AI agents call rybbit_get_config 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 configuration and version information without altering state, triggering side effects, or executing code. It poses minimal risk even if an AI agent calls it repeatedly or with unexpected arguments, as it only surfaces existing system metadata.
From the tool's definition Tool name 'rybbit_get_config' and description 'Get Rybbit server version and configuration' indicate pure retrieval of configuration metadata. No modification, deletion, or execution of external operations occurs.
Attacks that exploit this kind of access
Get Rybbit server version and configuration. 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_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_get_config 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_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_get_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_get_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 →