funtusov/mcp-server-architect
If you are the rightful owner of mcp-server-architect and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.
A Model Context Protocol server that acts as an AI Software Architect, analyzing codebases to generate Product Requirements Documents (PRDs) and providing reasoning assistance for complex coding tasks.
The mcp-server-architect is a sophisticated Model Context Protocol server designed to function as an AI Software Architect. It leverages a multi-model architecture, primarily using OpenAI's GPT-4o, to analyze codebases and generate comprehensive Product Requirements Documents (PRDs). The server employs an agent-based design, allowing it to autonomously decide which specialized tools to use for each task, such as code reading, web searches, and targeted LLM queries. This enables it to provide advanced reasoning assistance for complex coding challenges. The server is equipped with Logfire instrumentation for monitoring and debugging, and it integrates seamlessly with Claude Code via the Model Context Protocol. Deployment is straightforward, requiring minimal setup with the `uvx mcp-server-architect` command.
Features
- Multi-Model Architecture: Uses OpenAI's GPT-4o for primary agent tasks with access to specialized tools.
- Intelligent Codebase Analysis: Builds comprehensive code context from project files for architectural understanding.
- Agent-Based Design: Uses a smart agent that autonomously decides which tools to employ for each task.
- Tool-Based Processing: Equipped with specialized tools for code reading, web searches, and targeted LLM queries.
- Comprehensive PRD Generation: Creates detailed product requirement documents with architectural insights.
Usages
usage with uv
# Install uv if not already installed curl -LsSf https://astral.sh/uv/install.sh | sh # Run directly with uvx (one-liner) env GEMINI_API_KEY=your_api_key_here EXA_API_KEY=your_exa_key_here uvx mcp-server-architect
usage with pip
# Install the package from PyPI pip install mcp-server-architect # Run it as a command env GEMINI_API_KEY=your_api_key_here mcp-server-architect
usage with claude code local scope
# Local scope (only available to you in the current project) claude mcp add architect -- env GEMINI_API_KEY=your_api_key_here EXA_API_KEY=your_exa_key_here uvx mcp-server-architect
usage with claude code project scope
# Project scope (shared with everyone via .mcp.json) claude mcp add architect -s project -- env GEMINI_API_KEY=your_api_key_here EXA_API_KEY=your_exa_key_here uvx mcp-server-architect
usage with claude code user scope
# User scope (available to you across all projects) claude mcp add architect -s user -- env GEMINI_API_KEY=your_api_key_here EXA_API_KEY=your_exa_key_here uvx mcp-server-architect
Tools
Architect::generate_prd
Generates a Product Requirements Document based on codebase analysis.
Architect::think
Provides reasoning assistance for a stuck LLM on a coding task.
