How to Use the Kisi MCP in Pydantic AI

Build type-safe access control workflows with Pydantic AI validating every physical lock state at runtime.

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 Control via Pydantic AI

Triggering hardware commands with `unlock_door` opens a specific physical lock. When wrapped in a Pydantic AI agent via this MCP Server, the returned status is validated against strict Python type schemas, ensuring your application never processes malformed hardware responses. Before sending the unlock command, the agent runs `get_lock_details` to verify the lock's hardware health. If the returned payload contains unexpected fields, the Pydantic AI framework raises a validation error immediately, stopping the execution before any physical signal is sent.

Strict Directory Audits and User Validation

The `list_users` tool pulls your entire organization directory into a structured dataset. The MCP integration enforces strict data models on this list, validating that every user ID, email, and status field matches your Pydantic AI schemas. To confirm the caller's active authorization, the agent queries `get_my_profile`. It matches this profile against the roles returned by `list_role_assignments`, guaranteeing that your access control decisions are backed by validated Pydantic AI types.

Validated Location and Access Group Mapping

Gathering logical collections of users and permissions is handled by `list_access_groups`. Your Pydantic AI agent parses this data into strongly-typed Python models, making it impossible for silent database errors to corrupt your permission mapping. Mapping these groups against physical sites begins by calling `list_places` to get all registered locations. It then verifies the physical parameters of each site using `get_place_details`, ensuring that your security boundaries are physically and logically aligned within your typed Pydantic AI codebase.

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-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

You install the slim package with MCP support and initialize the toolset using your Vinkius HTTP URL. The agent automatically registers the 9 tools, wrapping their inputs and outputs in strict runtime type validation.

The framework will raise a validation error instantly, preventing your agent from operating on dirty or corrupted data. This is critical when handling physical security commands like `unlock_door`, where accuracy is paramount.

Yes, you can run the server externally and connect your agent via the unified toolset interface. The agent interacts with the 9 tools over a secure HTTP or SSE transport managed by Vinkius.

The agent can catch API errors during heavy operations like `list_locks`. Because the framework uses standard Python exception handling, you can write clean retry logic to manage Kisi API limits gracefully.

No, the framework processes all data in-memory on your local or cloud runtime. Your user IDs, lock configurations, and physical access histories remain fully within your control, passing securely through the Vinkius gateway without persistent storage.

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