AI agents call list_focus_sessions 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 and lists data (focus sessions) with optional filtering parameters. It has no side effects, creates no new data, deletes nothing, and triggers no external operations. It is a straightforward Read operation appropriate for querying the state of task management sessions.
From the tool's definition Tool name 'list_focus_sessions' combined with description 'List local focus sessions with optional task, plan, run, agent, and status filters' indicates a query/retrieval operation that returns information about existing focus sessions without modifying,…
Attacks that exploit this kind of access
List local focus sessions with optional task, plan, run, agent, and status filters. 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 list_focus_sessions: 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.
list_focus_sessions 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 list_focus_sessions 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 list_focus_sessions. 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.
list_focus_sessions 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 →