AI agents use rybbit_create_site to create or update resources in Rybbit — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Rybbit environment.
This tool creates a new site configuration in the analytics platform, which is a reversible write operation. It does not delete data (would be Destructive), execute arbitrary code (would be Execute), move money (would be Financial), or merely read data (would be Read). The incomplete description slightly reduces confidence, but the 'create' action clearly maps to Write category.
From the tool's definition Tool name 'rybbit_create_site' and description 'Create a new site in Rybbit' indicate this creates new data. The description appears incomplete ('Use type' cuts off), suggesting the full capability involves creating a reversible configuration object.
Attacks that exploit this kind of access
Create a new site in Rybbit. Use type. It is categorised as a Write tool in the Rybbit MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Rybbit MCP server in PolicyLayer and add a rule for rybbit_create_site: 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_create_site is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the rybbit_create_site 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_create_site. 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_create_site 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 →