AI agents call pages_snapshot to retrieve information from Voog without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The pages_snapshot tool creates a backup by reading and serializing page data to JSON format. This is fundamentally a Read operation—it retrieves and exports data without any side effects, modifications, or destructive actions. The low severity reflects that exporting data poses minimal risk to the system itself, though the sensitivity of exported content depends on access controls.
From the tool's definition Tool performs 'Backup all pages + per-page contents to JSON files', which is a retrieval and export operation with no modification, deletion, or execution of code.
Attacks that exploit this kind of access
Backup all pages + per-page contents to JSON files in. It is categorised as a Read tool in the Voog MCP Server, which means it retrieves data without modifying state.
Register the Voog MCP server in PolicyLayer and add a rule for pages_snapshot: 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 Voog. Nothing to install.
pages_snapshot 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 pages_snapshot 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 pages_snapshot. 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.
pages_snapshot is provided by the Voog MCP server (runnel/voog-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 →