iFlytek Workflow

What is ifly-workflow-mcp-server?

The ifly-workflow-mcp-server is a simple implementation of a Model Context Protocol (MCP) server specifically designed to integrate with iFlytek workflows. It allows users to call and manage iFlytek workflows through MCP tools, providing a standardized framework for LLM applications to access external data sources and tools.

How to use ifly-workflow-mcp-server?

To use the ifly-workflow-mcp-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 authentication information by creating and publishing a bot on the iFlytek platform, ensuring the workflow is debugged, conversed with successfully, and published as an API. After configuring your workflow, you can manually install the MCP client by adding the server configuration to your claude_desktop_config.json or mcp.json file, specifying the command, arguments, and environment variables, including the path to your config.yaml.

Key Features of ifly-workflow-mcp-server

Functional Overview

• Workflow Structure: Workflows are composed of multiple nodes, supporting 14 types including basic, tool, logic, and transformation types. Each workflow includes a Start Node (user input) and an End Node (output result).
• Execution Mode: Workflows execute automatically according to predefined sequences and rules once triggered, requiring no manual intervention.

Core Capabilities

• Robust Node Support: Offers 14 types of workflow nodes to meet diverse business requirements, supporting complex variable I/O for flexible data transmission.
• Advanced Orchestration Modes: Supports sequential, parallel, loop, and nested execution. It also utilizes a Hook Mechanism for streaming output, ensuring real-time processing.
• Multiple Development Paradigms: Accommodates single-turn (single-branch, multi-branch, loop) and multi-turn interaction (with context memory for dynamic conversations).

Capability Expansion

• Multi-Model Support: Based on the Model of Models (MoM) hybrid application architecture, providing multiple model choices at critical workflow stages for flexible model combinations and improved task adaptability.

Use Cases of ifly-workflow-mcp-server

The ifly-workflow-mcp-server is suitable for various business scenarios requiring intelligent workflow scheduling and integration with LLM applications. Potential use cases include:

• Automating Business Processes: Streamlining complex operations by defining workflows with various node types and execution modes.
• AI Agent Development: Building and deploying AI agents that can interact with external data and tools through iFlytek workflows.
• Data Processing and Transformation: Utilizing the robust node support and variable I/O for advanced data manipulation within workflows.
• Real-time Interactions: Leveraging streaming output via the Hook Mechanism for applications requiring immediate responses.
• Scalable AI Solutions: Combining different models through the MoM architecture to create adaptable and powerful AI solutions.

FAQ from the Project

Q: How do I get workflow authentication information? A: You need to create a bot on the iFlytek platform, debug and successfully converse with your workflow, and then publish it as an API. During the publishing process, you can select an application to bind and retrieve the corresponding workflow ID and authentication information. If you cannot select an app, you may need to apply at https://www.xfyun.cn.

Q: What is the Model Context Protocol (MCP)? A: The Model Context Protocol (MCP) is an open protocol designed for effortless integration between LLM applications and external data sources or tools. It offers a standardized framework to seamlessly provide LLMs with the context they require.

iFlytek Workflow MCP Server

The Model Context Protocol (MCP) is an open protocol designed for effortless integration between LLM applications and external data sources or tools, offering a standardized framework to seamlessly provide LLMs with the context they require.

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

Features

Functional Overview

This system is built on the iFlytek MCP server and enables intelligent workflow scheduling, making it suitable for various business scenarios.

• Workflow Structure: Composed of multiple nodes, supporting 14 types of nodes (including basic, tool, logic, and transformation types).
• Core Components: By default, the workflow includes a Start Node (user input) and an End Node (output result).
• Execution Mode: Once triggered, the workflow executes automatically according to predefined sequences and rules, requiring no manual intervention.

Core Capabilities

Robust Node Support

• 14 types of workflow nodes to meet diverse business requirements.
• Supports complex variable I/O, enabling flexible data transmission.

Advanced Orchestration Modes

• Sequential Execution: Tasks execute one after another in order.
• Parallel Execution: Multiple tasks run simultaneously to enhance efficiency.
• Loop Execution: Supports iterative loops for handling repetitive tasks.
• Nested Execution: Allows embedding sub-workflows within workflows, improving reusability.
• Utilizes the Hook Mechanism to enable streaming output, ensuring real-time processing.

Multiple Development Paradigms

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

Capability Expansion

• Multi-Model Support: Based on the Model of Models (MoM) hybrid application architecture, providing multiple model choices at critical workflow stages. This allows for flexible model combinations, improving task adaptability.

Usage with MCP client

Prepare config.yaml

Before using the mcp server, you should prepare a config.yaml to save your workflow info. The example config like this:

- flow_id: 'flow id'              # required
  name: 'flow name'               # optional, if not set, obtain the name from the cloud.
  description: 'flow description' # optional, if not set, obtain the description from the cloud.
  api_key: 'API Key:API Secret'   # required

Get workflow authentication information

1. Create a bot

2. Publish a workflow

• Step 1. Debug the workflow you just created.
• Step 2. Engage in a conversation with your workflow and ensure the conversation is successful.
• Step 3. You can now click the publish button.
• Step 4. Select "Publish as API" and click the "Configure" button.
• Step 5. Select the application you need to bind and bind it. Now you can retrieve the corresponding workflow ID and authentication information. Enjoy!

Note: If you find that you are unable to select an app, you can go to https://www.xfyun.cn to apply.

Manual Installation

To add a persistent client, add the following to your claude_desktop_config.json or mcp.json file:

{
    "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": "$CONFIG_PATH"
            }
        }
    }
}

Example config:

{
    "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": "/Users/hygao1024/Projects/config.yaml"
            }
        }
    }
}