AI agents call vitour_inspect_page to retrieve information from Mcp without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves browser state information (screenshot, styles, console/network logs) without side effects. It is a read-only inspection operation. The session closure is cleanup, not a destructive action. Severity is low because misuse (e.g., screenshotting sensitive UI) has limited blast radius compared to write/execute/destructive operations.
From the tool's definition Tool performs inspection and screenshot capture with 'optional target styles, console/network diagnostics' followed by session closure. No modification, deletion, execution of code, or financial operations described.
Attacks that exploit this kind of access
Inspect a Vitour page in the browser: screenshot, optional target styles, console/network diagnostics; session is closed after capture. It is categorised as a Read tool in the Mcp MCP Server, which means it retrieves data without modifying state.
Register the MCP server in PolicyLayer and add a rule for vitour_inspect_page: 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. Nothing to install.
vitour_inspect_page 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 vitour_inspect_page 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 vitour_inspect_page. 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.
vitour_inspect_page is provided by the MCP server (victormyschik/mcp). 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 →