AI agents invoke start_focus_session to trigger actions in Todos. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call — builds kicked off, notifications sent, workflows started.
This tool triggers the initiation of a focus session—an operation with side effects that changes system state and agent behavior. While not destructive or financial, it executes a command to begin a new work context. The effects depend on arguments (which task/plan is focused), making it an Execute rather than Write classification.
From the tool's definition Tool description states 'Start a local focus session' which initiates a new operational context/state for task management.
Attacks that exploit this kind of access
Start a local focus session for a task, plan, run, or general agent work. It is categorised as a Execute tool in the Todos MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Todos MCP server in PolicyLayer and add a rule for start_focus_session: 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.
start_focus_session is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the start_focus_session 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 start_focus_session. 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.
start_focus_session 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 →