Unleash the Power of Flowise with mcp-flowise: A Comprehensive Guide for UBOS Users

In the rapidly evolving landscape of AI, integrating large language models (LLMs) with external data sources and tools is paramount. This is where the Model Context Protocol (MCP) comes into play. MCP standardizes how applications provide context to LLMs, enabling more informed and effective AI interactions. mcp-flowise is a Python package that acts as a crucial bridge, seamlessly connecting the Flowise API with the MCP ecosystem.

For UBOS users, mcp-flowise unlocks a wealth of opportunities by enabling them to leverage their Flowise chatflows within the UBOS full-stack AI Agent development platform. This integration allows for the orchestration of AI Agents, connection to enterprise data, and the creation of custom AI Agents, ultimately boosting business departmental efficiency.

What is mcp-flowise?

mcp-flowise is designed to implement an MCP server, which integrates directly with the Flowise API. It offers a standardized and flexible method for listing chatflows, generating predictions, and dynamically registering tools specifically tailored for Flowise chatflows or assistants. This ensures that your AI agents have access to the most relevant and up-to-date information.

Key Features of mcp-flowise:

• Dynamic Tool Exposure: In LowLevel mode, mcp-flowise dynamically creates tools for each chatflow or assistant, making it highly adaptable to various use cases.
• Simplified Configuration: FastMCP mode exposes list_chatflows and create_prediction tools, simplifying the setup process for users who need a more straightforward configuration.
• Flexible Filtering: Both modes support filtering chatflows via whitelists and blacklists by IDs or names (using regular expressions), allowing precise control over which chatflows are exposed.
• Seamless MCP Integration: Integrates smoothly into MCP workflows, ensuring compatibility and ease of use within the larger MCP ecosystem.

Use Cases for mcp-flowise with UBOS

1. Enhanced Customer Support AI Agents

By integrating mcp-flowise into your UBOS platform, you can create AI agents that provide superior customer support. These agents can access and utilize Flowise chatflows to answer customer queries, resolve issues, and provide personalized recommendations. For instance:

• Scenario: A customer is experiencing technical difficulties with a product.
• Solution: The UBOS AI agent uses mcp-flowise to access a Flowise chatflow designed to troubleshoot the specific product. The agent guides the customer through a series of steps, leveraging the chatflow’s logic to identify and resolve the issue. This ensures consistent and effective support, reducing the workload on human agents.

2. Streamlined Sales and Marketing Automation

mcp-flowise enables the creation of AI agents that automate sales and marketing tasks, leading to increased efficiency and revenue. Consider these applications:

• Lead Qualification: An AI agent uses mcp-flowise to access a Flowise chatflow that analyzes incoming leads, scoring them based on predefined criteria. This helps the sales team prioritize the most promising leads, improving conversion rates.
• Personalized Marketing Campaigns: AI agents can use Flowise chatflows to create and deliver personalized marketing messages based on customer data. This results in higher engagement and better campaign performance.

3. Improved Internal Knowledge Management

Large organizations often struggle with managing and disseminating internal knowledge. mcp-flowise can help by creating AI agents that serve as intelligent knowledge assistants:

• Employee Onboarding: An AI agent uses mcp-flowise to access Flowise chatflows that guide new employees through the onboarding process. The agent provides answers to common questions, directs employees to relevant resources, and ensures a smooth transition into the company.
• Policy and Procedure Lookup: Employees can use an AI agent to quickly find information about company policies and procedures. The agent uses mcp-flowise to access Flowise chatflows that contain this information, providing accurate and up-to-date answers.

4. Advanced Data Analysis and Reporting

Integrating mcp-flowise with UBOS allows for the creation of AI agents that perform advanced data analysis and generate insightful reports:

• Sales Performance Analysis: An AI agent uses mcp-flowise to access a Flowise chatflow that analyzes sales data, identifying trends and patterns. The agent generates reports that provide valuable insights to the sales team, helping them make data-driven decisions.
• Customer Sentiment Analysis: AI agents can use Flowise chatflows to analyze customer feedback from various sources, such as social media, surveys, and reviews. This helps businesses understand customer sentiment and identify areas for improvement.

Modes of Operation: Choosing the Right Approach

mcp-flowise supports two distinct operation modes, each designed to cater to different use cases and levels of complexity:

1. FastMCP Mode (Simple Mode)

FastMCP mode is enabled by setting the environment variable FLOWISE_SIMPLE_MODE=true. This mode simplifies the integration process by exposing only two tools: list_chatflows and create_prediction. It is ideal for scenarios where you need a straightforward way to interact with a single chatflow or assistant.

• Key Benefits:
  • Simpler configuration, requiring minimal setup.
  • Suitable for use cases involving a single chatflow or assistant.
  • Provides a list_chatflows tool for discovering available chatflows.

2. LowLevel Mode

LowLevel mode, activated when FLOWISE_SIMPLE_MODE=False, dynamically registers all chatflows as separate tools. This approach offers greater flexibility and is well-suited for complex environments with numerous chatflows. Each chatflow is exposed as a distinct tool, named after the chatflow name (normalized).

• Key Benefits:
  • Dynamically registers all chatflows as separate tools.
  • Tools are named after chatflow names, making them easy to identify.
  • Uses descriptions from the FLOWISE_CHATFLOW_DESCRIPTIONS variable, providing detailed information about each tool.

Installing and Configuring mcp-flowise

Prerequisites

Before installing mcp-flowise, ensure you have the following prerequisites in place:

• Python 3.12 or higher
• uvx package manager

Installation Steps

1. Install via Smithery: For Claude Desktop, you can install mcp-flowise automatically using Smithery:

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

2. Install and Run via uvx: Verify that you can run the server directly from the GitHub repository using uvx:

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

Adding to MCP Ecosystem

Integrate mcp-flowise into your MCP ecosystem by adding it to the mcpServers configuration. Here’s an example:

{ “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}” } } } }

Running on Windows with uvx

Running mcp-flowise on Windows with uvx requires a slightly different approach due to potential issues with --from git+https. The recommended solution is to clone the repository locally and configure the mcpServers with the full path to uvx.exe and the cloned repository. Here’s an example configuration:

{ “mcpServers”: { “flowise”: { “command”: “C:Usersmatth.localbinuvx.exe”, “args”: [ “–from”, “C:Usersmatthdownloadsmcp-flowise”, “mcp-flowise” ], “env”: { “LOGLEVEL”: “ERROR”, “APPDATA”: “C:UsersmatthAppDataRoaming”, “FLOWISE_API_KEY”: “your-api-key-goes-here”, “FLOWISE_API_ENDPOINT”: “http://localhost:3006/” } } } }

Environment Variables: Configuring mcp-flowise

Properly configuring environment variables is crucial for the correct operation of mcp-flowise. Here’s a breakdown of the essential variables:

General

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

LowLevel Mode (Default)

• FLOWISE_CHATFLOW_DESCRIPTIONS: Comma-separated list of chatflow_id:description pairs. Example:

  FLOWISE_CHATFLOW_DESCRIPTIONS=“abc123:Chatflow One,xyz789:Chatflow Two”

FastMCP Mode (FLOWISE_SIMPLE_MODE=true)

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

Filtering Chatflows: Controlling Access

Filters can be applied in both modes using the following environment variables:

• 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.*"

Security Best Practices

• Protect Your API Key: Ensure the FLOWISE_API_KEY is kept secure and not exposed in logs or repositories.
• Environment Configuration: Use .env files or environment variables for sensitive configurations. Add .env to your .gitignore.

Troubleshooting Common Issues

• Missing API Key: Ensure FLOWISE_API_KEY is set correctly.
• Invalid Configuration: If both FLOWISE_CHATFLOW_ID and FLOWISE_ASSISTANT_ID are set, the server will refuse to start.
• Connection Errors: Verify FLOWISE_API_ENDPOINT is reachable.

UBOS: Your Full-Stack AI Agent Development Platform

UBOS is a comprehensive platform designed to bring the power of AI Agents to every business department. With UBOS, you can:

• Orchestrate AI Agents: Seamlessly manage and coordinate your AI agents to achieve specific goals.
• Connect to Enterprise Data: Integrate your AI agents with your enterprise data sources, ensuring they have access to the information they need.
• Build Custom AI Agents: Create custom AI agents tailored to your specific business requirements, using your LLM model.
• Develop Multi-Agent Systems: Build complex multi-agent systems that can tackle challenging tasks.

By integrating mcp-flowise with UBOS, you can unlock the full potential of your Flowise chatflows and create AI agents that drive real business value.

Conclusion

mcp-flowise is a powerful tool that bridges the gap between Flowise and the MCP ecosystem. For UBOS users, this integration offers a streamlined way to leverage Flowise chatflows within the UBOS platform, enabling the creation of intelligent AI agents that automate tasks, improve customer support, and drive business growth. By following this comprehensive guide, you can effectively install, configure, and utilize mcp-flowise to enhance your UBOS-powered AI initiatives. Embrace the future of AI with mcp-flowise and UBOS.