// SCAN REPORT

ElevenLabs MCP Server

19 tools. 9 can modify or destroy data without limits.

9 write tools that can modify data. Rate limits recommended.

Last updated: 1 Jul 2026

9 can modify or destroy data

10 read-only

19 tools total

Community server · catalogue entry verified 01/07/2026

How to control ElevenLabs MCP Server ↓

TOOL MAP

What ElevenLabs MCP Server exposes to your agents

Read (10) Write / Execute (9) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous ElevenLabs MCP Server tools

Execute · Medium isolate_audio The tool name 'isolate_audio' suggests audio processing (likely isolating vocals or stems from an audio file), which is an Execute-class operation triggering external audio processing. Execute · High make_outbound_call The tool name strongly implies initiating an outbound phone call, which is an external operation with real-world effects (contacting people, using phone minutes/credits). Execute · Medium play_audio Playing audio is an external operation that triggers system-level audio output, which goes beyond mere data retrieval. Execute · High speech_to_speech Based on the server context (Text to Speech, audio processing, voice cloning) and the tool name 'speech_to_speech', this tool likely transforms input audio into output audio using a different voice — an execution of an a

9 of ElevenLabs MCP Server's 19 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control ElevenLabs MCP Server

PolicyLayer is an MCP gateway — it sits between your AI agents and ElevenLabs MCP Server, and nothing reaches the server without passing your rules. These are the rules we recommend:

Rate limit write operations

{
  "add_knowledge_base_to_agent": {
    "limits": [
      {
        "counter": "add_knowledge_base_to_agent_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "check_subscription": {
    "limits": [
      {
        "counter": "check_subscription_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register ElevenLabs MCP Server — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON ELEVENLABS →

Instant setup, no code required.

FULL CATALOGUE

All 19 ElevenLabs MCP Server tools

EXECUTE 5 tools

Execute isolate_audio isolate_audio Execute make_outbound_call make_outbound_call Execute play_audio Play an audio file. Supports WAV and MP3 formats. Execute speech_to_speech speech_to_speech Execute text_to_sound_effects text_to_sound_effects

WRITE 4 tools

Write add_knowledge_base_to_agent add_knowledge_base_to_agent Write create_agent create_agent Write create_voice_from_preview create_voice_from_preview Write voice_clone voice_clone

READ 10 tools

Read check_subscription Check the current subscription status. Could be used to measure the usage of the API. Read get_agent Get details about a specific conversational AI agent Read get_voice Get details of a specific voice Read list_agents List all available conversational AI agents Read list_phone_numbers List all phone numbers associated with the ElevenLabs account Read search_voice_library search_voice_library Read search_voices search_voices Read speech_to_text speech_to_text Read text_to_speech text_to_speech Read text_to_voice text_to_voice

FAQ

Questions about ElevenLabs MCP Server

How do I prevent bulk modifications through ElevenLabs MCP Server? +

The ElevenLabs MCP Server server has 4 write tools including add_knowledge_base_to_agent, create_agent, create_voice_from_preview. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach ElevenLabs MCP Server.

How many tools does the ElevenLabs MCP Server MCP server expose? +

19 tools across 2 categories: Read, Write. 10 are read-only. 9 can modify, create, or delete data.

How do I enforce a policy on ElevenLabs MCP Server? +

Register the ElevenLabs MCP Server MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every ElevenLabs MCP Server tool call.

Deterministic rules across all 19 ElevenLabs MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON ELEVENLABS →

Instant setup, no code required.

19 ElevenLabs MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.