// MCP TOOL REFERENCE

ELEVENLABS TOOLS

10 tools from the ElevenLabs MCP Server, categorised by risk level.

READ TOOLS

get_models List available text-to-speech models 2/5 get_voices Retrieve available voices 2/5 transcribe_audio Transcribe audio to text 2/5

WRITE TOOLS

add_voice_to_library Add a custom voice to the library 3/5 convert_audio Apply voice conversion effects to audio 3/5 create_voice Clone a voice from audio samples 4/5 design_voice Generate a new voice from text description 3/5 generate_sound_effect Generate sound effects from text 3/5 isolate_audio Isolate speech from background noise 2/5 text_to_speech Convert text into natural-sounding speech 3/5

// FAQ

How many tools does the ElevenLabs MCP server have? +

The ElevenLabs MCP server exposes 10 tools across 2 categories: Read, Write.

How do I enforce policies on ElevenLabs tools? +

Use Intercept, the open-source MCP proxy. Write YAML rules for each tool — rate limits, argument validation, or deny rules — then run Intercept in front of the ElevenLabs server.

What risk categories do ElevenLabs tools fall into? +

ElevenLabs tools are categorised as Read (3), Write (7). Each category has a recommended default policy.

Enforce policies on ElevenLabs

Open source. One binary. Zero dependencies.

npx -y @policylayer/intercept

github.com/policylayer/intercept →