Details
With expose_control_tools: true, the same unauthenticated browser-origin path can enumerate process state, read logs, search logs, truncate logs, start processes, stop processes, restart processes, and scale processes. If the operator exposes user-defined MCP process tools, the attacker can invoke those configured commands and read their output.
Process logs and process output often contain service names, local paths, usernames, runtime state, internal URLs, and secrets emitted by child processes. Start, stop, restart, scale, and log truncation are process-control operations on the developer's local process-compose project.
Suggested Fix
Add a target-side trust boundary to the MCP SSE listener before MCP dispatch:
- Reject requests whose
Hostheader is not loopback or an explicit configured trusted name. - Reject browser requests whose
Originis not a trusted loopback or configured origin. - Require a random per-run bearer token or equivalent caller secret on both
/sseand the returned/messageendpoint. - Do not rely on localhost reachability as an authentication boundary for browser-reachable HTTP transports.
- Consider requiring an explicit authentication setting before starting SSE MCP with process-control tools.