How to Use the LiveKit MCP in Google ADK

Q: How do I configure the LiveKit MCP Server within Google ADK?

Instantiate McpToolset using StreamableHttpServerParameters pointing to your Vinkius endpoint. Pass this toolset into the tools parameter of your LlmAgent to expose all 41 communication tools via MCP.

Q: How do I restrict the LiveKit tools exposed to Google ADK?

Use the optional toolnames filter when initializing your McpToolset in Python. This limits the agent to specific actions, like only allowing listrooms and getparticipant while blocking destructive tools.

Q: Can I purchase phone numbers automatically through this integration?

You can search for available numbers by country using searchphonenumbers and buy them with purchasephonenumber. The agent can then configure rules using updatephonenumber to route calls.

Q: How does Vinkius protect SIP credentials and phone numbers used by Google ADK?

All SIP trunk configurations, including details from listsipinboundtrunk, are processed in an ephemeral sandbox. Vinkius won't ever log your SIP credentials, private keys, or actual voice data passing through the MCP gateway.

Orchestrate enterprise LiveKit media sessions directly from your Gemini models using the Google ADK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LiveKit MCP to Google ADK

Create your Vinkius account to connect LiveKit 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 LiveKit with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enterprise SIP Trunking and Phone Routing

The `create_sip_inbound_trunk` tool configures how incoming telephone calls connect to your WebRTC rooms. To handle outgoing dials, the agent invokes `create_sip_outbound_trunk` to bridge traditional phone lines with your active digital sessions. Incoming calls are routed dynamically when your agent executes `create_sip_dispatch_rule` to map phone numbers to specific rooms. This lets you build fully automated, voice-driven conference systems on top of Google Cloud.

Live Ingress Provisioning via Google ADK

The `create_ingress` tool establishes RTMP, WHIP, or pull-based entry points for external media streams. Your agent can monitor these entry points using `list_ingress` to verify that active streams are receiving data via the MCP Server. When settings need to change mid-stream, the agent calls `update_ingress` to modify room configurations or participant permissions. This setup allows Gemini to ingest external broadcasts and process them in real time.

Active Session Monitoring and Data Transfer

The `list_participants` tool retrieves a complete list of users currently connected to a specific room. Your agent can target individuals with `get_participant` to inspect their connection state and track details through the MCP. To send control signals or real-time text to active clients, the agent uses `send_data` to broadcast raw packets. This allows your enterprise pipeline to coordinate client-side UI changes without relying on external databases.

Setup guide

Set up LiveKit 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 LiveKit 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="LiveKit_agent",
    model="gemini-2.0-flash",
    instruction="You have access to LiveKit 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 LiveKit. 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 LiveKit 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 LiveKit MCP in Google ADK

Instantiate `McpToolset` using `StreamableHttpServerParameters` pointing to your Vinkius endpoint. Pass this toolset into the `tools` parameter of your `LlmAgent` to expose all 41 communication tools via MCP.

Yes, the long-context Gemini models can process complex routing rules and manage multiple active calls. The agent uses `create_sip_participant` to dial external numbers and join them into active rooms.

Use the optional `tool_names` filter when initializing your `McpToolset` in Python. This limits the agent to specific actions, like only allowing `list_rooms` and `get_participant` while blocking destructive tools.

You can search for available numbers by country using `search_phone_numbers` and buy them with `purchase_phone_number`. The agent can then configure rules using `update_phone_number` to route calls.

All SIP trunk configurations, including details from `list_sip_inbound_trunk`, are processed in an ephemeral sandbox. Vinkius won't ever log your SIP credentials, private keys, or actual voice data passing through the MCP gateway.

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