📌Overview

Purpose: To provide LLM Agents with AI-powered mentorship capabilities, enabling comprehensive support in areas like code review, design critique, writing feedback, and idea brainstorming through the Deepseek API.

Overview: The mentor-mcp-server serves as a Model Context Protocol (MCP) server that allows seamless communication between various clients and LLM agents. It harnesses advanced Deepseek reasoning to offer expert second opinions, facilitating better decision-making processes and enhancing the productivity of AI models.

Key Features:

• Code Analysis: Delivers thorough code reviews, bug detection, performance optimization suggestions, and security assessments to improve code quality.

• Design & Architecture: Offers critiques on UI/UX designs, architectural evaluations, and design pattern recommendations to ensure effective and user-friendly system architectures.

• Content Enhancement: Provides feedback on writing, grammar, documentation review, and structural suggestions to improve clarity and coherence in content.

• Strategic Planning: Facilitates brainstorming for feature enhancements, providing innovative suggestions and feasibility analyses for new ideas.

---

mentor-mcp-server

A Model Context Protocol server providing LLM Agents AI-powered Deepseek-Reasoning (R1) mentorship capabilities, including code review, design critique, writing feedback, and idea brainstorming through the Deepseek API.

Model Context Protocol

The Model Context Protocol (MCP) enables communication between:

• Clients: MCP-compatible clients like Claude Desktop and IDEs.
• Servers: Tools and resources for task management and automation.
• LLM Agents: AI models leveraging the server's capabilities.

Table of Contents

• Features
• Installation
• Configuration
• Tools
• Examples
• Development
• Project Structure
• License

Features

Code Analysis

• Comprehensive code reviews
• Bug detection and prevention
• Style and best practices evaluation

Design & Architecture

• UI/UX design critiques
• Architectural diagram analysis

Content Enhancement

• Writing feedback and improvement
• Documentation review

Strategic Planning

• Second opinions on approaches
• Feasibility analysis

Installation

# Clone the repository
git clone git@github.com:cyanheads/mentor-mcp-server.git
cd mentor-mcp-server

# Install dependencies
npm install

# Build the project
npm run build

Configuration

Add to your MCP client settings:

{
  "mcpServers": {
    "mentor": {
      "command": "node",
      "args": ["build/index.js"],
      "env": {
        "DEEPSEEK_API_KEY": "your_api_key",
        "DEEPSEEK_MODEL": "deepseek-reasoner",
        "DEEPSEEK_MAX_TOKENS": "8192",
        "DEEPSEEK_MAX_RETRIES": "3",
        "DEEPSEEK_TIMEOUT": "30000"
      }
    }
  }
}

Environment Variables

Variable	Required	Default	Description
DEEPSEEK_API_KEY	Yes	-	Your Deepseek API key
DEEPSEEK_MODEL	Yes	deepseek-reasoner	Deepseek model name
DEEPSEEK_MAX_TOKENS	No	8192	Maximum tokens per request
DEEPSEEK_MAX_RETRIES	No	3	Number of retry attempts
DEEPSEEK_TIMEOUT	No	30000	Request timeout (ms)

Tools

Code Review

<use_mcp_tool>
<server_name>mentor-mcp-server</server_name>
<tool_name>code_review</tool_name>
<arguments>
{
  "file_path": "src/app.ts",
  "language": "typescript"
}
</arguments>
</use_mcp_tool>

Design Critique

<use_mcp_tool>
<server_name>mentor-mcp-server</server_name>
<tool_name>design_critique</tool_name>
<arguments>
{
  "design_document": "path/to/design.fig",
  "design_type": "web UI"
}
</arguments>
</use_mcp_tool>

Writing Feedback

<use_mcp_tool>
<server_name>mentor-mcp-server</server_name>
<tool_name>writing_feedback</tool_name>
<arguments>
{
  "text": "Documentation content...",
  "writing_type": "documentation"
}
</arguments>
</use_mcp_tool>

Feature Enhancement

<use_mcp_tool>
<server_name>mentor-mcp-server</server_name>
<tool_name>brainstorm_enhancements</tool_name>
<arguments>
{
  "concept": "User authentication system"
}
</arguments>
</use_mcp_tool>

Examples

Find detailed examples of each tool's usage in the examples directory, including:

• 1
• 1
• 1
• 1
• 1

Development

# Build TypeScript code
npm run build

# Start the server
npm run start

# Development with watch mode
npm run dev

# Clean build artifacts
npm run clean

Project Structure

src/
├── api/         # API integration modules
├── tools/       # Tool implementations
│   ├── second-opinion/
│   ├── code-review/
│   ├── design-critique/
│   ├── writing-feedback/
│   └── brainstorm-enhancements/
├── types/       # TypeScript type definitions
├── utils/       # Utility functions
├── config.ts    # Server configuration
├── index.ts     # Entry point
└── server.ts    # Main server implementation

License

Apache License 2.0. See LICENSE for more information.