Data Stores.
Parameters
Key behaviors
- A primary key is added for you.
create_tableadds anidprimary key automatically unless you define your own. - Views give apps aggregation power.
create_viewstores an agent-authoredSELECTthat apps read like a table — the way to let an app show a rollup or join over a large table without pulling every row. Views run with the reading role’s privileges, so they stay safely scoped to the store. - Destructive changes are gated. Dropping a column, table, or view requires
confirm: true, because a published app may depend on it. - Locked stores refuse structure changes. If the store’s creator has locked
it, every operation except
describefails unless the requesting user is its creator or an org admin. Rows stay writable throughwrite_data_store.manage_knowledge_baseslistshowslockedandcanEditfor locked stores. - Every change is audited, and the store’s cached schema — which the agent sees in its context — refreshes automatically after each change.
Common use cases
Create a table
Create a view for an app to chart
Related
- Query Data Store — read data with SQL
- Write Data Store — insert, update, delete, upsert
- Data Stores — the feature overview