How to Use the Kisi MCP in Google ADK

Q: How do I connect the Kisi MCP Server to the Google ADK?

Run pip install google-adk in your environment. Create an McpToolset with StreamableHttpServerParameters pointing to your Vinkius URL. Pass it into your LlmAgent configuration.

Q: Can Google ADK restrict which Kisi tools the agent sees?

Absolutely. Use the toolnames filter when setting up the toolset. You might expose listkisiplaces for a reporting agent while completely hiding unlockkisilock to prevent accidental door operations.

Link the Kisi MCP Server to the Google ADK to process physical access logs through Gemini and correlate door events with BigQuery.

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

Audit Massive Access Histories

The `list_kisi_users` and `list_kisi_groups` tools pull your entire physical security directory straight into the Gemini context window. You feed thousands of user records directly to the model without hitting token limits. Enterprise security teams need to spot anomalies across massive datasets. Your agent cross-references this access data against HR records stored in BigQuery. It finds the contractors who still have active building access months after their project ended.

Automated Hardware Diagnostics

Running `check_kisi_status` alongside `list_kisi_locks` lets your agent map the real-time health of every physical door in your portfolio. The agent queries Vertex AI to predict maintenance needs based on historical failure rates. Broken locks compromise buildings. You schedule an agent to sweep the hardware status every hour. If a door stops responding, the system creates a high-priority maintenance ticket before employees arrive for the morning shift.

Google ADK MCP Server Access

Emergency response systems use `lockdown_kisi_lock` and `unlock_kisi_lock` to control physical perimeters dynamically. You bind these tools to the `LlmAgent` via the `McpToolset` class to enable Google ADK MCP Server Access. Context matters during an incident. The agent evaluates sensor data from Google Cloud, verifies the specific building using `get_kisi_place`, and triggers the lockdown. You restrict exposed tools using the `tool_names` filter so the model only has the permissions it absolutely needs.

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

Run `pip install google-adk` in your environment. Create an `McpToolset` with `StreamableHttpServerParameters` pointing to your Vinkius URL. Pass it into your LlmAgent configuration.

Absolutely. Use the `tool_names` filter when setting up the toolset. You might expose `list_kisi_places` for a reporting agent while completely hiding `unlock_kisi_lock` to prevent accidental door operations.

The framework handles pagination natively by iterating through `list_kisi_users` responses. Gemini's massive context window absorbs the full dataset, so you avoid building complex chunking logic.

Yes. The framework supports both Stdio and HTTP transports. For cloud-managed setups, the HTTP transport connects directly to the managed endpoint without local binary dependencies.

The MCP Server transmits specific lock IDs, user emails, and building coordinates. Google Cloud isolates this execution environment. Vinkius handles the authentication via zero-trust ephemeral tokens, keeping your physical security credentials off local machines.

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