{"type":"mcp_server","name":"ifly-workflow-mcp-server","description":"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.","category":"AI","language":"Python","stars":27,"forks":0,"owner":"iflytek","github_url":"https://github.com/iflytek/ifly-workflow-mcp-server","homepage":null,"setup":"## Setup\n\n1.  Prepare a `config.yaml` file with workflow information including `flow_id`, `name`, `description`, and `api_key`.\n2.  Create a bot on the iFlytek platform.\n3.  Publish the workflow as an API after debugging and successful conversation.\n4.  Bind the workflow to an application to retrieve the workflow ID and authentication information.\n5.  Add the iFlytek MCP server configuration to your `claude_desktop_config.json` or `mcp.json` file, specifying the command, arguments, and environment variables, including the path to the `config.yaml` file.","tools":"## Available Tools\n\n1.  **Workflow Structure** (Composed of multiple nodes, supporting 14 types of nodes.)\n2.  **Robust Node Support** (14 types of workflow nodes to meet diverse business requirements.)\n3.  **Complex variable I/O** (Enables flexible data transmission.)\n4.  **Advanced Orchestration Modes** (Sequential, Parallel, Loop, and Nested Execution.)\n5.  **Hook Mechanism** (Enables streaming output, ensuring real-time processing.)\n6.  **Multiple Development Paradigms** (Single-turn, single-branch, multi-branch, loop, and multi-turn interaction.)\n7.  **Multi-Model Support** (Based on the Model of Models (MoM) hybrid application architecture.)","faq":null,"created_at":"2025-03-24T12:08:53+00:00","updated_at":"2025-03-28T03:31:13+00:00","source_url":"https://model-context-protocol.com/servers/iflytek-workflow-mcp-server-implementation","related_articles":[]}