How do I get a Dext API Key?

Log in to your Dext account, navigate to **Settings > API**, and you can retrieve your unique API Key from that section. Ensure your plan includes API access.

Can the agent see receipt images?

The agent can retrieve the URL for the item image, allowing you to click and view the original document directly from the chat interface.

Does the integration support multiple currencies?

Yes, Dext automatically extracts the currency from your documents, and the agent will display the total amounts with their respective currency codes.

Dext MCP Server for Pydantic AI 10 tools — connect in under 2 minutes

Name: Dext
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 10 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Dext through the Vinkius and every tool is automatically validated against Pydantic schemas — catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token — get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Dext "
            "(10 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Dext?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Dext MCP Server

Integrate Dext (formerly Receipt Bank), the leading bookkeeping and accounting automation platform, directly into your AI workflow. Manage your digital inbox of receipts and invoices, track supplier extraction data, and monitor accounting categories and client accounts using natural language.

Pydantic AI validates every Dext tool response against typed schemas, catching data inconsistencies at build time. Connect 10 tools through the Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code — full type safety, structured output guarantees, and dependency injection for testable agents.

What you can do

Inbox Oversight — List and retrieve detailed information for all items in your Dext inbox, including processing status.
Data Extraction — Access granular technical metadata for extracted receipts, including tax details and supplier info.
Client Management — List and review accounting clients and their integration settings in your partner account.
Account Intelligence — Monitor connected bank accounts and accounting categories available for classification.

The Dext MCP Server exposes 10 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Dext to Pydantic AI via MCP

Follow these steps to integrate the Dext MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 10 tools from Dext with type-safe schemas

Why Use Pydantic AI with the Dext MCP Server

Pydantic AI provides unique advantages when paired with Dext through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture — switch between OpenAI, Anthropic, or Gemini without changing your Dext integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Dext connection logic from agent behavior for testable, maintainable code

Dext + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Dext MCP Server delivers measurable value.

Type-safe data pipelines: query Dext with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Dext tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Dext and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Dext responses and write comprehensive agent tests

Dext MCP Tools for Pydantic AI (10)

These 10 tools become available when you connect Dext to Pydantic AI via MCP:

get_account_metadata

Retrieve metadata and usage limits for your Dext account

get_item_details

Get detailed information for a specific inbox item

list_account_users

List all users with access to the current Dext account

list_accounting_categories

List the chart of accounts or categories available for classification

list_accounting_clients

List all clients associated with your Dext partner account

list_connected_bank_accounts

List all bank accounts configured for statement extraction

list_extracted_suppliers

List all suppliers automatically extracted from your documents

list_inbox_items

List all pending and processed items (receipts, invoices) in your Dext inbox

list_items_pending_review

Identify inbox items that are currently in the "Review" status

search_inbox_by_keyword

Search for receipts or invoices by supplier name or description

Example Prompts for Dext in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Dext immediately.

"List all items in my inbox that need review."

"Show me the details for the item from 'Starbucks' on June 12th."

"Search my inbox for 'office supplies'."

Troubleshooting Dext MCP Server with Pydantic AI

Common issues when connecting Dext to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Dext + Pydantic AI FAQ

Common questions about integrating Dext MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer — your Dext MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.