This record as markdown: /tools/cowork-bench/browser-select-option.md
What browser_select_option does on Cowork Bench
AI agents invoke browser_select_option to trigger actions in Cowork Bench. 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.
Why browser_select_option is rated High
This tool performs a browser action (selecting a dropdown option), which is an Execute-category operation. It interacts with an external browser environment, and the effects depend on what the dropdown controls — it could submit forms, trigger navigation, or initiate other operations. This makes it Execute rather than Write, as it drives external browser behavior rather than directly modifying stored data.
From the tool's definition 'Select an option in a dropdown' — triggers a browser interaction/action that modifies UI state and may cause downstream operations depending on the dropdown's context
Attacks that exploit this kind of access
The rule that runs browser_select_option safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Cowork Bench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For browser_select_option, this is the rule to start with:
browser_select_option 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Cowork Bench, apply this rule, and every browser_select_option call is checked against it from then on.
Questions about browser_select_option
Select an option in a dropdown. It is categorised as a Execute tool in the Cowork Bench MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Cowork Bench MCP server in PolicyLayer and add a rule for browser_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 Cowork Bench. Nothing to install.
browser_select_option 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 browser_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 browser_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.
browser_select_option is provided by the Cowork Bench MCP server (0717376/cowork_bench). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Cowork Bench, and thousands of servers like it.
Across the catalogue