Run the ElevenLabs MCP server and toolkit in a Meshagent Room in the cloud.

​
Required Environment Variables

  • ELEVENLABS_API_KEY: Your ElevenLabs API key.

​
Steps

  1. Install Meshagent:

    pip install "meshagent[all]"

  2. Sign up and authenticate with Meshagent:

  3. Start MCP Server as a Room Service:

    meshagent service test --room=test --role=agent --image=meshagent/mcp-elevenlabs:latest --env MESHAGENT_PORT=8001 --env ELEVENLABS_API_KEY=<insert-your-api-key-here> --port="num=8001 path=/webhook liveness=/ type=meshagent.callable" --name=mcp-elevenlabs-service

    What this does:

    • Launches the ElevenLabs MCP server in a Meshagent room (test).
    • MCP server will be accessible as a callable service.
    • Note: Rooms close automatically if they go inactive.

  4. Join the Room with a Chatbot Agent:

    meshagent chatbot join --room=test --agent-name=sample --name=sample --toolkit=mcp-elevenlabs
    • Starts a chatbot in the same room, with ElevenLabs toolkit enabled.
    • Multiple toolkits can be added to the same agent.
    • The output will include a room link for you to interact with the agent and ElevenLabs tools.

​
Tools Available

ElevenLabs MCP Server provides the following tools in Meshagent Rooms:

ToolShort Description
add_knowledge_base_to_agentAdd a knowledge base to ElevenLabs workspace.
check_subscriptionCheck the current subscription status.
create_agentCreate a conversational AI agent with custom configuration.
create_voice_from_previewAdd a generated voice to the voice library.
get_agentGet details about a specific conversational AI agent
get_voiceGet details of a specific voice
isolate_audioIsolate audio from a file and save the output audio file to a given directory.
list_agentsList all available conversational AI agents
list_phone_numbersList all phone numbers associated with the ElevenLabs account
make_outbound_callMake an outbound call via Twilio using an ElevenLabs agent.
play_audioPlay an audio file.
search_voice_librarySearch for a voice across the entire ElevenLabs voice library.
search_voicesSearch for existing voices in your ElevenLabs voice library.
speech_to_speechTransform audio from one voice to another using provided audio files.
speech_to_textTranscribe speech from an audio file and save or return the text.
text_to_sound_effectsConvert a text description of a sound effect into an audio file.
text_to_speechConvert text to speech with a given voice and save the output audio.
text_to_voiceCreate voice previews from a text prompt.
voice_cloneClone a voice using provided audio files.

​
Tools Details

​
add_knowledge_base_to_agent

Add a knowledge base to ElevenLabs workspace. Allowed file types: epub, pdf, docx, txt, html.

  • Parameters:
    • agent_id (string, required): ID of the agent to add the knowledge base to.
    • knowledge_base_name (string, required): Name of the knowledge base.
    • input_file_path (string, optional): Path to the file.
    • text (string, optional): Text to add.
    • url (string, optional): URL of the knowledge base.

​
check_subscription

Check the current subscription status.

​
create_agent

Create a conversational AI agent with custom configuration.

  • Parameters:
    • first_message (string, required): Initial message for conversations.
    • name (string, required): Name of the agent.
    • system_prompt (string, required): System prompt for the agent.
    • Other options: asr_quality, language, llm, max_duration_seconds, max_tokens, model_id, optimize_streaming_latency, record_voice, retention_days, similarity_boost, stability, temperature, turn_timeout, voice_id.

​
create_voice_from_preview

Add a generated voice to the voice library.

  • Parameters:
    • generated_voice_id (string, required)
    • voice_description (string, required)
    • voice_name (string, required)

​
get_agent

Retrieve details about a specific conversational AI agent.

  • Parameters:
    • agent_id (string, required)

​
get_voice

Retrieve details of a specific voice.

  • Parameters:
    • voice_id (string, required)

​
isolate_audio

Isolate audio from a file and save it to a directory (default: $HOME/Desktop).

  • Parameters:
    • input_file_path (string, required)
    • output_directory (string, optional)

​
list_agents

List all conversational AI agents.

​
list_phone_numbers

List all phone numbers associated with the ElevenLabs account.

​
make_outbound_call

Make an outbound call using an ElevenLabs agent via Twilio.

  • Parameters:
    • agent_id (string, required): Agent to handle the call
    • agent_phone_number_id (string, required): Phone number to use
    • to_number (string, required): Destination number (E.164 format)

​
play_audio

Play an audio file (WAV or MP3).

  • Parameters:
    • input_file_path (string, required)

​
search_voice_library

Search the entire ElevenLabs voice library.

  • Parameters:
    • page (integer, optional)
    • page_size (integer, optional)
    • search (string, optional)

​
search_voices

Search for voices in your ElevenLabs voice library.

  • Parameters:
    • search (string, optional)
    • sort (string, optional)
    • sort_direction (string, optional)

​
speech_to_speech

Transform audio from one voice to another.

  • Parameters:
    • input_file_path (string, required)
    • output_directory (string, optional)
    • voice_name (string, optional)

​
speech_to_text

Transcribe speech from an audio file and save or return text.

  • Parameters:
    • input_file_path (string, required)
    • diarize (boolean, optional)
    • language_code (string, optional)
    • output_directory (string, optional)
    • return_transcript_to_client_directly (boolean, optional)
    • save_transcript_to_file (boolean, optional)

​
text_to_sound_effects

Convert text to a sound effect and save as audio (duration: 0.5–5 seconds).

  • Parameters:
    • text (string, required)
    • duration_seconds (number, optional)
    • output_directory (string, optional)

​
text_to_speech

Convert text to speech with a selected voice, save as audio.

  • Parameters:
    • text (string, required)
    • output_directory (string, optional)
    • similarity_boost (number, optional)
    • speed (number, optional)
    • stability (number, optional)
    • style (number, optional)
    • use_speaker_boost (boolean, optional)
    • voice_id (string, optional)
    • voice_name (string, optional)

​
text_to_voice

Create voice previews from a text prompt.

  • Parameters:
    • voice_description (string, required)
    • output_directory (string, optional)
    • text (string, optional)

​
voice_clone

Clone a voice using provided audio files.

  • Parameters:
    • files (array, required)
    • name (string, required)
    • description (string, optional)

​
Learn More

See Why is it safer to run MCP Servers with Docker? for best practices on secure deployment.