iFlytek Workflow MCP Server
@iflytek
About iFlytek Workflow MCP Server
This a simple implementation of an MCP server using iFlytek. It enables calling iFlytek workflows through MCP tools.
Config
Add this server to your MCP-compatible client using the configuration below.
{
"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": ""
}
}
}
}Tools
No tools detected
Fetch the live tool list by running this server in a temporary sandbox using the button above.
Overview
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
Basic information
More Reasoning MCP servers
NeoCoder: Neo4j-Guided AI Coding Workflow
angrysky56An MCP server allowing AI assistants to use a Neo4j knowledge graph as their primary, dynamic instruction manual and long term project memory with adaptive templating and autonomous tool development tools.
quarkus-langchain4j-workshop
quarkusioQuarkus LangChain4J Workshop that demonstrates both single AI service capabilities and Agentic AI orchestration
Proplan Mcp
King-ProplanMCP server that gives Claude persistent project memory — roadmap, session history, and codebase context. Type continue and Claude picks up exactly where you left off
Agentic MCP Client
peakmojoA standalone agent runner that executes tasks using MCP (Model Context Protocol) tools via Anthropic Claude, AWS BedRock and OpenAI APIs. It enables AI agents to run autonomously in cloud environments and interact with various systems securely.
Agenticstore — The Open Source Standard For Local Mcp Tooling
agenticstoreAgenticStore: The secure toolkit for AI agents. Instantly equip Claude Desktop, Cursor, and Windsurf with 27+ MCP tools, persistent memory, and SearXNG search, all protected by a built-in PII prompt firewall to protect your data from being exposed to AI agents.
Comments