AI agents use rybbit_update_site_config 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 or modifies data reversibly by updating site configuration settings. While the changes are reversible (settings can be toggled back), the modification of tracking features like IP tracking, session replay, and error tracking could have significant privacy and operational implications if misconfigured by an AI agent.
From the tool's definition Tool name contains 'update' and description states 'Update configuration for an existing Rybbit site.' It modifies site settings reversibly (toggle tracking features).
Attacks that exploit this kind of access
Update configuration for an existing Rybbit site. Toggle tracking features like IP tracking, session replay, error tracking, button clicks, etc. 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_update_site_config: 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_update_site_config 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_update_site_config 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_update_site_config. 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_update_site_config 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 →