AI agents call browser_read_markdown to retrieve information from Byob without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and converts web page content to markdown format. It performs a read-only operation: opening a URL or using an existing tab to extract and format article body content. There is no modification, deletion, execution of code, or financial impact. The only potential concern is information disclosure from pages the user can access, but this is inherent to the read category.
From the tool's definition Tool name contains 'read' and description states 'Open a URL or use an existing tab and convert the main article body to markdown' - this is a retrieval and transformation operation with no side effects on the target resource.
Attacks that exploit this kind of access
Open a URL or use an existing tab and convert the main article body to markdown using. It is categorised as a Read tool in the Byob MCP Server, which means it retrieves data without modifying state.
Register the Byob MCP server in PolicyLayer and add a rule for browser_read_markdown: 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 Byob. Nothing to install.
browser_read_markdown 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 browser_read_markdown 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 browser_read_markdown. 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.
browser_read_markdown is provided by the Byob MCP server (wxtsky/byob). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.