Skip to main content
An agent lives inside a Box. Start from list_spaces when you need a spaceId, and from list_agents when you need an agentId: every other tool on this page takes one of those two.

​
list_spaces

Lists the Boxes of the workspace with how many agents each one holds. Takes no arguments.
Response

​
list_agents

Lists the agents of the workspace, newest first.
​
string
Restrict the list to one Box.
Each agent carries id, name (the display name), handle (the mention and call key), description, status, space_id and created_at. The id is what every other tool takes as agentId.

​
get_agent

The full picture of one agent in a single call. Read this before changing anything.
​
string
required
Returns the agent identity (handle, name, description), its soul (the system prompt), its model settings (provider, model, temperature, stepLimit), its enabled tools families, its selfImprovement flags, its setup answer with the install instructions behind it, its custom mcpServers, and summaries of its skills, schedules, triggers and connectors. Skills and scheduled tasks are summarised here. Use get_skill and list_schedules for their full text.
get_agent deliberately omits trigger URLs, because a trigger URL carries a secret. Use list_triggers to read them on purpose.

​
create_agent

Creates an agent and places it on the board. It is visible in the app immediately.
​
string
required
Free display name, for example Content Manager.
​
string
The system prompt, in markdown. Who the agent is, what it owns, how it works. This is the single most important field, so write it properly rather than leaving it empty.
​
string
One line on what this agent is for.
​
string
Optional when the workspace has a single Box. With several Boxes, the call fails and lists them so you can pick.
​
string[]
Catalog slugs to declare on the agent. The response gives each one its real status. See Connectors.
​
string
One of rerun, anthropic, claude, codex, openai, google, openrouter.
​
string
​
number
​
number
Maximum number of tool-calling steps in one run.
​
object
Capability families, all on by default, for example {"shell": false, "browser": false}. See Configure an agent for the list.
​
object
Defaults to everything on. {"allowSoulEdit": false, "allowToolInstall": false} pins the agent to the prompt and the tools you gave it.
​
object
The guided setup this agent runs on the account of whoever installs it from a template. required is a boolean and is mandatory inside the object. prompt is required when required is true, and is addressed to the agent, not to the user.
An agent created with defaults may rewrite its own prompt and install its own tools. Pass selfImprovement explicitly when that is not what you want.
Response
active: false means the creation succeeded but the plan has no free agent slot, so the agent will not run until one frees up. An inactiveReason explains it.

​
update_agent

Updates an agent. Every field is optional and only what you pass changes.
​
string
required
​
string
Display name only. It does not change the handle.
​
string
The mention and call key. Changing it breaks every @handle written into another agent prompt.
​
string
Full replacement of the system prompt, in markdown.
​
string
​
string
​
string
​
number
​
number
​
object
Capability families to toggle, for example {"shell": false, "browser": true}.
​
object
​
object
Renaming is safe. name is only what is displayed, and the handle other agents call with @handle stays put. Move the handle only when you mean to. The response lists the fields that were actually written in updated.

​
delete_agent

Permanently deletes an agent with its skills, scheduled tasks, memory and workspace files. Irreversible.
​
string
required
​
boolean
required
Must be true. See Destructive tools.