AIbase
EN
Explore
AI Expert Workflow
A

AI Expert Workflow

AI Expert Workflow MCP is a model context protocol server based on the OpenRouter API. Through three AI expert roles of product manager, UX designer, and software architect, it provides a complete workflow solution from product planning to technical implementation. The project supports independent generation of PRD documents and can also be integrated with Task Master for task management.
Artificial intelligence chatbotsDeveloper tools#AI workflow#Product planning#Technical architecture#PRD generation.TypeScript
2.5 points
29

What is AI Expert Workflow MCP?

This is an intelligent workflow system based on the OpenRouter API. It simulates three professional roles (product manager, UX designer, and software architect) to have conversations with users and gradually transform product ideas into complete technical solution documents. The system will guide users to improve all aspects of product design and finally generate professional-level documents.

How to use AI Expert Workflow?

Simply describe your product idea in natural language, and the system will guide you to improve product details through multiple rounds of conversations. When the information collection is complete, you can generate a professional document with one click. The whole process is as natural as collaborating with a real expert team.

Applicable scenarios

It is especially suitable for entrepreneurs, product managers, and developers to conduct system planning in the early stage of projects. Whether it is a mobile application, website, or complex system, professional-level planning documents can be obtained.

Main features

Collaboration of three AI expertsProduct manager defines requirements → UX designer plans the experience → Software architect designs the technical solution, fully covering the entire product development process.
Intelligent conversation guidanceGuide users to improve product details step by step through natural conversations to ensure that no important links are missed.
Professional document generationAutomatically generate PRD (Product Requirement Document), UX design document, and technical architecture document in line with industry standard formats.
Multi-model supportSupport multiple large models such as GPT - 4, Claude, and Gemini through OpenRouter. You can choose the most suitable AI according to your needs.

Advantages and limitations

Advantages
Fully cover the entire product development lifecycle
Obtain professional-level solutions without professional knowledge
Conversational interaction lowers the usage threshold
Support exporting documents in multiple formats
Flexibly choose different AI models
Limitations
Requires an OpenRouter API key
Complex projects may require multiple rounds of conversations
Technical solutions need to be reviewed by professionals

How to use

Install the tool
Globally install AI Expert Workflow via npm.
Set the API key
Obtain the OpenRouter API key and configure the environment variable.
Start the conversation
Run the command to start a conversation with AI experts and describe your product idea.
Generate the document
When the conversation is completed, enter the document generation instruction to obtain a professional solution.

Usage examples

Recipe app planningThe user wants to develop an app that can recommend recipes based on existing ingredients.
E-commerce membership system designDesign a membership points and level system for an e-commerce platform.

Frequently Asked Questions

Do I need programming knowledge to use it?
Can the generated documents be directly used for development?
Does it support Chinese conversations?
How to choose the most suitable AI model?

Related resources

OpenRouter model list
View all available AI models and their features.
GitHub repository
Project source code and latest updates.
Task Master integration guide
How to transform product documents into development tasks.
Installation
Copy the following command to your Client for configuration
{
     "mcpServers": {
       "ai-expert-workflow": {
         "command": "npx",
         "args": ["-y", "ai-expert-workflow-mcp"],
         "env": {
           "OPENROUTER_API_KEY": "YOUR_OPENROUTER_API_KEY_HERE",
           "OPENROUTER_MODEL": "tngtech/deepseek-r1t-chimera:free",
           "MAX_TOKENS": 8000,
           "TEMPERATURE": 0.7
         }
       },
       "taskmaster-ai": {
         "command": "npx",
         "args": ["-y", "task-master-ai"],
         "env": {
           "ANTHROPIC_API_KEY": "YOUR_ANTHROPIC_API_KEY_HERE",
           "PERPLEXITY_API_KEY": "YOUR_PERPLEXITY_API_KEY_HERE",
           "MODEL": "claude-3-sonnet-20240229",
           "PERPLEXITY_MODEL": "sonar-pro",
           "MAX_TOKENS": 64000,
           "TEMPERATURE": 0.2,
           "DEFAULT_SUBTASKS": 5,
           "DEFAULT_PRIORITY": "medium"
         }
       }
     }
   }

{
  "mcpServers": {
    "ai-expert-workflow": {
      "command": "node",
      "args": ["dist/index.js"],
      "cwd": "${workspaceFolder}",
      "env": {
        "OPENROUTER_API_KEY": "${env:OPENROUTER_API_KEY}",
        "OPENROUTER_MODEL": "tngtech/deepseek-r1t-chimera:free",
        "MAX_TOKENS": 4000,
        "TEMPERATURE": 0.7,
        "MCP_TIMEOUT": "120000",
        "DEBUG": "mcp"
      }
    },
    "taskmaster-ai": {
      "command": "npx",
      "args": ["-y", "task-master-ai"],
      "env": {
        "OPENROUTER_API_KEY": "${env:OPENROUTER_API_KEY}",
        "OPENROUTER_MODEL": "openai/gpt-4-turbo",
        "MAX_TOKENS": 8000,
        "TEMPERATURE": 0.7,
        "DEFAULT_SUBTASKS": 5,
        "DEFAULT_PRIORITY": "medium"
      }
    }
  }
}

"mcpServers": {
     "taskmaster-ai": {
       "command": "npx",
       "args": ["-y", "task-master-ai"],
       "env": {
         "ANTHROPIC_API_KEY": "YOUR_ANTHROPIC_API_KEY_HERE",
         "MODEL": "claude-3-sonnet-20240229"
       }
     }
   }
Note: Your key is sensitive information, do not share it with anyone.
N
Notte Browser
Certified
Notte is an open-source full-stack network AI agent framework that provides browser sessions, automated LLM-driven agents, web page observation and operation, credential management, etc. It aims to transform the Internet into an agent-friendly environment and reduce the cognitive burden of LLMs by describing website structures in natural language.
666
4.5 points
S
Search1api
The Search1API MCP Server is a server based on the Model Context Protocol (MCP), providing search and crawling functions, and supporting multiple search services and tools.
TypeScript
348
4 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
838
4.3 points
B
Bing Search MCP
An MCP server for integrating Microsoft Bing Search API, supporting web page, news, and image search functions, providing network search capabilities for AI assistants.
Python
234
4 points
M
MCP Alchemy
Certified
MCP Alchemy is a tool that connects Claude Desktop to multiple databases, supporting SQL queries, database structure analysis, and data report generation.
Python
335
4.2 points
P
Postgresql MCP
A PostgreSQL database MCP service based on the FastMCP library, providing CRUD operations, schema inspection, and custom SQL query functions for specified tables.
Python
117
4 points
M
MCP Scan
MCP-Scan is a security scanning tool for MCP servers, used to detect common security vulnerabilities such as prompt injection, tool poisoning, and cross-domain escalation.
Python
625
5 points
A
Agentic Radar
Agentic Radar is a security scanning tool for analyzing and assessing agentic systems, helping developers, researchers, and security experts understand the workflows of agentic systems and identify potential vulnerabilities.
Python
562
5 points
Featured MCP Services
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
838
4.3 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
1.7K
5 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
152
4.5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
100
4.3 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
6.7K
4.5 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
573
5 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
5.2K
4.7 points
M
Minimax MCP Server
The MiniMax Model Context Protocol (MCP) is an official server that supports interaction with powerful text-to-speech, video/image generation APIs, and is suitable for various client tools such as Claude Desktop and Cursor.
Python
761
4.8 points
AIbase
Zhiqi Future, Your AI Solution Think Tank
English简体中文繁體中文にほんご
© 2025AIbase