{"id":26937602,"url":"https://github.com/iflytek/ifly-workflow-mcp-server","last_synced_at":"2026-01-18T04:57:11.890Z","repository":{"id":284159493,"uuid":"953998052","full_name":"iflytek/ifly-workflow-mcp-server","owner":"iflytek","description":null,"archived":false,"fork":false,"pushed_at":"2025-03-24T12:55:27.000Z","size":41,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":3,"default_branch":"main","last_synced_at":"2025-03-24T13:41:32.350Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/iflytek.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2025-03-24T12:08:53.000Z","updated_at":"2025-03-24T12:55:31.000Z","dependencies_parsed_at":"2025-03-24T13:41:36.421Z","dependency_job_id":"257861eb-ce59-4f08-b099-c1ddbd9bccd6","html_url":"https://github.com/iflytek/ifly-workflow-mcp-server","commit_stats":null,"previous_names":["iflytek/ifly-workflow-mcp-server"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iflytek%2Fifly-workflow-mcp-server","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iflytek%2Fifly-workflow-mcp-server/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iflytek%2Fifly-workflow-mcp-server/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/iflytek%2Fifly-workflow-mcp-server/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/iflytek","download_url":"https://codeload.github.com/iflytek/ifly-workflow-mcp-server/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246819781,"owners_count":20839095,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-04-02T13:15:23.983Z","updated_at":"2026-01-18T04:57:11.871Z","avatar_url":"https://github.com/iflytek.png","language":"Python","funding_links":[],"categories":["AI Platforms","Table of Contents","Community Servers","🤖 AI/ML","Other Tools and Integrations","Task and Project Management","AI \u0026 Machine Learning"],"sub_categories":["RAG","Workflow Automation","How to Submit"],"readme":"\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://xinghuo.xfyun.cn/botcenter/createbot\"\u003e\u003cimg src=\"https://openres.xfyun.cn/xfyundoc/2024-04-26/1396db8a-313b-40f5-be2a-5babcad9cd64/1714102184743/sparklogo.svg\"\u003e\u003c/a\u003e\n\u003c/p\u003e\n\u003cp align=\"center\"\u003e\n    The fastest way to build workflows with an AI agent platform!\n\u003c/p\u003e\n\u003cp align=\"center\"\u003e\n  \u003ca href=\"https://github.com/iflytek/ifly-workflow-mcp-server/blob/main/LICENSE\" target=\"_blank\"\u003e\n      \u003cimg src=\"https://img.shields.io/static/v1?label=license\u0026message=MIT licensed\u0026color=white\" alt=\"License\"\u003e\n  \u003c/a\u003e |\n  \u003ca href=\"https://xinghuo.xfyun.cn/botcenter/createbot\" target=\"_blank\"\u003e\n      Docs\n  \u003c/a\u003e |\n  \u003ca href=\"https://xinghuo.xfyun.cn/botcenter/createbot\" target=\"_blank\"\u003e\n      Homepage\n  \u003c/a\u003e\n\u003c/p\u003e\n\n# iFlytek Workflow MCP Server\n\n[The Model Context Protocol (MCP)](https://modelcontextprotocol.io/introduction) 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.\n\nThis a simple implementation of an MCP server using iFlytek. It enables calling iFlytek workflows through MCP tools.\n\n## Features\n\n### Functional Overview\n\nThis system is built on the iFlytek MCP server and enables intelligent workflow scheduling, making it suitable for various business scenarios.\n\n- **Workflow Structure**: Composed of multiple nodes, supporting 14 types of nodes (including basic, tool, logic, and transformation types).\n- **Core Components**: By default, the workflow includes a **Start Node** (user input) and an **End Node** (output result).\n- **Execution Mode**: Once triggered, the workflow executes automatically according to predefined sequences and rules, requiring no manual intervention.\n\n### Core Capabilities\n\n#### **Robust Node Support**\n\n- 14 types of workflow nodes to meet diverse business requirements.\n- Supports **complex variable I/O**, enabling flexible data transmission.\n\n#### **Advanced Orchestration Modes**\n\n- **Sequential Execution**: Tasks execute one after another in order.\n- **Parallel Execution**: Multiple tasks run simultaneously to enhance efficiency.\n- **Loop Execution**: Supports iterative loops for handling repetitive tasks.\n- **Nested Execution**: Allows embedding sub-workflows within workflows, improving reusability.\n- Utilizes the **Hook Mechanism** to enable **streaming output**, ensuring real-time processing.\n\n#### **Multiple Development Paradigms**\n\n- **Single-turn, single-branch**: Linear execution of simple tasks.\n- **Single-turn, multi-branch**: Supports branching logic to handle complex processes.\n- **Single-turn loop**: Manages looped tasks to enhance automation.\n- **Multi-turn interaction**: Supports context memory for dynamic conversations.\n\n### Capability Expansion\n\n- **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.\n\n\n\n## Usage with MCP client\n\n### Prepare config.yaml\n\nBefore using the mcp server, you should prepare a config.yaml to save your workflow info. The example config like this:\n\n```yaml\n- flow_id: 'flow id'              # required\n  name: 'flow name'               # optional, if not set, obtain the name from the cloud.\n  description: 'flow description' # optional, if not set, obtain the description from the cloud.\n  api_key: 'API Key:API Secret'   # required\n```\n\n#### Get workflow authentication information\n1. [Create a bot](https://xinghuo.xfyun.cn/botcenter/createbot)\n![](./images/create_workflow.png)\n\n2. Publish a workflow\n- **Step 1.** Debug the workflow you just created.\n- **Step 2.** Engage in a conversation with your workflow and ensure the conversation is successful.\n- **Step 3.** You can now click the publish button.\n![](./images/debug_workflow.png)\n- **Step 4.** Select \"Publish as API\" and click the \"Configure\" button.\n![](./images/publish_workflow.png)\n- **Step 5.** Select the application you need to bind and bind it. Now you can retrieve the corresponding workflow ID and authentication information. Enjoy!\n![](./images/bind_app.png)\n\u003e **Note**: If you find that you are unable to select an app, you can go to https://www.xfyun.cn to apply.\n### Manual Installation\n\nTo add a persistent client, add the following to your `claude_desktop_config.json` or `mcp.json` file:\n\n```json\n{\n    \"mcpServers\": {\n        \"ifly-workflow-mcp-server\": {\n            \"command\": \"uvx\",\n            \"args\": [\n                \"--from\",\n                \"git+https://github.com/iflytek/ifly-workflow-mcp-server\",\n                \"ifly_workflow_mcp_server\"\n            ],\n            \"env\": {\n                \"CONFIG_PATH\": \"$CONFIG_PATH\"\n            }\n        }\n    }\n}\n```\n\n\n\nExample config:\n\n```json\n{\n    \"mcpServers\": {\n        \"ifly-workflow-mcp-server\": {\n            \"command\": \"uvx\",\n            \"args\": [\n                \"--from\",\n                \"git+https://github.com/iflytek/ifly-workflow-mcp-server\",\n                \"ifly_workflow_mcp_server\"\n            ],\n            \"env\": {\n                \"CONFIG_PATH\": \"/Users/hygao1024/Projects/config.yaml\"\n            }\n        }\n    }\n}\n```\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fiflytek%2Fifly-workflow-mcp-server","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fiflytek%2Fifly-workflow-mcp-server","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fiflytek%2Fifly-workflow-mcp-server/lists"}