hygao1024_xingchen_mcp_server

hygao1024_xingchen_mcp_server

by hygao1024
An MCP server implementation for integrating iFlytek workflows with the Model Context Protocol (MCP).

iFlytek Workflow MCP Server

iFlytek Logo

The iFlytek Workflow MCP Server is a powerful implementation of the Model Context Protocol (MCP) designed to integrate seamlessly with iFlytek workflows. It enables intelligent workflow scheduling, making it ideal for various business scenarios.

Overview

The Model Context Protocol (MCP) is an open protocol that facilitates effortless integration between Large Language Model (LLM) applications and external data sources or tools. This project provides a simple yet robust implementation of an MCP server using iFlytek, allowing users to call iFlytek workflows through MCP tools.

Features

Functional Overview

  • Workflow Structure: Composed of multiple nodes, supporting 14 types of nodes (basic, tool, logic, and transformation types).
  • Core Components: Includes a Start Node (user input) and an End Node (output result).
  • Execution Mode: Automatically executes workflows based on predefined sequences and rules without manual intervention.

Core Capabilities

Robust Node Support

  • Supports 14 types of workflow nodes.
  • Enables complex variable I/O for flexible data transmission.

Advanced Orchestration Modes

  • Sequential Execution: Tasks execute in order.
  • Parallel Execution: Multiple tasks run simultaneously.
  • Loop Execution: Handles repetitive tasks.
  • Nested Execution: Embeds sub-workflows within workflows.
  • Utilizes the Hook Mechanism for streaming output.

Multiple Development Paradigms

  • Single-turn, single-branch: Linear execution of simple tasks.
  • Single-turn, multi-branch: Supports branching logic.
  • Single-turn loop: Manages looped tasks.
  • Multi-turn interaction: Supports context memory for dynamic conversations.

Capability Expansion

  • Multi-Model Support: Based on the Model of Models (MoM) architecture, providing multiple model choices for enhanced adaptability.

Usage with MCP Client

Prepare config.yaml

Before using the MCP server, prepare a config.yaml file with your workflow information. Example:

- flow_id: 'flow id'
  name: 'flow name'
  description: 'flow description'
  api_key: 'key:secret'
  params:
    - name: 'input key name'
      type: 'string'
      description: 'input key description'
      required: true

Manual Installation

Add the following to your claude_desktop_config.json or mcp.json file:

{
    "mcpServers": {
        "xingchen-mcp-server": {
            "command": "uvx",
            "args": [
                "--from",
                "git+https://github.com/hygao1024/xingchen-mcp-server",
                "xingchen_mcp_server"
            ],
            "env": {
                "CONFIG_PATH": "$CONFIG_PATH"
            }
        }
    }
}

Example configuration:

{
    "mcpServers": {
        "xingchen-mcp-server": {
            "command": "uvx",
            "args": [
                "--from",
                "git+https://github.com/hygao1024/xingchen-mcp-server",
                "xingchen_mcp_server"
            ],
            "env": {
                "CONFIG_PATH": "/Users/hygao1024/Projects/config.yaml"
            }
        }
    }
}

License

This project is licensed under the MIT License. See the LICENSE file for details.

Resources

Features & Capabilities

Categories
mcp_server model_context_protocol python iflytek workflow_scheduling api_integration

Implementation Details

Stats

0 Views
3 GitHub Stars

Repository Info

hygao1024 Organization

Similar MCP Servers

continuedev_continue by continuedev
25049
21423
9300