How to Use the Daily.co MCP in Google ADK

Q: How do I initialize Daily.co inside Google ADK?

Install the google-adk package and set up McpToolset. Point the StreamableHttpServerParameters URL to your Vinkius endpoint. Pass that toolset directly to your LlmAgent constructor.

Q: Can my Google ADK agent filter Daily.co operations?

You can use the toolnames argument to restrict access. If an agent only needs to read attendance, expose getroompresence and hide the rest. This prevents accidental infrastructure modifications.

Q: Does this MCP Server expose our raw recording files?

Executing getrecordingaccesslink only returns a time-limited URL. The Vinkius zero-trust architecture acts as a pure passthrough, meaning your video files stream directly to your destination. We never intercept or inspect the actual media payload.

Connect Daily.co WebRTC infrastructure directly to your Google ADK enterprise agents via MCP.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Daily.co MCP to Google ADK

Create your Vinkius account to connect Daily.co 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 Daily.co with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Provision WebRTC via MCP Server

Calling `create_room` and `create_meeting_token` allows your Gemini models to manage live video environments. A customer support agent reads incoming tickets from BigQuery, decides a video call is necessary, and generates a secure link instantly. Managing the lifecycle requires zero manual intervention. Tearing down the infrastructure happens through `delete_room` once the session concludes. You can fetch historical data using `get_logs` and dump it straight into your Google Cloud storage. Your pipeline ingests the raw video metrics without manual downloads.

Manage Large-Scale Meeting Data

Pulling active user counts requires `get_global_presence` and `get_room_presence`. Gemini's massive token window easily ingests the JSON output from hundreds of active participants. Your agent analyzes this real-time attendance data to adjust server loads. Extracting post-call assets relies on `get_recording_access_link` and `get_batch_job`. The agent grabs the S3 download links and triggers Vertex AI pipelines to process the video files. Everything stays within your automated cloud workflow.

Control Live Streaming and Transcripts

Broadcasting to RTMP endpoints starts with `start_live_streaming`. Your agent configures the layout dynamically via `update_live_streaming` based on who is speaking. Pushing the feed to external platforms takes a single tool invocation. Capturing spoken text requires `start_transcription`. The agent monitors the meeting events and stops the process using `stop_transcription` when the discussion ends. All text routes back into your enterprise analytics pipeline for long-term storage.

Setup guide

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

Install the `google-adk` package and set up `McpToolset`. Point the `StreamableHttpServerParameters` URL to your Vinkius endpoint. Pass that toolset directly to your `LlmAgent` constructor.

You can use the `tool_names` argument to restrict access. If an agent only needs to read attendance, expose `get_room_presence` and hide the rest. This prevents accidental infrastructure modifications.

The MCP Server feeds raw JSON directly to the model. Dumping the output of `list_meetings` or `get_logs` into Gemini works flawlessly because the 1M+ token limit absorbs massive arrays without truncation.

HTTP transport fits best for cloud deployments. Stdio works for local testing, but remote execution via HTTP keeps your agent architecture decoupled from the integration logic.

Executing `get_recording_access_link` only returns a time-limited URL. The Vinkius zero-trust architecture acts as a pure passthrough, meaning your video files stream directly to your destination. We never intercept or inspect the actual media payload.

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