mentor-mcp-server
A Model Context Protocol server providing LLM Agents a second opinion via AI-powered Deepseek-Reasoning (R1) mentorship capabilities, including code review, design critique, writing feedback, and idea brainstorming through the Deepseek API. Set your LLM Agent up for success with expert second opinions and actionable insights.
Model Context Protocol
The Model Context Protocol (MCP) enables communication between:
- Clients: Claude Desktop, IDEs, and other MCP-compatible clients
- Servers: Tools and resources for task management and automation
- LLM Agents: AI models that leverage the server's capabilities
Table of Contents
Features
Code Analysis
- Comprehensive code reviews
- Bug detection and prevention
- Style and best practices evaluation
- Performance optimization suggestions
- Security vulnerability assessment
Design & Architecture
- UI/UX design critiques
- Architectural diagram analysis
- Design pattern recommendations
- Accessibility evaluation
- Consistency checks
Content Enhancement
- Writing feedback and improvement
- Grammar and style analysis
- Documentation review
- Content clarity assessment
- Structural recommendations
Strategic Planning
- Feature enhancement brainstorming
- Second opinions on approaches
- Innovation suggestions
- Feasibility analysis
- User value assessment
Installation
Configuration
Add to your MCP client settings:
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
Design Critique
Writing Feedback
Feature Enhancement
Examples
Detailed examples of each tool's usage and output can be found in the examples directory:
- Second Opinion Example - Analysis of authentication system requirements
- Code Review Example - Detailed TypeScript code review with security and performance insights
- Design Critique Example - Comprehensive UI/UX feedback for a dashboard design
- Writing Feedback Example - Documentation improvement suggestions
- Brainstorm Enhancements Example - Feature ideation with implementation details
Each example includes the request format and sample response, demonstrating the tool's capabilities and output structure.
Development
Project Structure
License
Apache License 2.0. See LICENSE for more information.
remote-capable server
The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.
使用 Deepseek API 为 LLM 代理提供 AI 驱动的指导,以进行代码审查、设计批评、写作反馈和头脑风暴,从而提高各种开发和战略规划任务的产出。
Related Resources
Related MCP Servers
- AsecurityAlicenseAqualityEnables integration of Perplexity's AI API with LLMs, delivering advanced chat completion by utilizing specialized prompt templates for tasks like technical documentation, code review, and API documentation.Last updated -16448JavaScriptMIT License
- -securityAlicense-qualityEnhances LLM applications with deep autonomous web research capabilities, delivering higher quality information than standard search tools by exploring and validating numerous trusted sources.Last updated -224PythonMIT License
- AsecurityAlicenseAqualityUnleashes LLM-powered agents to autonomously execute and debug web apps directly in your code editor, with features like webapp navigation, network traffic capture, and console error collection.Last updated -21,143PythonApache 2.0
- AsecurityAlicenseAqualityA coding agent toolkit that transforms LLMs into coding assistants capable of working directly on your codebase with semantic code retrieval and editing tools, providing IDE-like capabilities without requiring API subscriptions.Last updated -33PythonMIT License