How to Use the Cabify MCP in Google ADK

Q: How do I restrict a Google ADK agent from calling the Cabify ride request tool?

Use the toolnames filter in your McpToolset configuration. You can omit requestride from the allowed list, ensuring the agent can only read data using getpriceestimate or getridedetails.

Q: How does the Google ADK handle Cabify pricing across different LATAM regions?

The getpriceestimate tool returns prices in local currencies. Because Gemini has a deep understanding of regional contexts, it can easily convert LATAM currencies or Spain's Euros into your primary corporate reporting currency.

Connect Gemini enterprise agents to Cabify via the Google ADK to analyze corporate travel and book rides.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cabify MCP to Google ADK

Create your Vinkius account to connect Cabify 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 Cabify with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

BigQuery travel analysis with Google ADK

Feed your raw corporate travel logs from BigQuery directly into Gemini's massive context window. The Google ADK lets your agent cross-reference historical enterprise spending with live Cabify data using `get_ride_history` to find cost-saving opportunities. By analyzing months of trip records, the agent can identify frequent destinations. It then uses `add_saved_location` to register these offices, making future booking requests faster and reducing manual entry errors across your team.

Long-context route planning using Gemini

Gemini's million-token context allows your agent to process complex, multi-stop itineraries for an entire department. The agent uses `get_time_estimate` and `get_price_estimate` to calculate the most efficient schedules and budgets for dozens of travelers simultaneously. Because the Google ADK handles long-context inputs, you can feed entire flight schedules into your agent. It will automatically match arrival times with `request_ride` coordinates, ensuring drivers are dispatched exactly when employees land.

Restricted MCP toolsets for secure enterprise dispatch

Keep your corporate travel agent secure by limiting its access to sensitive MCP tools. The Google ADK lets you use the `tool_names` filter to expose only `get_ride_details` and `get_saved_locations` to junior-level agents while restricting booking rights. For executive assistants, you can open the full suite of tools, including `request_ride` and `cancel_ride`. This granular control prevents accidental bookings while allowing the agent to manage active trips directly from your Google Cloud environment.

Setup guide

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

Yes. You can pull your enterprise travel logs from BigQuery and pass them to a Gemini agent configured with the `get_ride_history` tool to audit travel expenses and flag discrepancies.

Use the `tool_names` filter in your `McpToolset` configuration. You can omit `request_ride` from the allowed list, ensuring the agent can only read data using `get_price_estimate` or `get_ride_details`.

The `get_price_estimate` tool returns prices in local currencies. Because Gemini has a deep understanding of regional contexts, it can easily convert LATAM currencies or Spain's Euros into your primary corporate reporting currency.

Yes, the Google ADK supports both Stdio and HTTP transports. You can initialize the server using `StreamableHttpServerParameters` to connect your Google Cloud agents to the Cabify MCP Server endpoints.

Every coordinate and location ID processed by the server is handled inside a zero-trust V8 sandbox. This ensures your office locations and employee drop-off coordinates are never cached or exposed to external networks.

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