ifly-workflow-mcp-server

This repository provides a simple implementation of an MCP server using iFlytek, enabling the execution of iFlytek workflows through MCP tools for intelligent workflow scheduling in various business scenarios.

24
0

iFlytek Workflow MCP Server

This repository provides a simple implementation of a Model Context Protocol (MCP) server using iFlytek, enabling the invocation of iFlytek workflows through MCP tools. The Model Context Protocol (MCP) is an open protocol designed for effortless integration between LLM applications and external data sources or tools.

Features:

The system facilitates intelligent workflow scheduling, suitable for diverse business scenarios. Workflows consist of multiple nodes (14 types), including start and end nodes. It supports sequential, parallel, loop, and nested execution modes, with a Hook Mechanism for streaming output. It also supports single-turn/multi-turn interactions.

Usage:

To use the MCP server, a config.yaml file containing workflow information (flow ID, API key) is required. The workflow authentication information can be obtained by creating and publishing a bot on the iFlytek platform. The repository also provides instructions for manual installation by adding a persistent client to the claude_desktop_config.json or mcp.json file.

Repository

IF
iflytek

iflytek/ifly-workflow-mcp-server

Created

March 24, 2025

Updated

March 28, 2025

Language

Python

Category

AI