Get the text content or HTML of the current page or a specific element.
AI agents call browser_get_content to retrieve information from Mcp Browser without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves data from the browser DOM without modifying state, creating resources, executing arbitrary code, deleting data, or moving money. It is a pure read operation analogous to fetching or querying. Severity is low because the blast radius of misuse is limited to information disclosure from already-navigated pages; the tool cannot independently access unauthorized content.
From the tool's definition Tool description explicitly states 'Get the text content or HTML of the current page or a specific element' — retrieval operation with no modification. Name contains 'get', indicating a read action.
Attacks that exploit this kind of access
Get the text content or HTML of the current page or a specific element. It is categorised as a Read tool in the Mcp Browser MCP Server, which means it retrieves data without modifying state.
Register the Mcp Browser MCP server in PolicyLayer and add a rule for browser_get_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 Mcp Browser. Nothing to install.
browser_get_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 browser_get_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 browser_get_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.
browser_get_content is provided by the Mcp Browser MCP server (mehranakila56-ops/mcp-browser-server). 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 →