How to Use the Cal.com MCP in Google ADK

Q: Can Google ADK read my entire Cal.com booking history?

Yes, if you grant the right permissions. The listbookings tool fetches your schedule audit log. Gemini's massive context window can ingest all of this data to analyze meeting trends.

Q: How do I restrict Cal.com actions in Google ADK?

Pass a toolnames list to your toolset configuration. If you only want read-only access, include getbooking and getschedules while excluding write actions. This prevents the agent from modifying calendar events.

Give your Gemini agents on Google ADK direct control over the Cal.com MCP Server for enterprise event management.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cal.com MCP to Google ADK

Create your Vinkius account to connect Cal.com 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 Cal.com with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Connect Cal.com to your Google ADK pipelines

Enterprise agents running on Google Cloud need to book meetings based on real business data. Wrapping your Vinkius URL in a McpToolset gives your LlmAgent immediate access to `create_booking` and `cancel_booking`. You can trigger appointments directly from BigQuery events. Gemini models handle massive context windows effortlessly. Passing the results of `list_bookings` into the prompt lets the AI reason over thousands of past appointments at once. The agent finds patterns and suggests meeting times based on historical data.

Manage event types using this MCP Server

Creating meeting templates manually wastes time when your agent can build them dynamically. Your bot executes `create_event_type` to spin up new meeting formats based on customer interactions. Calling `get_event_type` verifies the configuration applied correctly. Discovery happens automatically when you expose these tools. The framework lets you apply an optional tool_names filter if you only want the bot to read data via `list_event_types`. Restricting actions keeps your Vertex AI deployments focused on specific tasks.

Read team schedules and availability

Multi-tenant scheduling requires accurate availability checks against your active calendar. Invoking `get_schedules` pulls the exact time blocks tied to specific event formats. Cross-referencing this data with internal Google Workspace calendars prevents conflicts. Knowing who is authenticated stops routing errors. The `get_current_user` tool grabs the profile, timezone, and default schedule of the active account. Adding `list_memberships` to the mix ensures your Gemini agent knows exactly which department handles the request.

Setup guide

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

Install google-adk and create a StreamableHttpServerParameters object with your endpoint. Wrap that in an McpToolset and pass it to your LlmAgent. Both Stdio and HTTP transports are supported.

Yes, if you grant the right permissions. The `list_bookings` tool fetches your schedule audit log. Gemini's massive context window can ingest all of this data to analyze meeting trends.

Pass a tool_names list to your toolset configuration. If you only want read-only access, include `get_booking` and `get_schedules` while excluding write actions. This prevents the agent from modifying calendar events.

You build the bridge in your agent logic. The LLM queries BigQuery for customer tiers and then executes `create_event_type` to generate a custom meeting link. The protocol handles the external execution.

Timezones, meeting templates, and participant emails remain strictly isolated. Every request routes through a managed, ephemeral sandbox that destroys itself after execution. We handle the auth tokens so your Google Cloud environment never stores raw credentials.

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