How to Use the Alegra MCP in Pydantic AI

Build type-safe business agents with Pydantic AI and the Alegra MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Alegra MCP to Pydantic AI

Create your Vinkius account to connect Alegra 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 Alegra with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate business data with Pydantic AI

Every response from `list_contacts` or `get_invoice_details` gets checked against your Pydantic models. You catch bad data before it hits your database. If the server returns a malformed response, the agent stops immediately. This prevents the silent failures common in loosely typed systems.

Type-safe inventory tracking in Pydantic AI

Your agent calls `list_inventory_items` and ensures the output matches your expected schema. You define the types, and the framework enforces them. This makes your code predictable. You never have to guess if a field is missing or the wrong format.

Manage invoices using Pydantic AI schemas

When you call `create_invoice`, you pass validated data directly from your Pydantic structures. The agent handles the communication layer. This approach gives you total control over the structure of your financial records. It removes ambiguity from every transaction.

Setup guide

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

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

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

You define your Pydantic classes to match the tool output. The framework validates the server response against these classes at runtime.

Yes, if the server returns unexpected data, the framework throws a validation error. You can catch this and handle it gracefully.

The server is model-agnostic. You can swap your underlying model, and the type-safe toolsets will keep working the same way.

You define the connection via the toolset, and the framework manages the session. It supports both SSE and HTTP transports.

We use ephemeral memory for all tool responses. Your payment details are validated by your models and never persisted on the server side.

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

Mastra AI sdk-typescript

Start using the Alegra MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Get started