AI agents call rybbit_list_sites 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.
This tool retrieves and enumerates existing sites and organizations without creating, modifying, or deleting data. It is a straightforward query operation with no capability to alter state. Severity is low because listing accessible resources, while potentially revealing scope, does not enable direct unauthorized access or data modification.
From the tool's definition Tool name 'rybbit_list_sites' and description 'List all sites and organizations the authenticated user has access to' indicate data retrieval with no side effects. The verb 'list' is explicitly a read operation.
Attacks that exploit this kind of access
List all sites and organizations the authenticated user has access to. 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_list_sites: 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_list_sites 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_list_sites 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_list_sites. 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_list_sites 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 →