Loading connector details…
Loading connector details…
Choose a unique username to continue using AgentHotspot
by matthewhand • Automation & Orchestration
A Model Context Protocol (MCP) server that integrates with the Flowise API to list chatflows, create predictions, and dynamically expose chatflows as tools for agents.
Discover and list available Flowise chatflows and assistants programmatically for routing or selection.
Invoke specific Flowise chatflows or assistants as callable tools to generate predictions and handle conversational workflows.
Fine-grained exposure of only certain chatflows via ID or name filtering (whitelists/blacklists and regex) to limit tool surface area.
mcp-flowise provides an MCP-compatible server that connects to a Flowise instance, exposing chatflows and assistants as callable tools. It supports a default LowLevel mode that dynamically registers tools per chatflow and a FastMCP mode that exposes a minimal static toolset for simple configurations. The package includes flexible filtering (whitelists/blacklists by ID or name), environment-driven configuration, and works with uvx/Smithery for easy deployment and integration into MCP ecosystems.
List all available chatflows from the Flowise API. This function respects optional whitelisting or blacklisting if configured via FLOWISE_CHATFLOW_WHITELIST or FLOWISE_CHATFLOW_BLACKLIST. Returns: str: A JSON-encoded string of filtered chatflows.
Create a prediction by sending a question to a specific chatflow or assistant. Args: chatflow_id (str, optional): The ID of the chatflow to use. Defaults to FLOWISE_CHATFLOW_ID. question (str): The question or prompt to send to the chatflow. Returns: str: The raw JSON response from Flowise API or an error message if something goes wrong.
Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.