High-risk tools in Mcp Debugger
7 of the 29 tools in Mcp Debugger are classified as high risk. This page profiles those tools specifically, with recommended policy actions and the attack patterns that target them.
Every operation listed below is an action PolicyLayer recommends controlling at the transport layer. Open any tool to see the full profile, risk score, and YAML policy snippet.
Tools at high risk
-
debugger_startExecute 4/5Start a new debug session with a Node.js process. The process will be paused at the start.
-
debugger_start_cpu_profileExecute 3/5Start CPU profiling for a debug session. Collects CPU profile data for performance analysis.
-
debugger_step_intoExecute 3/5Execute the current line and pause at the first line inside any called function.
-
debugger_step_outExecute 3/5Execute until the current function returns and pause at the calling location.
-
debugger_step_overExecute 3/5Execute the current line and pause at the next line in the same scope.
-
debugger_stop_cpu_profileExecute 3/5Stop CPU profiling and return the profile data with bottleneck analysis.
-
debugger_stop_sessionExecute 3/5Stop a debug session, cleanup all resources, and kill the process if still running.
Attacks that target this class
High-risk tools in any server share these documented attack patterns. Each links to the full case and the defensive policy.
More on Mcp Debugger
Enforce policy on Mcp Debugger
One command generates a policy scaffold for every server in your MCP config.
npx -y @policylayer/intercept init