Dump all interactive elements on the page (inputs, buttons, links, selects) with their attributes.
AI agents call crow_browser_discover_selectors to retrieve information from Crow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool queries and returns data about page structure without modifying, executing, or destroying anything. It is a reconnaissance/discovery function that retrieves DOM element information for analysis. The severity is low because discovering selectors poses minimal risk on its own—the risk materializes only if an agent uses this data to subsequently interact with those elements. Classification: Read.
From the tool's definition Tool description explicitly states it 'Dump[s] all interactive elements on the page (inputs, buttons, links, selects) with their attributes' - a pure information retrieval action with no side effects.
Documented attack patterns abuse exactly the kind of access crow_browser_discover_selectors gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Crow, and nothing reaches the server without passing your rules. This is the rule we recommend for crow_browser_discover_selectors:
{
"version": "1",
"default": "deny",
"tools": {
"crow_browser_discover_selectors": {}
}
}crow_browser_discover_selectors is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Dump all interactive elements on the page (inputs, buttons, links, selects) with their attributes. It is categorised as a Read tool in the Crow MCP Server, which means it retrieves data without modifying state.
Register the Crow MCP server in PolicyLayer and add a rule for crow_browser_discover_selectors: 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 Crow. Nothing to install.
crow_browser_discover_selectors 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 crow_browser_discover_selectors 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 crow_browser_discover_selectors. 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.
crow_browser_discover_selectors is provided by the Crow MCP server (kh0pper/crow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Crow, 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.
576 Crow tools catalogued and risk-classified — across an index of 43,000+ MCP servers.