List all HTTP middlewares in Traefik
AI agents call list_middlewares to retrieve information from Traefik 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 information about Traefik middlewares without modifying, executing, or deleting any configurations. However, middleware details could reveal security-sensitive information (authentication rules, rate limiting policies, headers manipulation), justifying medium severity for a read operation. The confidence is high because the description unambiguously describes a listing/query action.
From the tool's definition Tool name 'list_middlewares' and description 'List all HTTP middlewares in Traefik' indicate a query/retrieval operation with no modification or execution of configurations.
Attacks that exploit this kind of access
List all HTTP middlewares in Traefik. It is categorised as a Read tool in the Traefik MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Traefik MCP Server MCP server in PolicyLayer and add a rule for list_middlewares: 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 Traefik MCP Server. Nothing to install.
list_middlewares 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_middlewares 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_middlewares. 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_middlewares is provided by the Traefik MCP Server MCP server (theupriser/treafik-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 →