How to Use the Bexio MCP in Pydantic AI

Q: What is the correct way to connect Bexio to Pydantic AI?

Install the required packages using pip install "pydantic-ai-slimmcp". Use the unified MCPToolset("http://...") constructor to point to your Vinkius URL, and pass it to your Agent's toolsets parameter.

Build type-safe Swiss business workflows in Pydantic AI with strict runtime validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Bexio MCP to Pydantic AI

Create your Vinkius account to connect Bexio 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 Bexio with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fail-safe ERP integrations using Pydantic AI

Silent data corruption is the worst enemy of automated accounting when querying your ERP with `get_invoice` or `list_orders` using this MCP Server. If the API structure changes or returns unexpected nulls, your agent raises an explicit validation error immediately. You will never have to worry about your agent writing corrupted data back to your Swiss accounting ledger.

Model-agnostic business operations with this MCP Server

You are not locked into a single model provider when managing your business data using `list_projects` or `list_users`. The framework acts as a clean abstraction layer. You can swap the underlying LLM in a single line of code while keeping your custom tools and validation schemas completely intact.

Clean tool definition using the unified MCPToolset

Legacy HTTP wrappers are deprecated in favor of a clean, unified interface for accessing `list_contacts` and `list_offers`. Your Python agent gains instant access to these resources via the unified `MCPToolset`. The framework handles the underlying SSE or HTTP transport mechanics behind the scenes so you can focus on writing clean business logic.

Setup guide

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

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

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

Install the required packages using `pip install "pydantic-ai-slim[mcp]"`. Use the unified `MCPToolset("http://...")` constructor to point to your Vinkius URL, and pass it to your Agent's `toolsets` parameter.

If the MCP Server returns data that deviates from the expected schema during a `get_contact` call, the framework throws a runtime validation error. This prevents your agent from processing incomplete or corrupted customer profiles.

Yes, because the framework is model-agnostic. You can run your billing agents against local models or commercial APIs while using the same Vinkius-hosted tools to manage your Swiss business.

No, you do not. Vinkius hosts and manages the server infrastructure, so your Python script only needs to connect to the provided HTTP stream to start executing operations.

Your contacts, invoices, projects, and orders are processed strictly in-memory during execution. Vinkius operates a zero-trust V8 sandbox that isolates your credentials and handles the API token authentication securely without storing your business data.

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