List App Router routes (pages + route handlers) for the configured project, read from the filesystem — including DYNAMIC routes:
AI agents call route_map to retrieve information from Nextjs Agent without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
route_map queries and enumerates filesystem data about Next.js routes and route handlers. It performs a read-only introspection of the application structure without creating, modifying, deleting, or executing code. The tool simply catalogs available routes (including dynamic ones) for inspection purposes. This is a straightforward data retrieval use case with no side effects.
From the tool's definition Tool description explicitly states 'List App Router routes' and 'read from the filesystem' — these are passive retrieval operations with no mutation.
Attacks that exploit this kind of access
List App Router routes (pages + route handlers) for the configured project, read from the filesystem — including DYNAMIC routes:. It is categorised as a Read tool in the Nextjs Agent MCP Server, which means it retrieves data without modifying state.
Register the Nextjs Agent MCP server in PolicyLayer and add a rule for route_map: 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 Nextjs Agent. Nothing to install.
route_map 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 route_map 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 route_map. 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.
route_map is provided by the Nextjs Agent MCP server (zohaib3249/nextjs-agent-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 →