Frequently Asked Questions (FAQ) about mcp-flowise

What is mcp-flowise?

mcp-flowise is a Python package that implements a Model Context Protocol (MCP) server, integrating with the Flowise API. It allows for listing chatflows, creating predictions, and dynamically registering tools for Flowise chatflows or assistants.

What is MCP?

MCP (Model Context Protocol) is an open protocol that standardizes how applications provide context to Large Language Models (LLMs), enabling AI models to interact with external data sources and tools.

What are the prerequisites for installing mcp-flowise?

To install mcp-flowise, you need Python 3.12 or higher and the uvx package manager.

How do I install mcp-flowise?

You can install mcp-flowise via Smithery or by using uvx directly from the GitHub repository. Detailed installation steps are provided in the documentation.

What are the modes of operation in mcp-flowise?

mcp-flowise supports two modes: FastMCP (Simple) mode and LowLevel mode. FastMCP mode exposes list_chatflows and create_prediction tools, while LowLevel mode dynamically registers all chatflows as separate tools.

How do I enable FastMCP mode?

Enable FastMCP mode by setting the environment variable FLOWISE_SIMPLE_MODE to true.

What environment variables are required for mcp-flowise?

The required environment variables include FLOWISE_API_KEY (your Flowise API Bearer token) and FLOWISE_API_ENDPOINT (Base URL for Flowise).

How can I filter chatflows in mcp-flowise?

Filters can be applied using environment variables such as FLOWISE_WHITELIST_ID, FLOWISE_BLACKLIST_ID, FLOWISE_WHITELIST_NAME_REGEX, and FLOWISE_BLACKLIST_NAME_REGEX.

How do I protect my Flowise API key?

Ensure the FLOWISE_API_KEY is kept secure and not exposed in logs or repositories. Use .env files or environment variables for sensitive configurations and add .env to your .gitignore file.

What should I do if I encounter connection errors?

Verify that the FLOWISE_API_ENDPOINT is reachable and that your Flowise server is running.

Can I run mcp-flowise on Windows?

Yes, but running mcp-flowise on Windows with uvx requires a specific configuration, including using full paths to uvx.exe and the cloned repository.

What is UBOS?

UBOS is a full-stack AI Agent Development Platform focused on bringing AI Agents to every business department. Our platform helps you orchestrate AI Agents, connect them with your enterprise data, build custom AI Agents with your LLM model, and create Multi-Agent Systems.

How does mcp-flowise integrate with UBOS?

mcp-flowise allows UBOS users to leverage their Flowise chatflows within the UBOS platform, enabling the creation of intelligent AI agents that automate tasks, improve customer support, and drive business growth.

What are some use cases for mcp-flowise with UBOS?

Use cases include enhanced customer support AI agents, streamlined sales and marketing automation, improved internal knowledge management, and advanced data analysis and reporting.