Extract clean article text from the current page using Mozilla Readability. Strips ads, nav, and boilerplate. Set format=
AI agents call crow_browser_extract_text 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 reads and retrieves text content from a web page using Mozilla Readability for parsing. It performs no modifications, deletions, or external operations—only extraction and presentation of existing data. The extracted content is read-only with no side effects on the page or external systems. This is a classic Read operation.
From the tool's definition Tool description states it 'Extract[s] clean article text from the current page' and 'Strips ads, nav, and boilerplate.' The verb 'extract' and action of retrieving text content without modification indicates data retrieval.
Documented attack patterns abuse exactly the kind of access crow_browser_extract_text 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_extract_text:
{
"version": "1",
"default": "deny",
"tools": {
"crow_browser_extract_text": {}
}
}crow_browser_extract_text 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 clean article text from the current page using Mozilla Readability. Strips ads, nav, and boilerplate. Set format=. 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_extract_text: 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_extract_text 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_extract_text 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_extract_text. 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_extract_text 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.