How to Use the Loyverse MCP in Pydantic AI

Q: How do I install the Loyverse MCP toolset for Pydantic AI?

Run pip install "pydantic-ai-slimmcp" in your environment. Initialize the connection using MCPToolset with your Vinkius HTTP URL, then pass it to your agent's toolsets parameter.

Run type-safe retail automation using Pydantic AI to validate Loyverse data 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 Loyverse MCP to Pydantic AI

Create your Vinkius account to connect Loyverse 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 Loyverse with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe customer records in Pydantic AI

Silent data corruption will ruin your CRM. By connecting this MCP Server to Pydantic AI, you ensure that every customer record fetched via `l_list_customers` is validated against strict Python types before your code touches it. If the POS API returns unexpected null fields or broken strings, the framework throws a loud validation error immediately. This keeps your database clean and prevents your agent from making decisions based on bad data.

Validated inventory tracking

Keep your stock levels accurate without guessing. Your agent can call `l_list_items` to fetch live inventory counts, with the framework validating the pagination parameters and response structures at runtime. Since Pydantic AI is model-agnostic, you can use this toolset with any LLM provider. The type-safety guarantees remain identical whether you run your inventory audits through Anthropic, OpenAI, or local models.

Strict transaction logging

Financial reports require absolute precision. Use `l_list_receipts` to retrieve store transactions, knowing that every date filter and receipt amount is parsed and verified by Pydantic models. This setup eliminates the risk of your agent hallucinating transaction values or misinterpreting date ranges. You get clean, structured Python objects that are ready for your accounting pipelines.

Setup guide

Set up Loyverse 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": {
        "loyverse-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Loyverse 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 Loyverse. 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 Loyverse 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 Loyverse MCP in Pydantic AI

Run pip install "pydantic-ai-slim[mcp]" in your environment. Initialize the connection using MCPToolset with your Vinkius HTTP URL, then pass it to your agent's toolsets parameter.

Yes, as long as the server is running externally. Pydantic AI connects to the server via Streamable HTTP or SSE transports using the MCP unified toolset class.

The execution will fail immediately with a validation error. This prevents your agent from processing corrupt data, ensuring your retail pipelines only handle structured, type-safe records.

Yes. The framework is completely model-agnostic, meaning you can run your retail analysis tools using local models or commercial APIs without changing your tool schemas.

All MCP API requests are proxied securely through Vinkius's isolated runtime. No customer names, phone numbers, or transaction receipts are cached, keeping your retail operations fully compliant with privacy standards.

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