Start a new pomodoro session
AI agents invoke start_pomodoro to trigger actions in TodoPomo MCP Server. 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 execution of a pomodoro session workflow rather than merely reading data (like list_tasks) or persisting data changes (like add_task or update_task). It starts an active process with real-world timing consequences.
From the tool's definition Tool 'start_pomodoro' initiates a timed work session, which is an operational trigger that begins external state change (starting a timer/session) whose effects depend on runtime arguments and system state.
Attacks that exploit this kind of access
Start a new pomodoro session. It is categorised as a Execute tool in the TodoPomo MCP Server MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the TodoPomo MCP Server MCP server in PolicyLayer and add a rule for start_pomodoro: 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 TodoPomo MCP Server. Nothing to install.
start_pomodoro 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_pomodoro 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_pomodoro. 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_pomodoro is provided by the TodoPomo MCP Server MCP server (pratyayrajak/todopomo-mcp). 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 →