Low Risk

crow_browser_extract_tables

Extract HTML tables from the current page as structured JSON data.

How to control crow_browser_extract_tables ↓

What crow_browser_extract_tables does on Crow

AI agents call crow_browser_extract_tables 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.

Low Risk

Why crow_browser_extract_tables needs a policy

This tool retrieves structured data from a webpage without creating, modifying, or deleting any content. It performs a query-like operation on the DOM of the current browser page. The blast radius is minimal—misuse would only expose whatever data happens to be visible on the page, with no side effects or ability to alter state. Low severity reflects the read-only nature and limited scope of potential harm.

From the tool's definition Tool name and description indicate it 'extract[s]' and 'retrieve[s]' HTML tables as JSON data from a webpage. The verb 'extract' and the passive nature of reading page content without modification confirm Read category.

Documented attack patterns abuse exactly the kind of access crow_browser_extract_tables gives an agent:

How to control crow_browser_extract_tables

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_tables:

policy.json
{
  "version": "1",
  "default": "deny",
  "tools": {
    "crow_browser_extract_tables": {}
  }
}

crow_browser_extract_tables is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.

  1. Create a free account and register Crow — nothing to install.
  2. Add this policy — paste it, or build it visually.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
CAP THIS TOOL →

Free to start. No card required.

Related tools and policies

Go deeper

Questions about crow_browser_extract_tables

What does the crow_browser_extract_tables tool do? +

Extract HTML tables from the current page as structured JSON data. It is categorised as a Read tool in the Crow MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on crow_browser_extract_tables? +

Register the Crow MCP server in PolicyLayer and add a rule for crow_browser_extract_tables: 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.

What risk level is crow_browser_extract_tables? +

crow_browser_extract_tables is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit crow_browser_extract_tables? +

Yes. Add a rate_limit block to the crow_browser_extract_tables 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.

How do I block crow_browser_extract_tables completely? +

Set action: deny in the PolicyLayer policy for crow_browser_extract_tables. 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.

What MCP server provides crow_browser_extract_tables? +

crow_browser_extract_tables 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.

Enforce policy on every Crow tool call.

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.

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.