How to Use the Flowise MCP in Claude

Q: How do I connect Flowise to Claude Desktop?

Open your claudedesktopconfig.json file and add the Flowise MCP Server to your mcpServers list. Save the file, restart the Claude Desktop app, and the new tools will show up in your chat window.

Q: Can Claude Desktop run complex Flowise agentflows?

Yes. The agent uses listagentflows to find your multi-agent setups and executes them using the predict tool. It handles the routing automatically based on your visual layout.

Q: How does Claude Desktop handle Flowise credentials?

The server uses listcredentials to check which integrations are active. Claude Desktop only sees the metadata and names of these credentials, keeping your actual API keys hidden and secure on your server.

Q: Do I need to restart Claude Desktop when I update a chatflow?

No. The getchatflow tool pulls the latest configuration live from your Flowise instance. Any changes you make in the visual editor reflect instantly in your next prediction.

Run Flowise low-code AI workflows and execute predictions directly from your Claude Desktop app.

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 Claude Desktop

Create your Vinkius account to connect Flowise to Claude Desktop 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 Claude Desktop

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Trigger Flowise predictions directly inside Claude Desktop

The Flowise MCP Server connects Claude Desktop directly to your visual AI pipelines so you can run live runs without leaving your chat window. You use the `predict` tool to trigger specific chatflows and get responses back instantly. To check which pipelines are active before running them, your agent uses `list_chatflows` and `list_agentflows` to inspect your setup. This lets you swap between different backend models and logic paths on the fly.

Inspect active workflows and configuration details

This MCP Server exposes your low-code architecture directly to your workspace. Your agent uses `get_chatflow` to pull the exact node configuration and parameters of your visual flows. You can also run `list_tools` to see what external APIs or databases your Flowise instance can access. It gives you a clear view of your operational capabilities before you execute a single run.

Audit execution history and credentials in real time

Monitoring performance requires looking at previous runs with this MCP Server. Your agent uses `get_history` to pull past execution logs and track how your flows are behaving under real conditions. Security checks are straightforward too. The agent uses `list_credentials` to verify which API keys and integrations are active without exposing the raw secrets themselves.

Setup guide

Set up Flowise MCP in Claude Web or Desktop

1

Open Claude Settings

Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
2

Add Custom Connector

Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.
3

Start a conversation

Open a new chat. The Flowise MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Prerequisites

Claude Desktop installed (macOS or Windows)
Active Vinkius subscription with a valid endpoint token

1

Open Claude Desktop Settings

Click the menu icon at the top-left corner, go to Settings → Developer → Edit Config. This opens claude_desktop_config.json in your default text editor.
2

Paste the Flowise MCP configuration

Copy the JSON snippet on the right into the mcpServers object. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Restart Claude Desktop

Close and reopen the application. Claude needs a full restart to load new MCPs — refreshing a conversation is not enough.
4

Verify the connection

Open a new conversation. Click the 🔌 icon at the bottom of the message input. You should see tools listed under flowise-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 Claude Desktop

Open your `claude_desktop_config.json` file and add the Flowise MCP Server to your `mcpServers` list. Save the file, restart the Claude Desktop app, and the new tools will show up in your chat window.

Yes. The agent uses `list_agentflows` to find your multi-agent setups and executes them using the `predict` tool. It handles the routing automatically based on your visual layout.

The server uses `list_credentials` to check which integrations are active. Claude Desktop only sees the metadata and names of these credentials, keeping your actual API keys hidden and secure on your server.

No. The `get_chatflow` tool pulls the latest configuration live from your Flowise instance. Any changes you make in the visual editor reflect instantly in your next prediction.

Your execution logs and history data remain stored in your own database. The `get_history` tool pulls this data on demand for debugging, meaning your raw logs never sit on third-party servers.

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