How to Use the join.me MCP in Google ADK

Q: How does Google ADK authenticate with the join.me server?

You pass your Vinkius endpoint token to the StreamableHttpServerParameters when initializing your toolset. Gemini then gains secure access to tools like schedulemeeting and getuserinfo without exposing raw credentials to the model.

Q: Can I use Google ADK to clean up canceled join.me sessions?

Yes, your agent can run deletemeeting to purge canceled events from your dashboard. This helps keep your join.me schedule synchronized with your Google Calendar or internal databases.

Q: How does Google ADK handle large join.me meeting lists?

The MCP Server returns structured JSON from listmeetings that Gemini's long-context window easily processes. The Google ADK ensures these large payloads are streamed efficiently without hitting token limits.

Q: Can I start a pre-scheduled call automatically?

Yes, the agent can invoke startscheduledmeeting using the ID of any upcoming session. This opens the browser-based meeting room instantly for the host.

Q: How secure is my join.me profile data within Google ADK?

All profile details retrieved by getuserinfo are processed in memory and never stored on Vinkius servers. The connection uses encrypted HTTPS transports, ensuring your meeting metadata remains strictly within your Google Cloud boundary.

Trigger join.me browser meetings from Gemini using Google ADK to connect calendar data with enterprise analytics.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect join.me MCP to Google ADK

Create your Vinkius account to connect join.me 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 join.me with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Long-context schedule analysis via Google ADK

Feed months of join.me meeting logs into Gemini's massive context window by running `list_meetings` through your agent. The Google ADK lets your agent ingest thousands of past sessions to find patterns in client availability. This helps your team optimize call times based on real historical data rather than guesswork. The agent can drill down into specific join.me sessions using `get_meeting` to pull precise connection details. This data can be piped directly into BigQuery via Google ADK, letting you analyze your team's communication patterns alongside your core business metrics.

Deploy enterprise meetings with this MCP Server

Spin up instant collaborations by letting Gemini invoke `start_adhoc_meeting` directly from your cloud console. The Google ADK handles the HTTP transport to this MCP Server, allowing your enterprise agents to launch join.me video calls without any local downloads. It connects your team instantly when urgent cloud alerts require live huddles. You can restrict which join.me tools are exposed to Gemini using the Google ADK toolset filters. For instance, you can allow `start_scheduled_meeting` while blocking destructive actions to keep your communication environment secure.

Sync webhooks with Vertex AI workflows

Automate real-time event routing by configuring join.me webhooks directly through your Google ADK agent. By calling `create_webhook`, your agent sets up immediate notifications for meeting events, routing them directly to your Cloud Functions. The agent manages these connections using `list_webhooks` to ensure your Google Cloud event-driven pipelines remain clean. This removes the need for manual webhook configuration in the join.me developer portal.

Setup guide

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

You pass your Vinkius endpoint token to the `StreamableHttpServerParameters` when initializing your toolset. Gemini then gains secure access to tools like `schedule_meeting` and `get_user_info` without exposing raw credentials to the model.

Yes, your agent can run `delete_meeting` to purge canceled events from your dashboard. This helps keep your join.me schedule synchronized with your Google Calendar or internal databases.

The MCP Server returns structured JSON from `list_meetings` that Gemini's long-context window easily processes. The Google ADK ensures these large payloads are streamed efficiently without hitting token limits.

Yes, the agent can invoke `start_scheduled_meeting` using the ID of any upcoming session. This opens the browser-based meeting room instantly for the host.

All profile details retrieved by `get_user_info` are processed in memory and never stored on Vinkius servers. The connection uses encrypted HTTPS transports, ensuring your meeting metadata remains strictly within your Google Cloud boundary.

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