Skip to main content

Permissions & Tools

Agents can only access resources you explicitly allow through permissions. Each permission grants the agent one or more tools it can call during execution.

Built-in Tools

These tools are always available, regardless of permissions:

ToolDescription
files_listList files in the persistent storage directory
files_readRead a file from persistent storage
files_writeWrite a file to persistent storage
finishEnd the agent execution with a response

Tables

Grant the agent access to query and modify your database tables. Each table can have granular action control.

ToolDescription
tables_select_{table}Query rows from the table
tables_insert_{table}Insert new rows
tables_update_{table}Update existing rows
tables_delete_{table}Delete rows

Configure per table in the permissions picker — select which tables and which actions (select, insert, update, delete) the agent can perform.

Connections

Grant the agent access to external integrations (Slack, Stripe, Salesforce, etc.). Instead of creating a separate tool for each possible action, agents use a search and execute pattern:

ToolDescription
search_connection_actionsSearch available actions for a connection (with regex and pagination)
execute_connection_actionExecute a specific action on a connection

The agent first searches for the right action, then executes it. Only actions from connections you explicitly permit are allowed.

Example flow:

  1. Agent calls search_connection_actions with connection_name: "slack" and query: "send.*message"
  2. Gets a list of matching actions with their parameter schemas
  3. Calls execute_connection_action with the chosen action name and parameters

Source Code

Grant the agent read-only access to your project's source code files. Useful for agents that need to analyze or reference your codebase.

ToolDescription
source_code_listList source code files (filterable by glob pattern)
source_code_readRead a source code file

You can restrict access to specific paths using a glob pattern (e.g., src/**/*.py).

Browser

When a browser session is provided, the agent gets tools for web automation:

ToolDescription
navigateNavigate to a URL
clickClick an element on the page
type_textType text into an input field
press_keyPress a keyboard key
select_optionSelect a dropdown option
extract_textExtract text from a page element (requires CSS selector)
screenshotTake a screenshot of the page
waitWait for a duration or condition
run_javascriptExecute JavaScript on the page
list_downloadsList downloaded files
move_downloadMove a downloaded file to persistent storage

Send Task

When the agent stage has workflow transitions to downstream stages, a send_task_* tool is automatically created for each transition:

ToolDescription
send_task_{type}Send a task to the next stage in the workflow
info

The agent must call send_task_* before calling finish to forward data to downstream stages. If it finishes without sending a task, the workflow stops at this stage.