How to Use the kvCORE MCP in Google ADK

Q: Can Google ADK restrict which kvCORE tools run?

Yes. You use the toolnames filter when setting up the toolset. This lets you expose searchkvcoreleads while blocking write access entirely.

Give your Google ADK agents direct access to kvCORE leads and active property listings.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect kvCORE MCP to Google ADK

Create your Vinkius account to connect kvCORE 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 kvCORE with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Feed kvCORE leads into Gemini

The `get_lead_details` tool pulls specific contact histories into Gemini's massive context window. You initialize `McpToolset` with your Vinkius URL and pass it to the `LlmAgent`. Your agent can now read thousands of interaction logs and summarize a buyer's true intent. It pairs perfectly with `list_lead_activity`. The agent ingests every viewed property, clicked email, and text message. You get a behavioral profile of the buyer without clicking through tabs in a CRM dashboard.

Track marketing campaigns in Google Cloud

The `list_marketing_campaigns` tool extracts your active outbound strategies. Your Google ADK agent pulls this data and maps it against external datasets you hold in BigQuery. You see exactly which campaigns drive actual pipeline movement. When a campaign generates a response, the agent uses `update_lead_info` to tag the contact. It runs entirely on Google Cloud infrastructure. You automate the tedious tagging work that humans forget to do.

Query properties with this MCP Server

The `list_property_listings` tool exposes your current inventory to the agent. If a user asks about homes in a specific zip code, the agent fetches the active list. It handles the API request in the background. It digs deeper using `get_listing_details`. The agent retrieves exact metadata for a single address. You can pipe this data straight into Vertex AI for pricing analysis or automated listing descriptions.

Setup guide

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

Install the google-adk package. Set up StreamableHttpServerParameters with your Vinkius endpoint and pass the resulting McpToolset to your LlmAgent.

Yes. You use the tool_names filter when setting up the toolset. This lets you expose search_kvcore_leads while blocking write access entirely.

The MCP Server pulls the data, and your agent writes it. You can extract data via list_agent_tasks and pipe it directly into your GCP data warehouse.

Gemini's 1M+ token context window swallows massive payloads. It reads the entire output of list_lead_activity in a single pass without losing details.

The server handles campaign names and lead IDs within an ephemeral zero-trust environment. Vinkius manages the authentication layer so your Google Cloud architecture never stores raw CRM passwords. The isolated sandbox prevents cross-tenant data leaks.

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