Bring Smart Lock
to Pydantic AI
Learn how to connect BoxLock to Pydantic AI and start using 7 AI agent tools in minutes. Fully managed, enterprise secure, and ready to use without writing a single line of code.
What is the BoxLock MCP Server?
Connect your BoxLock Control (v3) account to any AI agent and take full control of your physical security and automated supply chain logistics through natural conversation.
What you can do
- Lock Orchestration — List and manage all BoxLock smart locks in your organization programmatically, retrieving detailed battery levels and high-fidelity connectivity status
- Remote Authorization — Programmatically authorize locks to be opened via physical button press for specific workers or maintenance windows in real-time
- Access Intelligence — Monitor real-time access events and retrieve detailed historical activity logs to maintain high-fidelity audit trails of all openings and scans
- Asset Tracking Architecture — Access complete directories of barcodes and trackable assets to maintain a perfectly coordinated digital ledger of physical goods
- Location Visibility — Retrieve complete directories of physical sites and groups to coordinate your infrastructure security directly through your agent
How it works
1. Subscribe to this server
2. Retrieve your API Key (Bearer Token) from your BoxLock Control dashboard (Settings > Developer API)
3. Start managing your physical access from Claude, Cursor, or any MCP client
No more manual status checking of individual locks or missing delivery attempts. Your AI acts as your dedicated security operations and logistics coordinator.
Who is this for?
- Logistics Managers — instantly authorize delivery access and monitor asset scans using natural language commands
- Facility Operations — track lock battery health and manage worker permissions without leaving your workspace
- Security Teams — automate the auditing of physical access events and monitor tampering alerts through simple AI queries
Built-in capabilities (7)
Get lock details
List lock activity logs
List all active barcodes
List all locations
List all BoxLock smart locks
List all organization users
Pass data as a JSON string. Remotely authorize a lock to be opened
Why Pydantic AI?
Pydantic AI validates every BoxLock tool response against typed schemas, catching data inconsistencies at build time. Connect 7 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 BoxLock integration code
- —
Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors
- —
Dependency injection system cleanly separates your BoxLock connection logic from agent behavior for testable, maintainable code
BoxLock in Pydantic AI
BoxLock and 3,400+ other MCP servers. One platform. One governance layer.
Teams that connect BoxLock 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 BoxLock in Pydantic AI
The BoxLock 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 7 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
BoxLock for Pydantic AI
Every tool call from Pydantic AI to the BoxLock 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 BoxLock API Key?
Log in to your BoxLock Control account, navigate to Settings > Developer API, and generate a new v3 Bearer Token.
Can I open a lock remotely via AI?
Yes! The press_to_open tool allows you to authorize the physical button on a lock to be active for a specific worker and reason programmatically.
How do I check battery levels?
Use the list_locks or get_lock tools to retrieve real-time metadata including current battery percentage and signal strength for every device.
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 BoxLock MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.
MCPServerHTTP not found
Update: pip install --upgrade pydantic-ai