How to Use the Kisi MCP in Google ADK

Q: Can the agent handle thousands of locks across multiple offices?

Yes, the agent uses listlocks to retrieve the entire hardware directory in structured payloads. Gemini's large context window allows the agent to analyze thousands of lock states simultaneously without running out of memory.

Run enterprise facility management and physical security audits from Google ADK using real-time building data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Kisi MCP to Google ADK

Create your Vinkius account to connect Kisi 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 Kisi with Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

BigQuery Auditing with Google ADK and Kisi

Retrieving permissions with `list_role_assignments` pulls the active authorization of every user in your physical organization. By combining this MCP Server with the Google ADK, your Gemini agent can export live authorization tables directly into BigQuery for instant compliance mapping. The agent then calls `list_access_groups` to match these roles against your physical security groups. This lets your Google ADK pipeline identify permission drift by comparing Vertex AI data with actual physical lock permissions.

Multi-Site Facility Mapping via Google ADK

The `list_places` tool fetches all physical locations registered to your enterprise account. When your Gemini-powered agent runs this tool inside the Google ADK, it processes the geographic layout of your offices, allowing you to run cross-site analysis. Drilling down further, the agent calls `get_place_details` for each site to extract specific configuration parameters. It maps these details against the hardware locks returned by `list_locks` to build a complete inventory of your physical security assets inside your Google Cloud console.

Direct Hardware Control and Lock Monitoring

Sending an immediate signal via `unlock_door` opens a designated physical lock. Using this within the MCP context allows you to build automated entry workflows that run alongside your Google ADK pipelines. To ensure safety, the Gemini agent runs `get_lock_details` immediately after the command to verify the physical state of the bolt. This dual-action loop confirms whether the door is open, closed, or experiencing a hardware malfunction before reporting back to your Google ADK console.

Setup guide

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

You initialize the toolset class using your Vinkius HTTP endpoint URL and pass it to your Gemini agent. The framework exposes all 9 tools, giving your enterprise agent the ability to query physical security infrastructure.

Yes, you can pass a specific list of allowed tool names to your toolset constructor. This prevents the agent from accessing the `unlock_door` tool while keeping `list_locks` active for auditing.

Vinkius handles the underlying authentication handshake, so your Gemini agent only needs a single endpoint token. This keeps your master API keys out of your Google Cloud environment variables.

Yes, the agent uses `list_locks` to retrieve the entire hardware directory in structured payloads. Gemini's large context window allows the agent to analyze thousands of lock states simultaneously without running out of memory.

Your physical access logs, user profiles, and lock configurations flow directly between the Kisi API and your Google Cloud virtual environment. Vinkius operates as a zero-trust gateway, meaning no physical security data is cached or stored outside your designated cloud project.

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