Flowise MCP server

Integrates with Flowise API to enable interaction with chatflows and assistants through dynamic tool registration or simplified static tools for listing and prediction creation.
Back to servers
Provider
Andy Dukes
Release date
Mar 17, 2025
Language
Python

This MCP-Flowise server connects Flowise API chatflows to Model Context Protocol (MCP) compatible services like Claude Desktop. It enables you to access and interact with Flowise chatflows through standardized tools, making them available to MCP clients.

Installation Options

Using Smithery (Recommended)

The easiest way to install mcp-flowise for Claude Desktop is via Smithery:

npx -y @smithery/cli install @matthewhand/mcp-flowise --client claude

Manual Installation with uvx

If you prefer to run it directly with uvx:

uvx --from git+https://github.com/andydukes/mcp-flowise mcp-flowise

Integrating with MCP Ecosystem

Add mcp-flowise to your MCP ecosystem by configuring the mcpServers section:

{
    "mcpServers": {
        "mcp-flowise": {
            "command": "uvx",
            "args": [
                "--from",
                "git+https://github.com/matthewhand/mcp-flowise",
                "mcp-flowise"
            ],
            "env": {
                "FLOWISE_API_KEY": "${FLOWISE_API_KEY}",
                "FLOWISE_API_ENDPOINT": "${FLOWISE_API_ENDPOINT}"
            }
        }
    }
}

Operation Modes

FastMCP Mode (Simple)

Enable this mode by setting FLOWISE_SIMPLE_MODE=true. This provides:

  • Two static tools: list_chatflows and create_prediction
  • Simpler configuration with FLOWISE_CHATFLOW_ID or FLOWISE_ASSISTANT_ID
  • Easy access to all available chatflows

LowLevel Mode (Default)

This mode (FLOWISE_SIMPLE_MODE=false or unset):

  • Dynamically registers each chatflow as a separate tool
  • Names tools based on chatflow names (normalized)
  • Uses descriptions from FLOWISE_CHATFLOW_DESCRIPTIONS or falls back to chatflow names

Windows Configuration

If running on Windows with uvx, use a local clone and full paths:

{
  "mcpServers": {
    "flowise": {
      "command": "C:\\Users\\matth\\.local\\bin\\uvx.exe",
      "args": [
        "--from",
        "C:\\Users\\matth\\downloads\\mcp-flowise",
        "mcp-flowise"
      ],
      "env": {
        "LOGLEVEL": "ERROR",
        "APPDATA": "C:\\Users\\matth\\AppData\\Roaming",
        "FLOWISE_API_KEY": "your-api-key-goes-here",
        "FLOWISE_API_ENDPOINT": "http://localhost:3006/"
      }
    }
  }
}

Environment Variables

Required Variables

  • FLOWISE_API_KEY: Your Flowise API Bearer token
  • FLOWISE_API_ENDPOINT: Base URL for Flowise (default: http://localhost:3006)

LowLevel Mode Variables

  • FLOWISE_CHATFLOW_DESCRIPTIONS: Comma-separated list of chatflow_id:description pairs
    FLOWISE_CHATFLOW_DESCRIPTIONS="abc123:Chatflow One,xyz789:Chatflow Two"
    

FastMCP Mode Variables

  • FLOWISE_CHATFLOW_ID: Single Chatflow ID (optional)
  • FLOWISE_ASSISTANT_ID: Single Assistant ID (optional)
  • FLOWISE_CHATFLOW_DESCRIPTION: Optional description for the exposed tool

Filtering Chatflows

Control which chatflows are exposed using these filters:

  • Whitelist by ID:
    FLOWISE_WHITELIST_ID="id1,id2,id3"
  • Blacklist by ID:
    FLOWISE_BLACKLIST_ID="id4,id5"
  • Whitelist by Name (Regex):
    FLOWISE_WHITELIST_NAME_REGEX=".*important.*"
  • Blacklist by Name (Regex):
    FLOWISE_BLACKLIST_NAME_REGEX=".*deprecated.*"

Note: Whitelists take precedence over blacklists when both are configured.

Troubleshooting

  • Missing API Key: Verify FLOWISE_API_KEY is set correctly
  • Invalid Configuration: Don't set both FLOWISE_CHATFLOW_ID and FLOWISE_ASSISTANT_ID
  • Connection Errors: Ensure FLOWISE_API_ENDPOINT is correct and reachable

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later