How to Use the DealMachine MCP in Google ADK

Q: How do I restrict exposed tools in my DealMachine Google ADK setup?

Use the toolnames filter when initializing your toolset. This prevents the agent from accidentally calling write operations if you only want it doing read-only analysis.

Feed DealMachine property records directly into your Google ADK agents for enterprise analysis.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect DealMachine MCP to Google ADK

Create your Vinkius account to connect DealMachine 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 DealMachine with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Process massive property lists with Gemini

Enterprise real estate teams deal with thousands of records at once. Google ADK lets you dump massive datasets into Gemini's massive token context window. Your agent pulls your entire pipeline using `list_real_estate_leads` and cross-references it against market trends. From there, the model can identify patterns in your target neighborhoods. It uses `get_property_details` to pull specific mortgage and equity data for the most promising addresses. You stop guessing and start letting the model find the hidden signals.

Sync DealMachine with your BigQuery data

You probably already have historical market data sitting in Google Cloud. Connecting this MCP Server bridges the gap between your proprietary database and your active prospecting CRM. The agent grabs your current inventory via `list_tracked_properties`. Once the agent has the active list, it queries BigQuery to compare your tracked addresses against historical tax records. If it finds a mismatch, it triggers `search_leads_by_address` to update the CRM. Your data stays perfectly synced without writing custom ETL pipelines.

Track marketing spend across Google Cloud

Direct mail campaigns generate a ton of operational metadata. Your Gemini agent can extract send dates and engagement metrics by calling `list_marketing_campaigns`. It parses the results and formats them for your Vertex AI dashboards. Keeping an eye on your account limits is just as critical. The agent runs `get_account_details` to check your credit balance before suggesting a new massive mailer. You build workflows that respect your actual budget constraints.

Setup guide

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

Install google-adk and set up a McpToolset using the StreamableHttpServerParameters class. Pass the Vinkius endpoint URL. Hand that toolset to your LlmAgent and it starts working immediately.

Yes, thanks to Gemini's massive context window. The agent can pull hundreds of leads via the MCP integration and analyze them simultaneously. You get macro-level insights that standard single-prompt models miss.

Use the tool_names filter when initializing your toolset. This prevents the agent from accidentally calling write operations if you only want it doing read-only analysis.

It works out of the box. The ADK integrates natively with Google Cloud infrastructure. Your agent can pull property data from the MCP Server and pipe it directly into your custom Vertex models.

Your API tokens live in a secure, zero-trust environment. Whenever your agent requests sensitive deed histories or equity estimates, the request executes in a temporary, isolated sandbox. The execution context is destroyed immediately after the response.

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