How to Use the ElevenLabs MCP in Google ADK

Q: How do I connect ElevenLabs to Google ADK?

Use McpToolset with StreamableHttpServerParameters pointing to your Vinkius endpoint. Pass this toolset into the LlmAgent constructor so Gemini can call voice endpoints.

Q: Can Google ADK filter which ElevenLabs tools are exposed?

Yes, you can pass an optional toolnames list to restrict access to sensitive tools. This ensures your agent cannot accidentally trigger deletevoice during runtime.

Q: Does ElevenLabs support long-context synthesis in Google ADK?

The texttospeech tool processes text payloads generated by Gemini's long-context reasoning. You can feed large text blocks extracted from documents into the tool to produce long-form audio.

Q: How do I monitor ElevenLabs API usage with Google ADK?

Your agent runs getsubscriptioninfo to check character balances and billing periods. This data can be logged to Vertex AI monitoring dashboards for cost tracking.

Q: How does the ElevenLabs MCP Server handle voice clone data privacy?

Custom voice clones and settings retrieved via getvoicesettings are accessed over a secure, encrypted tunnel. Vinkius isolates the MCP server process inside a zero-trust sandbox, preventing any exposure of your voice models.

Deploy Gemini agents using Google ADK with the ElevenLabs MCP server to generate voice assets directly from your data pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ElevenLabs MCP to Google ADK

Create your Vinkius account to connect ElevenLabs to Google ADK and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup ElevenLabs with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise voice synthesis with Google ADK

The `text_to_speech` tool allows your Gemini agent to convert structured data from BigQuery into high-fidelity voice announcements. Your pipeline fetches target customer text from Google Cloud and feeds it directly into the audio generator. This integration enables real-time synthesis of localized phone scripts without manual recording sessions. Because Gemini supports a 1M+ token context window, the agent analyzes entire customer histories before deciding which voice profile to run.

Dynamic ElevenLabs MCP Server voice management

The `list_voices` tool provides your Google ADK agent with the full library of active voice clones stored in your account. It's easy for the agent to query `get_voice_settings` on this MCP server to verify stability and clarity metrics before selecting the voice. You can filter which tools are exposed to Vertex AI by configuring the toolset parameters during initialization. This prevents the model from invoking administrative endpoints like `delete_voice` unless explicitly authorized.

Audio log synchronization and archival

The `list_audio_history` tool pulls your generation history to sync audio metadata with your internal databases. Your agent calls `get_download_link` to secure the raw MP3 file and archive it in a Google Cloud Storage bucket. Once the file is safely stored, the agent executes `delete_history_item` to keep your ElevenLabs cloud storage clean. This automated feedback loop maintains a tidy account status while preserving your generated assets locally.

Setup guide

Set up ElevenLabs MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with ElevenLabs tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="ElevenLabs_agent",
    model="gemini-2.0-flash",
    instruction="You have access to ElevenLabs tools via MCP.",
    tools=mcp_tools,
)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by ElevenLabs. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect ElevenLabs now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about ElevenLabs MCP in Google ADK

Use `McpToolset` with `StreamableHttpServerParameters` pointing to your Vinkius endpoint. Pass this toolset into the `LlmAgent` constructor so Gemini can call voice endpoints.

Yes, you can pass an optional `tool_names` list to restrict access to sensitive tools. This ensures your agent cannot accidentally trigger `delete_voice` during runtime.

The `text_to_speech` tool processes text payloads generated by Gemini's long-context reasoning. You can feed large text blocks extracted from documents into the tool to produce long-form audio.

Your agent runs `get_subscription_info` to check character balances and billing periods. This data can be logged to Vertex AI monitoring dashboards for cost tracking.

Custom voice clones and settings retrieved via `get_voice_settings` are accessed over a secure, encrypted tunnel. Vinkius isolates the MCP server process inside a zero-trust sandbox, preventing any exposure of your voice models.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript