BrowserFind
Find fresh accessibility element references by semantic role and/or accessible name without returning a full page snapshot. Use this when BrowserObserve is too large or the target is absent from the compact snapshot. Like BrowserObserve, it invalidates all earlier refs in the same tab. The return...
This record as markdown: /tools/dutydeck/browserfind.md
What BrowserFind does on DutyDeck
AI agents call BrowserFind to retrieve information from DutyDeck without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why BrowserFind is rated Low
Even though BrowserFind only reads data, uncontrolled read access leaks sensitive information and racks up API costs: an agent caught in a retry loop can make thousands of calls a minute without anyone noticing.
Attacks that exploit this kind of access
The rule that runs BrowserFind safely
PolicyLayer is an MCP gateway: it sits between your AI agents and DutyDeck, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For BrowserFind, this is the rule to start with:
BrowserFind is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect DutyDeck, apply this rule, and every BrowserFind call is checked against it from then on.
Questions about BrowserFind
Find fresh accessibility element references by semantic role and/or accessible name without returning a full page snapshot. Use this when BrowserObserve is too large or the target is absent from the compact snapshot. Like BrowserObserve, it invalidates all earlier refs in the same tab. The returned refs are valid only for this tab and current page generation. It is categorised as a Read tool in the DutyDeck MCP Server, which means it retrieves data without modifying state.
Register the DutyDeck MCP server in PolicyLayer and add a rule for BrowserFind: 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 DutyDeck. Nothing to install.
BrowserFind is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the BrowserFind 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 BrowserFind. 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.
BrowserFind is provided by the DutyDeck MCP server (taokoplay/DutyDeck). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on DutyDeck, and thousands of servers like it.
This server
Across the catalogue