MCP.so
ログイン

iFlytek Workflow MCP Server

@iflytek

リポジトリ

iFlytek Workflow MCP Server について

This a simple implementation of an MCP server using iFlytek. It enables calling iFlytek workflows through MCP tools.

基本情報

カテゴリ

推論

ライセンス

MIT

ランタイム

python

トランスポート

stdio

公開者

iflytek

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "ifly-workflow-mcp-server": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/iflytek/ifly-workflow-mcp-server",
        "ifly_workflow_mcp_server"
      ],
      "env": {
        "CONFIG_PATH": ""
      }
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is iFlytek Workflow MCP Server?

It is an MCP server implementation using iFlytek that enables calling iFlytek workflows through MCP tools. Built on the iFlytek MCP server, it allows intelligent workflow scheduling for various business scenarios.

How to use iFlytek Workflow MCP Server?

Prepare a config.yaml file with workflow authentication info including flow_id and api_key. Then configure the server in your MCP client (e.g., Claude Desktop) using the uvx command with the CONFIG_PATH environment variable pointing to your YAML file. Launch the server.

Key features of iFlytek Workflow MCP Server

  • Supports 14 types of workflow nodes (basic, tool, logic, transformation)
  • Executes automatically with predefined sequence and rules
  • Offers sequential, parallel, loop, and nested execution modes
  • Provides hook mechanism for streaming output
  • Handles single-turn, multi-branch, loop, and multi-turn interactions
  • Supports multi-model selection via Model of Models (MoM) architecture

Use cases of iFlytek Workflow MCP Server

  • Automating multi-step business processes with conditional branching
  • Running tasks in

コメント

「推論」の他のコンテンツ

AWorld: Advancing Agentic AI

inclusionAI

Search, understand, reproduce, and improve an idea with ease

1.2K

n8n Workflow Builder MCP

ifmelate

MCP server that allow LLM in agent mode builds n8n workflows for you

51

Part 1. Real-Time LangGraph Agent with MCP Tool Execution

junfanz1

This project demonstrates a decoupled real-time agent architecture that connects LangGraph agents to remote tools served by custom MCP (Modular Command Protocol) servers. The architecture enables a flexible and scalable multi-agent system where each tool can be hosted independent

27

MCP Sandbox

danstarns

Turn any JavaScript module into a sandboxed MCP (Model Context Protocol) server with automatic reflection and type inference.

5

Emergency Medicare Management MCP Server

manolaz

emergency-medicare-planner-mcp-server

5