How to Use the Dext MCP in OpenAI Agents SDK

Q: How does the OpenAI Agents SDK handle Dext rate limits?

The OpenAI Agents SDK manages execution limits by checking getaccountmetadata before initiating batch Dext runs. If your Dext account is near its monthly extraction limit, the agent pauses further document processing to prevent API rejection.

Q: Can I use OpenAI Agents SDK to search specific Dext receipts?

Yes. Your OpenAI Agents SDK agent calls searchinboxbykeyword to scan the Dext inbox for specific keywords or supplier names. This allows the OpenAI Agents SDK to isolate and extract target Dext invoices instantly during an audit.

Q: What happens if an invoice category is missing in Dext?

The OpenAI Agents SDK agent calls listaccountingcategories to fetch the current Dext chart of accounts. If the category does not match, the agent flags the item for manual review instead of guessing the classification.

Feed raw financial documents to your OpenAI Agents SDK pipelines and let agents audit receipts using direct Dext tools.

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 OpenAI Agents SDK

Create your Vinkius account to connect Dext to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Audit pending invoices with OpenAI Agents SDK

This MCP Server provides the `list_items_pending_review` tool to expose unapproved receipts directly to your OpenAI Agents SDK pipeline. Your OpenAI Agents SDK agent pulls these items, reads the raw data, and flags discrepancies before they hit your Dext ledger. You configure your OpenAI Agents SDK agent to check supplier details via `get_item_details` to verify Dext tax rates. This setup stops bad data from slipping into your Dext accounting files without requiring manual checks for every single receipt in your OpenAI Agents SDK pipeline.

Map client accounts via this MCP Server

This MCP Server exposes `list_accounting_clients` so your OpenAI Agents SDK routing system knows exactly which client ledger to target in Dext. The OpenAI Agents SDK agent reads the client list and routes incoming documents to the correct Dext account folder automatically. The OpenAI Agents SDK agent checks `list_account_users` to find the assigned bookkeeper for that specific Dext client. If an invoice looks suspicious, the agent triggers an internal handoff to notify the right human team member.

Match bank statements to extracted suppliers

The `list_connected_bank_accounts` tool retrieved through this MCP Server provides your OpenAI Agents SDK agent with active bank feeds to reconcile against incoming Dext invoices. The OpenAI Agents SDK agent compares extraction metadata against actual bank transactions to flag missing paperwork. By calling `list_extracted_suppliers`, the OpenAI Agents SDK agent verifies if the supplier name exists in your historical Dext database. If the supplier is new, the agent queries `list_accounting_categories` to assign the correct tax code based on previous transaction patterns.

Setup guide

Set up Dext MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Dext tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Dext tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Dext tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Dext Agent",
            instructions="You have access to Dext tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

The OpenAI Agents SDK manages execution limits by checking `get_account_metadata` before initiating batch Dext runs. If your Dext account is near its monthly extraction limit, the agent pauses further document processing to prevent API rejection.

Yes. Your OpenAI Agents SDK agent calls `search_inbox_by_keyword` to scan the Dext inbox for specific keywords or supplier names. This allows the OpenAI Agents SDK to isolate and extract target Dext invoices instantly during an audit.

You define validation schemas in your Python code before passing Dext tools to the OpenAI Agents SDK agent. The SDK validates the parameters for tools like `get_item_details` before making the actual Dext API call, preventing malformed requests.

The OpenAI Agents SDK agent calls `list_accounting_categories` to fetch the current Dext chart of accounts. If the category does not match, the agent flags the item for manual review instead of guessing the classification.

Yes. All raw receipt scans, bank account numbers, and client lists from Dext remain inside the Vinkius sandboxed environment. The MCP Server uses ephemeral transport, meaning your financial data is never stored or used to train OpenAI models.

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