mcpserver.so LogoMCPFly
Submit
iFlytek Workflow MCP Server logo

iFlytek Workflow MCP Server

by iFlytek

AI/Automation & WorkflowiFlytekWorkflowAI Agent

This is a simple implementation of an MCP server using iFlytek, enabling the calling of iFlytek workflows through MCP tools. It's designed for effortless integration between LLM applications and external data sources or tools.

View on GitHub

Last updated: N/A

What is iFlytek Workflow MCP Server?

The iFlytek Workflow MCP Server is an implementation of a Model Context Protocol (MCP) server that allows users to integrate iFlytek workflows with LLM applications. It provides a standardized framework to seamlessly provide LLMs with the context they require.

How to use iFlytek Workflow MCP Server?

To use the server, you need to prepare a config.yaml file containing your workflow information (flow ID, name, description, and API Key). You can obtain the workflow ID and authentication information by creating and publishing a workflow on the iFlytek platform. After configuring the config.yaml, you can add the server to your claude_desktop_config.json or mcp.json file and specify the path to your configuration file.

Key features of iFlytek Workflow MCP Server

  • Robust Node Support (14 types)

  • Complex Variable I/O

  • Sequential, Parallel, Loop, and Nested Execution

  • Hook Mechanism for Streaming Output

  • Multi-Model Support (MoM)

Use cases of iFlytek Workflow MCP Server

  • Intelligent workflow scheduling

  • Single-turn, single-branch task execution

  • Single-turn, multi-branch process handling

  • Single-turn loop task management

  • Multi-turn interaction with context memory

FAQ from iFlytek Workflow MCP Server

What is MCP?

The Model Context Protocol (MCP) is an open protocol designed for effortless integration between LLM applications and external data sources or tools.

How do I get the workflow ID and API Key?

You can obtain these by creating and publishing a workflow on the iFlytek platform and binding it to an application.

What types of nodes are supported?

The workflow supports 14 types of nodes, including basic, tool, logic, and transformation types.

What execution modes are supported?

The workflow supports sequential, parallel, loop, and nested execution modes.

What is MoM?

MoM stands for Model of Models, a hybrid application architecture that allows for flexible model combinations at critical workflow stages.