Deep extraction for a specific controller: actions with routes, filters, rate limiting, strong params, rescue handlers.
AI agents call get_controller to retrieve information from Rails Insight without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool inspects and extracts metadata about Rails controllers from the codebase index. It reads structural information about controller actions and their configurations. There is no evidence of code execution, data modification, deletion, or financial operations.
From the tool's definition Tool name is 'get_controller' and description states it performs 'Deep extraction for a specific controller' — retrieves and queries codebase information (actions, routes, filters, rate limiting, strong params, rescue handlers) with no modification or…
Attacks that exploit this kind of access
Deep extraction for a specific controller: actions with routes, filters, rate limiting, strong params, rescue handlers. It is categorised as a Read tool in the Rails Insight MCP Server, which means it retrieves data without modifying state.
Register the Rails Insight MCP server in PolicyLayer and add a rule for get_controller: 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 Rails Insight. Nothing to install.
get_controller 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 get_controller 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 get_controller. 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.
get_controller is provided by the Rails Insight MCP server (@reinteractive/rails-insight). 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 →