High-risk tools in ElevenLabs MCP Enhanced
6 of the 29 tools in ElevenLabs MCP Enhanced 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
-
isolate_audioExecuteRemoves background noise from audio. Returns: cleaned audio file path. Use when: extracting voice from noisy recordings.
-
make_outbound_callExecuteInitiates phone call with agent. Returns: call details. Use when: making automated calls via Twilio integration.
-
play_audioExecutePlays audio file locally. Returns: playback confirmation. Use when: previewing generated audio without downloading.
-
speech_to_speechExecuteTransforms voice in audio. Returns: audio file with new voice. Use when: changing speaker voice in existing audio.
-
text_to_dialogueExecuteConverts multi-speaker text to audio. Returns: dialogue audio file paths. Use when: creating conversations with multiple voices.
-
text_to_sound_effectsExecuteGenerates sound effects from text. Returns: audio file path. Use when: creating custom sound effects from descriptions.
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.