An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Flowise to ChatGPT, Claude and Gemini

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Manage your low-code workflows through natural conversation.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 7 capabilities

We ship only the actions that matter.

Capability set01 / 02

01-04

4 capabilities in this set.

Part of 7 available through Flowise.

  1. 01

    List credentials

    Lists the credentials stored in your Flowise environment. This helps you verify which authentication components are available for your flows.

  2. 02

    List agentflows

    Returns a list of all configured agentflows. Use this to see which multi-step reasoning workflows are ready to use.

  3. 03

    List tools

    Shows the custom capabilities and third-party integrations configured in Flowise. Use this to check what capabilities your flows can access.

  4. 04

    Get history

    Retrieves the chat execution history from your Flowise instance. Use this to pull past conversational logs for debugging.

Capability set02 / 02

05-07

3 capabilities in this set.

Part of 7 available through Flowise.

  1. 05

    List chatflows

    Provides a list of all deployed chatflows in your instance. This is the quickest way to see what workflows you have available.

  2. 06

    Get chatflow

    Fetches the specific architectural details of a chatflow. It provides the nodes and edges that define the flow's logic.

  3. 07

    Predict

    Sends a user query to a specific chatflow and returns the AI response. This lets you test your flows in real-time.

Real work

What teams actually run

01

Rapid Prototyping

Test how a new RAG pipeline responds to different prompts without leaving your IDE.

02

Logic Debugging

Analyze execution history to find exactly where a multi-step agentflow failed.

03

Capability Auditing

Quickly check which capabilities and credentials are active to ensure an agent has the right permissions.

04

Workflow Monitoring

Verify the health and availability of your Flowise orchestration layer.

Automate a task

Put Flowise to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

Flowise works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put Flowise to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

866ms average. Fast in production.

Flowise is checked daily against the live service.

Daily averagePeak 1000ms
Oct 3Today
Fastest day
685ms
Slowest day
1000ms
14-day trend
Stable-3%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 7 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of Flowise, so you can see the experience inside your AI.

It does not authenticate your account with Flowise. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

Flowise Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_x0CXvywaUNOIkFSe5hI4681xfnamFZZaTdsop8is/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — Flowise capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "flowise-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_x0CXvywaUNOIkFSe5hI4681xfnamFZZaTdsop8is/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up Flowise in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work Flowise owners hand off.

This MCP is built for people building complex AI logic through low-code interfaces who want to stay in their primary development environment.

  • 01

    AI Developers

    They use it to test and debug chatflows and agentflows without switching to the Flowise UI.

  • 02

    Automation Engineers

    They trigger AI predictions and monitor execution histories using natural language commands.

  • 03

    Product Teams

    They audit available capabilities and verify conversational logs in real-time to check product behavior.

FAQ

Questions Flowise owners ask.

  • 01

    How do I connect this MCP to my Flowise instance?

    You just need to provide your Flowise Base URL and your API Key, which you can find in your Flowise Settings menu.

  • 02

    Which AI clients can I use with this MCP?

    This MCP works with any compatible client, including Claude, Cursor, and Windsurf.

  • 03

    Can I run tests on my flows through my AI agent?

    Yes, you can use the predict capability to send questions to specific chatflows and get responses in real-time.

  • 04

    How do I debug a failed agentflow?

    You can ask your agent to retrieve the execution history for that specific flow to inspect the logs and traces.

  • 05

    Does this MCP host my Flowise instance?

    No, this MCP connects to your existing Flowise instance. Vinkius manages the connection and the MCP itself so it is ready to use in your client.

  • 06

    Can my agent run a prediction against a specific Flowise chatflow?

    Yes. Use the 'predict' capability. Provide the 'chatflow_id' and your question. The agent will command the Flowise backend to process the logic chain and return the AI-generated response directly in your chat.

  • 07

    How do I see the past conversational logs for a chatflow via chat?

    Use the 'get_history' capability with the 'chatflow_id'. Your agent will retrieve the past execution traces and logs, helping you understand how users have interacted with that specific logic chain natively.

  • 08

    Can I list all custom capabilities configured in my Flowise instance through the agent?

    Absolutely. Use the 'list_tools' capability. Your agent will retrieve custom capabilities and integrations configured in your environment, allowing you to audit available capabilities through natural conversation.

Explore

More in AI Frontier

Suggestions

Connect Flowise to Claude, Cursor, ChatGPT & more