How to Use the Dext MCP in Pydantic AI

Q: How does Pydantic AI handle Dext API validation errors?

The framework wraps tools like getitemdetails in strict Python type models. If Dext returns unexpected data types, Pydantic AI catches the error at runtime, preventing your agent from processing corrupt invoices.

Q: Can I filter Dext clients using Pydantic AI?

Yes. Your Pydantic AI agent calls listaccountingclients and parses the output into a structured Pydantic model. You can write custom validators to filter out Dext clients that do not meet your active service criteria.

Q: How do I search Dext files securely using Pydantic AI?

The Pydantic AI agent executes searchinboxbykeyword and maps the search results to a strictly validated schema. This guarantees that any receipt data returned to your Pydantic AI agent contains all required financial fields before processing.

Q: What happens if a tax category is misclassified?

The Pydantic AI agent queries listaccountingcategories to get the allowed Dext chart of accounts. If the extracted category is not in the validated list, the agent rejects the item and prompts the user to select a valid category.

Validate every Dext invoice and bank record at runtime using type-safe Pydantic AI agent pipelines.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Dext MCP to Pydantic AI

Create your Vinkius account to connect Dext 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 Dext with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate inbox items using Pydantic AI

This MCP Server provides the `list_inbox_items` tool to pull pending documents directly into your Pydantic AI validation pipeline. The framework enforces strict type checks on every Dext receipt, ensuring fields like tax amounts and dates are formatted correctly. If `get_item_details` returns an unexpected null value or a corrupted string from Dext, the Pydantic AI agent raises a validation error immediately. This loud failure prevents corrupted financial records from ever reaching your accounting ledger.

Audit client metadata with this MCP Server

This MCP Server uses `get_account_metadata` to verify your Dext account status and limits before running heavy validation jobs. The Pydantic AI agent checks these limits at runtime, ensuring your pipeline does not crash mid-run due to API exhaustion. The Pydantic AI agent also calls `list_account_users` to map active Dext users to strict Pydantic schemas. This ensures only authorized user roles are permitted to trigger automated document publishing tasks.

Reconcile bank accounts with type safety

The `list_connected_bank_accounts` tool retrieved through this MCP Server retrieves configured bank feeds directly into your type-safe agent. Pydantic AI validates the bank account numbers and balances against your internal database models before running matching logic. The Pydantic AI agent then calls `list_extracted_suppliers` to match Dext transactions to known vendors. If a supplier name fails to match your pre-defined Pydantic Enum of approved vendors, the transaction is flagged for manual review.

Setup guide

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

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

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

The framework wraps tools like `get_item_details` in strict Python type models. If Dext returns unexpected data types, Pydantic AI catches the error at runtime, preventing your agent from processing corrupt invoices.

Yes. Your Pydantic AI agent calls `list_accounting_clients` and parses the output into a structured Pydantic model. You can write custom validators to filter out Dext clients that do not meet your active service criteria.

The Pydantic AI agent executes `search_inbox_by_keyword` and maps the search results to a strictly validated schema. This guarantees that any receipt data returned to your Pydantic AI agent contains all required financial fields before processing.

The Pydantic AI agent queries `list_accounting_categories` to get the allowed Dext chart of accounts. If the extracted category is not in the validated list, the agent rejects the item and prompts the user to select a valid category.

All client lists, invoices, and bank data are fetched via encrypted HTTPS connections directly to Dext. Vinkius hosts the MCP Server in an ephemeral, zero-trust container, meaning no financial data is ever cached on disk or shared.

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