How to Use the Kavak MCP in Google ADK

Q: Can Google ADK agents filter the Kavak inventory by location?

Yes. The agent calls listlocations to map the physical hubs, then applies those region codes when querying searchvehicles. It can also check if a specific location supports home deliveries.

Q: How does the Kavak integration handle financing calculations?

The getfinancingoptions tool calculates loan structures. Your Gemini agent can pull these terms and instantly join them with internal credit models you host on Vertex AI.

Q: Can I restrict my Google ADK agent from making Kavak reservations?

Yes. Just use the toolnames filter when configuring your McpToolset. Exclude createreservation and scheduletestdrive so the agent remains read-only.

Q: Is my trade-in data safe when querying this MCP connection?

When you submit exact vehicle VINs and mileage to estimatetradein, the transaction runs through an ephemeral zero-trust container. Once the valuation returns to your Google Cloud environment, the process terminates and drops all input parameters.

Connect Gemini agents to Kavak's used car inventory and pricing data through the Google ADK MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kavak MCP to Google ADK

Create your Vinkius account to connect Kavak 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 Kavak with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Market Pricing via Kavak MCP Server

The `get_market_pricing` tool pulls real-time valuation intelligence for specific car models across the Mexican market. Your Gemini agent ingests this pricing data and compares it against historical trends you already store in BigQuery. You can feed a massive dataset of past trades into Gemini's 1M+ token context window. The agent then runs `estimate_trade_in` against current Kavak metrics, factoring in mileage and condition, to generate highly accurate net-cost estimates for your fleet buyers.

Process Massive Inspection Reports

Agents use `get_vehicle_inspection` to pull the complete 240-point mechanical breakdown for any listed car. They combine this with `get_vehicle_history` to check ownership records and past accidents. Google ADK handles the heavy lifting here. Gemini reads the raw text from both reports, cross-references the mechanical faults with the accident history, and flags discrepancies before your procurement team makes a bid.

Secure Vehicles and Book Drives

Your agent searches the active marketplace using `search_vehicles`, filtering for specific features. When it finds a match, it pulls the exact physical showroom details via `list_locations`. It does not just look at cars. The agent can execute `create_reservation` to lock the inventory, then immediately trigger `schedule_test_drive` for a home delivery. You manage the tool access using the tool_names filter in the ADK, ensuring the agent only books what it is authorized to hold.

Setup guide

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

Install google-adk. Set up an McpToolset using StreamableHttpServerParameters with your Vinkius URL. Pass that toolset directly to your LlmAgent initialization.

Yes. The agent calls list_locations to map the physical hubs, then applies those region codes when querying search_vehicles. It can also check if a specific location supports home deliveries.

The get_financing_options tool calculates loan structures. Your Gemini agent can pull these terms and instantly join them with internal credit models you host on Vertex AI.

Yes. Just use the tool_names filter when configuring your McpToolset. Exclude create_reservation and schedule_test_drive so the agent remains read-only.

When you submit exact vehicle VINs and mileage to estimate_trade_in, the transaction runs through an ephemeral zero-trust container. Once the valuation returns to your Google Cloud environment, the process terminates and drops all input parameters.

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