AI agents call get_idle_focus_prompts to retrieve information from Todos without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves idle prompts associated with active focus sessions. The 'get' operation and 'return' language confirm this is a read-only operation that queries state without creating, modifying, deleting, or executing anything. The data retrieved is already present in the system (local idle prompts). Blast radius is minimal—misuse would only expose prompt text that likely belongs to the requesting session.
From the tool's definition Tool name 'get_idle_focus_prompts' uses the verb 'get', and description states 'Return local idle prompts' which indicates retrieval/query of existing data with no modification or side effects.
Attacks that exploit this kind of access
Return local idle prompts for active focus sessions. It is categorised as a Read tool in the Todos MCP Server, which means it retrieves data without modifying state.
Register the Todos MCP server in PolicyLayer and add a rule for get_idle_focus_prompts: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Todos. Nothing to install.
get_idle_focus_prompts is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the get_idle_focus_prompts rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for get_idle_focus_prompts. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
get_idle_focus_prompts is provided by the Todos MCP server (@hasna/todos). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →