Extract structured data from the page using CSS selectors. Define a schema of selector → field name mappings.
AI agents call crow_browser_scrape 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.
The tool performs data extraction (Read category). CSS selector-based scraping retrieves information from web pages without creating, modifying, deleting, or executing code. The lack of any write, delete, or execution capability and the explicit focus on extraction places this firmly in the Read category. Severity is low because misuse would only expose publicly accessible information already on the page.
From the tool's definition Tool extracts data using CSS selectors without modifying content. Description explicitly states 'Extract structured data from the page', which is a retrieval operation with no side effects.
Documented attack patterns abuse exactly the kind of access crow_browser_scrape 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_scrape:
{
"version": "1",
"default": "deny",
"tools": {
"crow_browser_scrape": {}
}
}crow_browser_scrape 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.
Extract structured data from the page using CSS selectors. Define a schema of selector → field name mappings. 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_scrape: 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_scrape 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_scrape 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_scrape. 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_scrape 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.