How to Use the Daftra MCP in Pydantic AI

Q: How do I register the Daftra MCP Server in Pydantic AI?

Install the framework using pip install "pydantic-ai-slimmcp". Use the unified MCPToolset class initialized with your Vinkius HTTP endpoint, and pass it to your Agent via the toolsets argument to register these MCP tools automatically.

Q: Does Pydantic AI support the older MCPServerHTTP transport for Daftra?

No, MCPServerHTTP is deprecated in the latest versions of the framework. You should use the unified MCPToolset class with your Vinkius HTTP endpoint to handle all communications with your MCP server.

Validate every Daftra invoice and client profile at runtime using type-safe schemas in Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Daftra MCP to Pydantic AI

Create your Vinkius account to connect Daftra 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 Daftra with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe ERP operations with Pydantic AI

Stop worrying about malformed API payloads breaking your production database. When your agent calls `create_client` to register a new account, Pydantic AI validates the inputs against strict schemas at runtime. If the agent tries to pass an invalid email or a malformed phone number, the framework blocks the call before it ever reaches your ERP. The same strict validation applies to reads. When fetching details with `get_client_details`, the framework ensures the returned outstanding balance matches your expected float types. You get clean, predictable data structures instead of raw, unpredictable JSON.

Hardened financial auditing via MCP Server

Auditing your finances requires absolute precision. Your agent uses `list_invoices` to gather transactions and `get_invoice_details` to verify tax lines. Pydantic AI validates every single invoice object, ensuring your agent never processes corrupt data or hallucinated fields. If the API returns unexpected data formats, the framework fails loudly with a validation error. This prevents your agent from making decisions based on incomplete or corrupted billing records, keeping your ledger perfectly clean.

Secure cost tracking and inventory management

Keep your inventory and expenses aligned without manual data entry. Your agent pulls current stock lists via `list_inventory_products` and matches them against business outlays retrieved with `list_expenses`. The framework checks these data structures against your defined Pydantic models to guarantee type safety. By using `get_site_metadata` to fetch organizational settings, your agent adapts to different tax zones and currencies. The framework validates these configurations, making sure your cost-tracking logic remains accurate across different business entities.

Setup guide

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

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

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

Install the framework using `pip install "pydantic-ai-slim[mcp]"`. Use the unified `MCPToolset` class initialized with your Vinkius HTTP endpoint, and pass it to your `Agent` via the `toolsets` argument to register these MCP tools automatically.

The framework will raise a validation error instantly instead of passing bad data to the model. If a tool like `get_invoice_details` returns a string where a float was expected, the run halts immediately to prevent your agent from executing logic on corrupt financial data.

No, `MCPServerHTTP` is deprecated in the latest versions of the framework. You should use the unified `MCPToolset` class with your Vinkius HTTP endpoint to handle all communications with your MCP server.

Pydantic AI is completely model-agnostic. You can connect your validated server to OpenAI, Anthropic, Gemini, or even a local Ollama instance, and the runtime type validation will work exactly the same way across all of them.

Your client names, invoice records, and API keys are protected by an ephemeral V8 sandbox. Vinkius executes the connector in a zero-trust environment that processes requests on the fly and never writes your ERP data to persistent storage.

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