Extract HTML/text content from pages
AI agents call chrome_get_web_content to retrieve information from Chrome MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool only reads and retrieves data from web pages. It does not modify, delete, or execute code. While it can access potentially sensitive information on a page, the blast radius of misuse is limited to information disclosure (what the page already renders), not system compromise or data destruction. Low severity is appropriate for a read-only information extraction tool.
From the tool's definition Tool extracts content from pages without modifying state. Description explicitly states 'Extract HTML/text content from pages' — a retrieval operation with no side effects.
Attacks that exploit this kind of access
Extract HTML/text content from pages. It is categorised as a Read tool in the Chrome MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Chrome MCP Server MCP server in PolicyLayer and add a rule for chrome_get_web_content: 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 Chrome MCP Server. Nothing to install.
chrome_get_web_content 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 chrome_get_web_content 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 chrome_get_web_content. 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.
chrome_get_web_content is provided by the Chrome MCP Server MCP server (standbyme626/mcp-chrome). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →