How to Use the Daftra MCP in Cursor

Q: How do I connect the Daftra server to Cursor?

Create a .cursor/mcp.json file in your project's root directory. Add the Vinkius server URL to that file, and the Daftra tools will be available in Agent mode for anyone working on the project.

Build apps on your Daftra data faster. Let Cursor's agent pull live client and invoice details directly into your code.

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 Cursor

Create your Vinkius account to connect Daftra to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Code against your live Daftra data

Stop writing code against mock data. With this server, you can tell the Cursor agent, "get the details for client X and write a React component to display it." The agent calls `get_client_details` and gives you code populated with real information from your Daftra account. This changes how you build. Your code works with actual client names, invoice totals, and product lists from the start. It means you can spot issues and refine your logic immediately, without having to write a separate data-fetching layer first.

Build client management features

If you're building a customer portal, you can accelerate the work by having the agent call `list_clients` or `search_clients_by_name`. It can generate the code for search functions or client list displays right in your editor. It works for writing data, too. Need to build the backend for a "new client" form? Tell the agent what you need, and it can use the `create_client` tool to generate a working API endpoint handler in seconds.

Script reports with this MCP Server

Forget exporting CSVs to analyze your finances. Tell the agent, "get all invoices from last quarter and write a Python script to sum them up." It will use `list_invoices` to fetch the data and then generate the exact script you asked for. This is great for quick analysis. You can do the same with your expenses using `list_expenses`. Pull the raw data directly into your workspace and let the agent help you build scripts for categorization, filtering, or generating summaries.

Setup guide

Set up Daftra MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the Daftra MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent Daftra transactions." If the MCP tools are loaded correctly, Cursor will call the Daftra tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "daftra-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Cursor

In an agent chat, ask it to "list all inventory products." It runs the `list_inventory_products` tool, gets the data from Daftra, and can then format it as JSON, a typed array, or whatever else you need for your code.

Not right now. This server lets you read clients, invoices, and expenses, and you can create new clients with `create_client`. It does not include tools for updating or deleting existing records.

Create a `.cursor/mcp.json` file in your project's root directory. Add the Vinkius server URL to that file, and the Daftra tools will be available in Agent mode for anyone working on the project.

Absolutely. Just tell the agent your goal, like "find client 'ABC Corp' and list all their paid invoices." It will chain the `search_clients_by_name` and `list_invoices` tools to get the job done.

The server only fetches the Daftra data that your agent explicitly requests, like client names or invoice totals. Vinkius isolates each call in a secure sandbox, and your main Daftra API key is never stored in your editor or project files.

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