AI agents call routes_for to retrieve information from Graphdb without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool indexes and queries existing Rails route definitions to help developers understand code structure. It retrieves information about routes without creating, modifying, deleting, or executing anything. The blast radius of misuse is minimal — worst case an AI agent learns about routes it shouldn't, but cannot act on that knowledge without other tools.
From the tool's definition Tool description states it retrieves 'HTTP routes that hit a controller' — a query/lookup operation with no side effects. Consistent with sibling tools like 'find_callers', 'find_definition', and 'find_references', which are all read-only graph traversals.
Attacks that exploit this kind of access
Rails-specific: HTTP routes that hit a controller (or controller#action). It is categorised as a Read tool in the Graphdb MCP Server, which means it retrieves data without modifying state.
Register the Graphdb MCP server in PolicyLayer and add a rule for routes_for: 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 Graphdb. Nothing to install.
routes_for 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 routes_for 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 routes_for. 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.
routes_for is provided by the Graphdb MCP server (samagra001/claude-code-graphdb). 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 →