Extract text (or metadata) from a PDF by URL or local path, using pdfjs-dist. Good for gov reports, papers, invoices.
AI agents call crow_browser_extract_pdf 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 a pure retrieval operation on document content. While PDFs may contain sensitive information (invoices, gov reports), the tool itself only reads and does not modify, execute commands, or trigger external operations. The blast radius of misuse is limited to information disclosure of data already accessible via URL or local path, hence low severity.
From the tool's definition Tool extracts text or metadata from PDFs—no modification, deletion, or execution occurs. Description explicitly states 'Extract text (or metadata)' without any side effects.
Documented attack patterns abuse exactly the kind of access crow_browser_extract_pdf 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_pdf:
{
"version": "1",
"default": "deny",
"tools": {
"crow_browser_extract_pdf": {}
}
}crow_browser_extract_pdf 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 text (or metadata) from a PDF by URL or local path, using pdfjs-dist. Good for gov reports, papers, invoices. 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_pdf: 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_pdf 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_pdf 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_pdf. 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_pdf 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.