How to Use the Flowise MCP in Cursor

Q: How do I configure Flowise inside the Cursor editor?

Create an mcp.json file in your .cursor directory and add the Flowise MCP Server configuration. Once saved, enable Agent mode in Cursor, and the tools will be ready to use in your chat sidebar.

Q: Can Cursor modify my Flowise chatflows directly?

No. The server uses getchatflow to read configurations and predict to run them, but it does not write or edit the visual nodes. You still use the visual editor for design and this server for execution.

Q: How do I debug failing Flowise runs inside Cursor?

Ask your agent to inspect the failure. It will use gethistory to pull the latest execution logs and pinpoint which node failed, allowing you to fix the visual layout quickly.

Q: Does Cursor support Flowise credentials?

Yes, but only for validation. The agent uses listcredentials to verify that the correct API keys are connected to your flows, ensuring you do not run predictions on unauthenticated endpoints.

Execute and debug your Flowise low-code backends directly inside the Cursor editor while writing code.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Flowise MCP to Cursor

Create your Vinkius account to connect Flowise 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 Flowise with Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Execute Flowise predictions inside the Cursor editor

The Flowise MCP Server lets your Cursor agent test visual backend flows while you write your application code. You use the `predict` tool to run prompts against your chatflows and see the raw JSON output in your editor sidebar. This eliminates the need to jump back and forth to a browser to test your endpoints. Your agent can write frontend code using the exact structure returned by your live visual pipelines.

Discover active chatflows and system tools

This MCP Server maps out your entire visual backend for your editor. The agent uses `list_chatflows` and `list_agentflows` to discover what endpoints are available for your application to call. If you need to know what custom components are installed, the agent uses `list_tools` to fetch the active tool list. You get instant documentation of your backend capabilities right next to your code.

Inspect node configurations and history logs

Debugging visual nodes requires seeing their internal state. Your agent uses `get_chatflow` to pull down the exact JSON layout of your nodes so you can verify routing logic. When a run fails, you use `get_history` to pull the execution logs. This lets you compare previous runs and pinpoint exactly which node in your visual flow caused the error.

Setup guide

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

.cursor/mcp.json

{
  "mcpServers": {
    "flowise-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 Flowise. 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 Flowise 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 Flowise MCP in Cursor

Create an `mcp.json` file in your `.cursor` directory and add the Flowise MCP Server configuration. Once saved, enable Agent mode in Cursor, and the tools will be ready to use in your chat sidebar.

No. The server uses `get_chatflow` to read configurations and `predict` to run them, but it does not write or edit the visual nodes. You still use the visual editor for design and this server for execution.

Ask your agent to inspect the failure. It will use `get_history` to pull the latest execution logs and pinpoint which node failed, allowing you to fix the visual layout quickly.

Yes, but only for validation. The agent uses `list_credentials` to verify that the correct API keys are connected to your flows, ensuring you do not run predictions on unauthenticated endpoints.

All prediction payloads sent via the MCP Server go directly to your self-hosted or managed instance. No raw prediction data or inputs are cached or stored by the editor itself.

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