Select an option in a dropdown/select element by its @ref
AI agents use select_option to create or update resources in Webclaw — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Webclaw environment.
Selecting a dropdown option is a reversible form modification action. It creates or modifies the current form state without permanently destroying data or executing arbitrary code. While it affects UI/form state, the change is reversible (another selection can change it back).
From the tool's definition Tool selects an option in a dropdown/select element, which modifies form state and user interface selections. The description explicitly indicates it performs a selection action that changes the state of an HTML form element.
Documented attack patterns abuse exactly the kind of access select_option gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Webclaw, and nothing reaches the server without passing your rules. This is the rule we recommend for select_option:
{
"version": "1",
"default": "deny",
"tools": {
"select_option": {
"limits": [
{
"counter": "select_option_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}select_option stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Select an option in a dropdown/select element by its @ref. It is categorised as a Write tool in the Webclaw MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Webclaw MCP server in PolicyLayer and add a rule for select_option: 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 Webclaw. Nothing to install.
select_option is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the select_option 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 select_option. 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.
select_option is provided by the Webclaw MCP server (kuroko1t/webclaw). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Webclaw, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
21 Webclaw tools catalogued and risk-classified — across an index of 43,000+ MCP servers.