AI agents call list_routes to retrieve information from Django MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or queries route information from a Django project without modifying, executing, or deleting anything. It falls clearly into the Read category as a listing/retrieval operation. The low severity reflects that route information is non-sensitive project metadata that an AI agent could safely query.
From the tool's definition Tool named 'list_routes' on a Django MCP Server described as providing 'read-only resources' and enabling exploration of 'Django project structure'. The name indicates listing/querying routes (URL patterns), which is a read operation with no side effects.
Documented attack patterns abuse exactly the kind of access list_routes gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Django MCP Server, and nothing reaches the server without passing your rules. This is the rule we recommend for list_routes:
{
"version": "1",
"default": "deny",
"tools": {
"list_routes": {}
}
}list_routes is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
list_routes. It is categorised as a Read tool in the Django MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Django MCP Server MCP server in PolicyLayer and add a rule for list_routes: 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 Django MCP Server. Nothing to install.
list_routes 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 list_routes 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 list_routes. 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.
list_routes is provided by the Django MCP Server MCP server (joshuadavidthomas/mcp-django). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Django MCP Server, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
13 Django MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.