AI agents call site_get 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.
This tool retrieves site configuration and metadata without any capability to modify, delete, or execute operations. The 'Read-only' designation and the nature of the returned fields (title, code, data, languages) confirm this is a pure data retrieval operation with no side effects. Blast radius is minimal—an agent querying site metadata poses negligible risk.
From the tool's definition Tool description explicitly states 'Read-only' and lists parameters like 'title, code, data, languages' that are site metadata retrieval operations.
Attacks that exploit this kind of access
Get the site singleton (title, code, data, languages, ...). Read-only. 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 site_get: 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.
site_get 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 site_get 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 site_get. 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.
site_get 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 →