How to Use the Kisi MCP in AutoGen

Q: How do I register Kisi tools with an AutoGen AssistantAgent?

Use the mcpservertools utility to fetch the tools from the server. Pass that schema-converted list directly to the agent's constructor so it knows how to query the hardware.

Let your AutoGen agents debate and coordinate physical security decisions using live Kisi hardware data via this 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 Kisi MCP to AutoGen

Create your Vinkius account to connect Kisi to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Multi-Agent Consensus via MCP Server

The `list_users` and `list_access_groups` tools give your AutoGen agents the raw data needed to deliberate on permission changes. A security agent checks the proposed change against compliance rules while an admin agent looks at operational needs. They debate the risk using live data from this MCP Server before making a change. This ensures no single agent can modify access groups without a verified consensus. It keeps things tight.

Coordinated Door Opening Protocols

The `unlock_door` and `get_lock_details` tools are executed only after your AutoGen agents agree that a physical request is safe. One agent verifies the user's profile while another checks if the target lock is in an alarmed state. Once both agents clear the request, the primary agent calls the tool to open the physical door. This multi-agent verification eliminates accidental triggers or rogue actions on your physical doors.

Automated Facility Audits with AutoGen

The `list_places` and `list_role_assignments` tools allow your agent team to run scheduled audits of your physical offices. The auditor agent compiles the current assignments, and the writer agent drafts a report on security anomalies. This setup removes human error from physical security monitoring. The agents work in parallel, passing tool outputs back and forth until they compile a clean, verified list of access discrepancies.

Setup guide

Set up Kisi MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Kisi tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Kisi_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Kisi data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Kisi_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Kisi data")
    print(result.messages[-1].content)

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 AutoGen

You set up a group chat where a gatekeeper agent must approve the transaction. The tool is only invoked once the gatekeeper validates the user's profile against your security policies.

Yes, the extension supports both stdio and Streamable HTTP transports. You pass the server parameters directly into the tool adapter to expose the locks to your agents.

The executing agent catches the error and reports it to the group chat. The coordinator agent can then decide to retry or alert a human administrator.

Use the mcp_server_tools utility to fetch the tools from the server. Pass that schema-converted list directly to the agent's constructor so it knows how to query the hardware.

The server handles user profiles and role assignments strictly in a secure, ephemeral V8 isolate. No physical location data or access logs are stored permanently, keeping your office security configuration private.

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