AI agents invoke stopwatch to trigger actions in Widget MCP. 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.
The tool performs an action that affects the interface state and user experience rather than merely retrieving data. While the impact is benign (a visual timer widget with no side effects on data or systems), execution of interactive operations falls under Execute rather than Read.
From the tool's definition Stopwatch tool starts a stopwatch that 'counts up from zero', triggering an interactive UI component. This constitutes executing an operation (initiating a stopwatch widget) whose effect depends on when the user stops it, making it an Execute category tool…
Documented attack patterns abuse exactly the kind of access stopwatch gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Widget MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for stopwatch:
{
"version": "1",
"default": "deny",
"tools": {
"stopwatch": {
"limits": [
{
"counter": "stopwatch_rate",
"window": "minute",
"max": 10,
"scope": "grant"
}
]
}
}
}stopwatch stays usable, but rate-capped — a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Start a stopwatch that counts up from zero. You don. It is categorised as a Execute tool in the Widget MCP MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Widget MCP server in PolicyLayer and add a rule for stopwatch: 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 Widget MCP. Nothing to install.
stopwatch 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 stopwatch 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 stopwatch. 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.
stopwatch is provided by the Widget MCP server (ref-tools/widget-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 4 Widget MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
4 Widget MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.