High-risk tools in MCP Prompts Server
12 of the 51 tools in MCP Prompts Server 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
-
reset_esp32ExecuteReset the ESP32 device
-
android_launch_appExecuteLaunch an app on Android device
-
debug_session_startExecuteStart a debugging session with GDB/LLDB
-
docker_exec_analysisExecuteExecute analysis tools in Docker containers
-
execute_cross_device_workflowExecuteExecute a workflow that coordinates multiple embedded devices
-
run_testsExecuteExecute tests with automatic framework detection
-
slash_commandExecuteExecute a slash command to quickly apply a prompt template
-
workflow_executeExecuteExecute a multi-tool orchestrated workflow
-
android_play_soundExecutePlay a sound on Android device
-
android_show_toastExecuteShow a toast message on Android device
-
calibrate_esp32_sensorsExecuteCalibrate ESP32 sensors
-
configure_esp32ExecuteSend configuration to ESP32 device
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.