How to Use the Daftra MCP in Mastra AI

Q: Does the Daftra MCP Server support human-in-the-loop approvals with Mastra AI?

Yes. You can configure requireToolApproval in your Mastra AI agent. When the agent wants to use a tool like createclient, it will pause and wait for a person to approve the action before it proceeds.

Build accounting and client management bots for Daftra that don't break. Mastra AI handles the retries and complex logic for you.

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 Mastra AI

Create your Vinkius account to connect Daftra 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 Daftra with Mastra AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate Invoicing and Follow-up

Automate your entire accounts receivable process. Build a Mastra AI agent that runs on a schedule, uses `list_invoices` to find overdue payments, and then uses `get_client_details` to get contact information for follow-up. Mastra AI's workflow engine means you can build this logic once and trust it to run. If a call to the Daftra API fails, the agent automatically retries with backoff, ensuring your process doesn't just stop because of a temporary network issue.

Create a Duplicate-Proof Client Onboarding Bot

Stop creating duplicate clients in Daftra. Your agent can use a workflow: first, run `search_clients_by_name` to check if a client exists. If not, proceed to `create_client`. If they do exist, the workflow can stop and notify an admin. This isn't just a simple script; it's a reliable process. Mastra AI lets you define these conditional branches, so your agent handles edge cases correctly every time without you writing a ton of boilerplate code.

Run a Nightly Financial Sync with this MCP Server

Run a nightly financial sync you can actually depend on. This MCP Server gives your agent access to your Daftra financials, and Mastra AI ensures the job gets done. Your agent can pull everything using `list_expenses`, `list_invoices`, and `list_estimates` to build a daily report or sync data to another system. The built-in retry mechanism is perfect for long-running, unsupervised tasks that need to be resilient.

Setup guide

Set up Daftra 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 Daftra 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: "daftra-mcp-client",
  servers: {
    "daftra-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

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

const result = await agent.generate(
  "List recent Daftra 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 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 Mastra AI

You can use the output of one tool to decide which tool to call next. For example, use the result from `search_clients_by_name` in an `if` block to decide whether to call `create_client` or to stop the workflow.

Yes. You can configure `requireToolApproval` in your Mastra AI agent. When the agent wants to use a tool like `create_client`, it will pause and wait for a person to approve the action before it proceeds.

You'll get a URL for the Daftra MCP Server from Vinkius. Just pass that URL when you initialize the `MCPClient` in your Mastra AI code. The client handles the connection and authentication.

Yes, that's a core feature of Mastra AI. Retries with exponential backoff are handled automatically by the framework, so your agent is resilient to temporary API failures when calling tools like `get_invoice_details`.

We don't store your Daftra financial data. Period. When your agent requests expense amounts or invoice totals, the data is proxied through our zero-trust platform and sent directly to your Mastra AI client. It's never written to disk on our end.

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