Bring Access Control
to Pydantic AI
Learn how to connect Kisi to Pydantic AI and start using 10 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the Kisi MCP Server?
Connect your Kisi account to any AI agent and take full control of your facility's physical security and high-fidelity access orchestration through natural conversation.
What you can do
- Lock Portfolio Orchestration — List all cloud-connected locks, retrieve detailed high-fidelity status metadata, and monitor door health programmatically
- Remote Unlock Operations — Programmatically trigger high-fidelity remote unlocks for specific doors directly through your agent for perfectly coordinated visitor access
- Facility Lockdown Architecture — Access high-fidelity emergency lockdown protocols for individual doors or entire places to ensure immediate site security
- Place & Site Discovery — Access your complete directory of high-fidelity physical locations and places to understand and orchestrate your facility infrastructure
- User & Member Monitoring — List organization users and access complete high-fidelity profile metadata to maintain perfect security alignment
- Operational Monitoring — Verify account-level API connectivity and monitor access orchestration volume directly through your agent for perfectly coordinated security scaling
How it works
1. Subscribe to this server
2. Retrieve your API Key from your Kisi dashboard (Settings > API Keys)
3. Start managing your facility security from Claude, Cursor, or any MCP client
No more manual checking of individual door logs or physical keycards. Your AI acts as your dedicated security coordinator and facility architect.
Who is this for?
- Security Managers — instantly retrieve lock statuses and monitor site health using natural language commands without leaving your creative workspace
- Facility Managers — trigger high-fidelity remote unlocks and monitor door activity to ensure healthy and secure operations
- IT Admins — verify technical API logs and user assignments to optimize access control through simple AI queries
Built-in capabilities (10)
Check API Status
Get lock details
Get place details
Get user details
List access groups
List cloud locks
List physical places
List organization users
Lockdown a door
Unlock a door
Why Pydantic AI?
Pydantic AI validates every Kisi tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.
- —
Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application
- —
Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Kisi integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your Kisi connection logic from agent behavior for testable, maintainable code
Kisi in Pydantic AI
Kisi and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect Kisi to Pydantic AI through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 3,400+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Kisi in Pydantic AI
The Kisi MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 10 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in Pydantic AI only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Kisi for Pydantic AI
Every tool call from Pydantic AI to the Kisi MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
How do I find my Kisi API Key?
Log in to your account, navigate to Settings > API Keys, and generate a new high-fidelity API Secret.
Can I unlock a door via AI?
Yes! The unlock_kisi_lock tool allows your agent to trigger a high-fidelity remote unlock for any cloud-connected door in your organization.
How do I list my organization's places?
Use the list_kisi_places tool to retrieve the complete high-fidelity directory of physical locations along with their unique identifiers for precise orchestration.
How does Pydantic AI discover MCP tools?
Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.
Does Pydantic AI validate MCP tool responses?
Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.
Can I switch LLM providers without changing MCP code?
Absolutely. Pydantic AI abstracts the model layer. your Kisi MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai