How to Use the Kisi MCP in Pydantic AI

Q: How do I initialize the Kisi MCP Server in Pydantic AI?

Install pydantic-ai-slimmcp. Initialize MCPToolset with your HTTP endpoint URL. Pass this toolset directly to your Agent instance. Note that the old MCPServerHTTP class is deprecated.

Integrate the Kisi MCP Server with Pydantic AI to enforce strict type validation on every physical door operation and user access audit.

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 Pydantic AI

Create your Vinkius account to connect Kisi to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-Safe Door Operations

The `unlock_kisi_lock` and `lockdown_kisi_lock` tools execute hardware commands that demand absolute precision. Your agent validates every parameter against strict Pydantic models before the network request ever leaves your infrastructure. Silent failures in physical security are unacceptable. If the model hallucinates a lock ID or passes a string instead of an integer, the framework fails loudly. You catch the validation error immediately rather than waiting for a confused employee at a locked door.

Strict User Directory Syncs

Auditing access requires the `list_kisi_users` and `get_kisi_user` tools to pull exact credential assignments. The agent receives this data and validates the schema structure at runtime. APIs change and unexpected null values break downstream logic. Pydantic AI intercepts the raw response and ensures it matches your expected models. You get a clean, validated dictionary of user permissions ready for compliance reporting.

Pydantic AI MCP Server Mapping

Infrastructure monitoring relies on `check_kisi_status` and `list_kisi_places` to verify building connectivity. You mount these capabilities using the unified `MCPToolset` class to finalize your Pydantic AI MCP Server Mapping. Model-agnostic design means you swap LLMs without rewriting your security logic. You test the hardware queries locally with a fast open-source model, then deploy to production with Anthropic or OpenAI. The validation rules remain identical across the board.

Setup guide

Set up Kisi MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "kisi-alternative-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to Kisi tools.",
)

result = await agent.run("List recent Kisi transactions")
print(result.output)

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 Pydantic AI

Install `pydantic-ai-slim[mcp]`. Initialize `MCPToolset` with your HTTP endpoint URL. Pass this toolset directly to your Agent instance. Note that the old `MCPServerHTTP` class is deprecated.

The framework throws a severe validation error immediately. If `get_kisi_lock` returns a missing status field, the agent halts execution. You never process malformed data silently.

Yes. Every tool execution runs async by default. This prevents your main thread from blocking while waiting for `list_kisi_locks` to return data from the cloud API.

It does. You can point the agent at any compatible local model while keeping the exact same tool definitions. This lets you test your access control logic without burning API credits.

The MCP Server touches highly sensitive access group IDs, lock states, and employee credentials. The connection routes through a V8 Isolate Sandbox with strict zero-trust enforcement. No persistent state remains after the execution context closes.

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