Skip to main content

mcp-flowise

MCP server that exposes the chatflows of your local Flowise as tools for Claude, Cursor, free-code, or any MCP client.

PyPI npm

Tools

Simple mode (default):

  • list_chatflows() — lists available chatflows (id + name).
  • create_prediction(chatflow_id, question) — runs a Chat/Form-trigger chatflow and returns its response.
  • trigger_webhook(chatflow_id, payload) — runs a Webhook-trigger chatflow via POST /api/v1/webhook/{id}.

Dynamic mode (FLOWISE_DYNAMIC=true):

  • Registers one tool per chatflow at startup, e.g. flowise_support_bot(question).

Requirements

  • A running Flowise instance (default http://localhost:3000)
  • Node.js 18+ or Python 3.10+ with uv

Installation

One-command install (any client)

npx -y -p @suamkf08/mcp-flowise mcp-flowise-install --client claude
npx -y -p @suamkf08/mcp-flowise mcp-flowise-install --client cursor
npx -y -p @suamkf08/mcp-flowise mcp-flowise-install --client free-code
npx -y -p @suamkf08/mcp-flowise mcp-flowise-install --client vscode
npx -y -p @suamkf08/mcp-flowise mcp-flowise-install --client windsurf

-p @suamkf08/mcp-flowise pulls the published package that ships the mcp-flowise-install binary; npx then runs that binary. (There is no separate @suamkf08/mcp-flowise-install package on npm — the installer lives inside @suamkf08/mcp-flowise.)

The script asks for your FLOWISE_API_ENDPOINT and FLOWISE_API_KEY, writes the config automatically, and tells you where it was saved. Restart your client after running it.


Manual install

Claude Desktop

Add this to your claude_desktop_config.json (~/Library/Application Support/Claude/claude_desktop_config.json on macOS, %APPDATA%\Claude\claude_desktop_config.json on Windows):

Option A — via npm (Node.js required):

{
  "mcpServers": {
    "mcp-flowise": {
      "command": "npx",
      "args": ["-y", "@suamkf08/mcp-flowise"],
      "env": {
        "FLOWISE_API_ENDPOINT": "http://localhost:3000",
        "FLOWISE_API_KEY": ""
      }
    }
  }
}

Option B — via uvx (uv required):

Install uv first if you don't have it:

# macOS / Linux
curl -LsSf https://astral.sh/uv/install.sh | sh

# Windows
powershell -c "irm https://astral.sh/uv/install.ps1 | iex"

Then add to claude_desktop_config.json:

{
  "mcpServers": {
    "mcp-flowise": {
      "command": "uvx",
      "args": ["mcp-flowise"],
      "env": {
        "FLOWISE_API_ENDPOINT": "http://localhost:3000",
        "FLOWISE_API_KEY": ""
      }
    }
  }
}

Cursor

Add to .cursor/mcp.json in your project (or ~/.cursor/mcp.json globally):

{
  "mcpServers": {
    "mcp-flowise": {
      "command": "npx",
      "args": ["-y", "@suamkf08/mcp-flowise"],
      "env": {
        "FLOWISE_API_ENDPOINT": "http://localhost:3000",
        "FLOWISE_API_KEY": ""
      }
    }
  }
}

free-code

Add to ~/.free-code/agent/mcp.json (or import with /mcp-import):

{
  "mcpServers": {
    "mcp-flowise": {
      "command": "npx",
      "args": ["-y", "@suamkf08/mcp-flowise"],
      "env": {
        "FLOWISE_API_ENDPOINT": "http://localhost:3000",
        "FLOWISE_API_KEY": ""
      }
    }
  }
}

Then enable it in free-code:

/mcp enable mcp-flowise
/reload

Configuration

Environment variable Default Description
FLOWISE_API_ENDPOINT http://localhost:3000 Base URL of your Flowise instance
FLOWISE_API_KEY (empty) Bearer token (Flowise → Settings → API Keys)
FLOWISE_DYNAMIC false Set to true to register one tool per chatflow
FLOWISE_WHITELIST_ID (empty) Comma-separated chatflow IDs to include
FLOWISE_BLACKLIST_ID (empty) Comma-separated chatflow IDs to exclude
FLOWISE_WHITELIST_NAME_REGEX (empty) Only include chatflows whose name matches
FLOWISE_BLACKLIST_NAME_REGEX (empty) Exclude chatflows whose name matches

Development

git clone https://github.com/suamkf08/mcp-flowise
cd mcp-flowise
uv run mcp-flowise        # starts over stdio; Ctrl+C to quit

Inspect with MCP Inspector:

uv run mcp dev mcp_flowise/server.py

Flowise API reference

  • List chatflows: GET {endpoint}/api/v1/chatflows
  • Run chatflow: POST {endpoint}/api/v1/prediction/{chatflowId} with {"question": "..."}
  • Auth header: Authorization: Bearer <FLOWISE_API_KEY>

Metadata

Release files for mcp-flowise 0.1.5

For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.

Source distribution (sdist)

Source distribution for mcp-flowise 0.1.5
File Size Uploaded
mcp_flowise-0.1.5.tar.gz 13.6 kB Details

Built distribution (wheel)

Table of built distributions (wheels) for mcp-flowise 0.1.5
File Interpreter ABI Platform
mcp_flowise-0.1.5-py3-none-any.whl Python 3 none any Details

Total release size: 19.3 kB

Release files / mcp_flowise-0.1.5.tar.gz

Download URL mcp_flowise-0.1.5.tar.gz
Size 13.6 kB
Tags Source
SHA-256 checksum
How to use checksums
56165f8c721e445a1ff97fa97854871e2cc887233b9990464c9a528a7b98bec6
BLAKE2b-256 checksum
How to use checksums
704f41da49535f485e0b4fae83a82847b80b6a3085a78bd7ebd8828c37f4ff6d
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.3

Release files / mcp_flowise-0.1.5-py3-none-any.whl

Download URL mcp_flowise-0.1.5-py3-none-any.whl
Size 5.7 kB
Tags Python 3
SHA-256 checksum
How to use checksums
c8be33e52d8e06920a87730c1afaf4b12c5b46f5a29a92e15263bb2164fe5a60
BLAKE2b-256 checksum
How to use checksums
408f21544f97d1388c4fdb3d6c4bca5c79bf0baa092f7e354a8520b9991fb342
Upload date
Uploaded using Trusted Publishing?
What is trusted publishing?
No
Uploaded via twine/6.2.0 CPython/3.12.3

Release history Release notifications | RSS feed

This release

0.1.5 This release

2 release files

0.1.1

2 release files

0.1.0

2 release files

Anthropic, PBC Visionary sponsor Bloomberg Visionary sponsor Hudson River Trading Visionary sponsor Meta Visionary sponsor NVIDIA Visionary sponsor Microsoft Sustainability sponsor Depot Continuous Integration AWS Cloud computing and Security Sponsor Datadog Monitoring Fastly CDN Google Download Analytics Sentry Error logging StatusPage Status page