How to Use the Nutrient Workflow MCP in Cursor

Q: How do I add the Nutrient Workflow MCP Server to my Cursor editor?

Add the server to your .cursor/mcp.json file in your project root under the mcpServers key. Once saved, enable Agent mode in your Cursor chat to let the AI call the tools.

Q: Does the Nutrient Workflow integration with Cursor support multi-user testing?

Yes, it does. Your agent can query listusers to get valid user IDs, then use those IDs to assign and complete tasks during your development sessions.

Q: How do I fetch the status of an active request while coding?

You can have your agent run getrequest or listrequests to pull real-time execution data directly into your chat or inline edit session.

Generate code that interacts with your PDF workflows directly inside Cursor using live document data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers — Included with Plan

Connect Nutrient Workflow MCP to Cursor

Create your Vinkius account to connect Nutrient Workflow to Cursor — we handle the hosting, security, and runtime updates so you don't have to. No server setup required.

GDPR Included with Plan

Setup Nutrient Workflow with Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity Vinkius runs on Gemini

Gemini

Grok

Build and test PDF workflows directly in Cursor

The `start_request` tool lets your agent initiate real document runs while you write your application code. Instead of guessing payload structures, your AI client calls the tool to get live API responses. This lets you write code against actual JSON structures rather than outdated documentation or mock endpoints. You can inspect the exact output of `get_process` to understand how your system handles document states. Having this live context in your editor means you write working integration code faster. You eliminate the constant cycle of writing code, deploying, and checking external logs.

Inspect active tasks to debug document routing

The `get_task` tool retrieves precise metadata about specific steps in your document lifecycle. When writing custom event listeners, your agent uses this MCP Server to check if fields are populating correctly. It compares the live state against `list_user_tasks` to ensure your routing logic works under real-world conditions. You don't have to leave your editor to verify if a task was assigned to the correct user. Your agent queries `list_users` and matches the IDs directly inside your open files. This direct feedback loop makes debugging complex document routing a simple task.

Automate task completion during local development

The `complete_task` tool allows your agent to programmatically sign off on steps to test downstream triggers. When you are writing code for webhook handlers, you can have your editor execute this tool to simulate user actions. It updates the state machine instantly, letting you observe how your application reacts. This makes integration testing incredibly fast. You can chain `start_request` with `complete_task` to run through an entire document lifecycle in seconds. Your agent writes the test assertions based on the actual live state returned by the server.

Setup guide

Set up Nutrient Workflow 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 Nutrient Workflow 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 Nutrient Workflow transactions." If the MCP tools are loaded correctly, Cursor will call the Nutrient Workflow tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "nutrient-workflow-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 Nutrient Workflow. 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 Nutrient Workflow 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 Nutrient Workflow MCP in Cursor

Add the server to your `.cursor/mcp.json` file in your project root under the `mcpServers` key. Once saved, enable Agent mode in your Cursor chat to let the AI call the tools.

Yes, your agent can call the MCP Server to fetch actual workflow templates via `list_processes` and generate realistic test payloads. This ensures your local tests match your production document structures.

Yes, it does. Your agent can query `list_users` to get valid user IDs, then use those IDs to assign and complete tasks during your development sessions.

You can have your agent run `get_request` or `list_requests` to pull real-time execution data directly into your chat or inline edit session.

Your document workflow metadata, including task assignments and process definitions, is transmitted directly between Cursor and the secure Vinkius sandbox. No intermediate data is cached or stored, keeping your proprietary business logic and user profiles secure.

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