AI agents call rybbit_get_site_id to retrieve information from Rybbit without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves site identifiers from a domain name lookup. It reads data without creating, modifying, deleting, or executing any operations. The severity is low because the information returned (a numeric siteId) appears to be non-sensitive configuration data needed for authorized API access, not sensitive user or financial data.
From the tool's definition Tool performs a lookup operation: 'Look up a site by domain name. Returns the numeric siteId used for analytics API queries.' This is a query/retrieval action with no side effects.
Attacks that exploit this kind of access
Look up a site by domain name. Returns the numeric siteId used for analytics API queries. Note: for SDK tracking setup, use the hash siteId returned by rybbit_create_site instead. It is categorised as a Read tool in the Rybbit MCP Server, which means it retrieves data without modifying state.
Register the Rybbit MCP server in PolicyLayer and add a rule for rybbit_get_site_id: 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 Rybbit. Nothing to install.
rybbit_get_site_id 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 rybbit_get_site_id 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 rybbit_get_site_id. 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.
rybbit_get_site_id is provided by the Rybbit MCP server (nks-hub/rybbit-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 →