Limits and security

​

Rate limits

Over the limit, the tool’s reply says so and asks you to wait: about a minute for the burst limit, or until the rolling 24 hours pass for the daily one. Nothing arrives as an HTTP error. Limits are per user, not per organisation, so one agent cannot exhaust an agency’s whole team. There is also a guard on guessing: after 20 failed workspace or site lookups in an hour, the reply asks you to wait an hour and fetch valid ids from list_workspaces and list_sites.

​

Read-only, always

Every tool reads. Nothing an agent does can change a site, edit prompts, start a run, create a card, generate a draft or spend anything on your account. Kevin’s writing capabilities in the app are deliberately withheld from MCP.

​

Your permissions, nothing more

Every call runs as the signed-in user. Workspaces you do not belong to and sites you are not assigned to do not exist as far as the tools are concerned. Membership is refreshed within about 30 seconds.

​

Untrusted content

Answers, competitor pages and citation snippets are written by third parties. Koalr labels them as data to report on, so an instruction hidden in a competitor’s page is not followed by your agent. This applies to every tool that returns excerpts, including get_prompt_detail and get_citations.

​

Disconnecting

Remove the server from your client and the agent stops immediately. Sign-ins expire within 24 hours; if you need a connection cut off sooner, email support and say which client you used. Membership is refreshed within about 30 seconds, so removing someone from a workspace stops their agent within about 30 seconds.

​

Reporting a problem

Email support@koalr.ai with the client, the tool and the time. Include the request identifier from the error if there is one.