How to Use the Dext MCP in Mastra AI

Q: How do I use the Dext MCP server to process all items pending review with Mastra AI?

Create a workflow that starts by calling listitemspendingreview. Then, use a loop in your Mastra AI definition to iterate through each item returned and call getitemdetails to process it.

Q: Can my workflow access the full Dext chart of accounts?

Absolutely. The listaccountingcategories tool provides the full chart of accounts. Your Mastra AI workflow can fetch this list to make decisions about how to categorize new invoices.

Build unstoppable accounting workflows for Dext with Mastra AI's conditional logic and automatic retries.

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 Mastra AI

Create your Vinkius account to connect Dext to Mastra 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 Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create Resilient AP Bots

An accounting workflow that breaks is worse than no workflow. Mastra AI's engine lets you build processes that can handle failure. For example, if a call to `get_item_details` fails, Mastra automatically retries with exponential backoff. You define the logic. If `list_items_pending_review` returns an item from a new supplier, route it for human approval. If it's a known supplier from `list_extracted_suppliers`, automatically categorize it using `list_accounting_categories` and move on.

Automate Client Onboarding

Use Mastra AI to build a workflow that fully onboards a new accounting client. The process can start by pulling a client list with `list_accounting_clients`, then check their configuration with `get_account_metadata`. The workflow can then verify users with `list_account_users` and check for `list_connected_bank_accounts`. If a bank account is missing, Mastra can trigger a notification and pause the workflow, resuming automatically once the issue is fixed.

Build Workflows with this MCP Server

This Dext MCP Server gives you the tools to build real accounting automation. A simple workflow could be: poll `list_inbox_items` every hour. For each new item, get its details with `get_item_details`. Then, use Mastra's conditional logic to decide the next step. You can search for matching supplier names with `search_inbox_by_keyword` to find historical patterns, all inside a single, reliable workflow.

Setup guide

Set up Dext MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All Dext tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "dext-mcp-client",
  servers: {
    "dext-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "Dext Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to Dext tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent Dext transactions"
);
console.log(result.text);

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 Mastra AI

Mastra AI has built-in support for automatic retries and conditional branching. You can configure your workflow to catch an error from a Dext tool, wait, and try again, or route the task to a different path for manual review.

Yes. Mastra AI supports human-in-the-loop patterns. Your workflow can pull an invoice, check its value, and if it's over a certain threshold, pause and wait for an external approval before proceeding.

Create a workflow that starts by calling `list_items_pending_review`. Then, use a loop in your Mastra AI definition to iterate through each item returned and call `get_item_details` to process it.

Absolutely. The `list_accounting_categories` tool provides the full chart of accounts. Your Mastra AI workflow can fetch this list to make decisions about how to categorize new invoices.

Your Mastra agent communicates with the Dext server through a secure, authenticated channel managed by Vinkius. The system is designed for zero trust; no financial data like invoice details or bank connections is ever logged or stored by the MCP server itself. It's a direct pipe, and each session is ephemeral.

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