AI agents call done as a supporting operation in Fast Playwright MCP workflows.
This tool appears to be a lifecycle/signaling tool that marks a task as done. It doesn't read, write, execute, delete, or move money. It's a control-flow signal with no described data operations, placing it in 'Other'. Confidence is moderate since the description is minimal and uninformative about any underlying effects.
From the tool's definition 'Call this tool when the task is complete.' — signals task completion with no described side effects.
Documented attack patterns abuse exactly the kind of access done gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Fast Playwright MCP, and nothing reaches the server without passing your rules. This is the rule we recommend for done:
{
"version": "1",
"default": "deny",
"tools": {
"done": {
"limits": [
{
"counter": "done_rate",
"window": "minute",
"max": 60,
"scope": "grant"
}
]
}
}
}done gets a rate cap, and everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Call this tool when the task is complete. It is categorised as a Other tool in the Fast Playwright MCP MCP Server, which means it performs auxiliary operations.
Register the Fast Playwright MCP server in PolicyLayer and add a rule for done: 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 Fast Playwright MCP. Nothing to install.
done is a Other tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the done 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 done. 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.
done is provided by the Fast Playwright MCP server (tontoko/fast-playwright-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 34 Fast Playwright MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
34 Fast Playwright MCP tools catalogued and risk-classified — across an index of 42,500+ MCP servers.