mentor-mcp-server

aljaz/mentor-mcp-server

Fork 0

mirror of https://github.com/aljazceru/mentor-mcp-server.git synced 2025-12-18 06:24:20 +01:00

Commit Graph

Author	SHA1	Message	Date
cyanheads	ed5afdd56c	feat: upgrade to deepseek-reasoner with Chain of Thought - Switch to deepseek-reasoner model for improved analysis - Add Chain of Thought (CoT) reasoning capabilities - Update types to support reasoning_content in responses - Update second-opinion tool to showcase CoT reasoning - Add max_tokens configuration for response length control - Update documentation and examples The deepseek-reasoner model provides step-by-step reasoning before generating final responses, improving the quality and transparency of the analysis. The reasoning is now exposed in tool responses under the 'reasoning' field.	2025-01-25 19:14:26 -08:00
cyanheads	a6edebbf8e	refactor: update Deepseek API implementation - Switch to OpenAI SDK for Deepseek API calls - Add openai package dependency - Update configuration for Deepseek API - Update environment variable examples - Improve error handling for API responses This change improves reliability and maintainability by using the official SDK with proper typing and error handling.	2025-01-25 19:09:41 -08:00
cyanheads	8968a96a98	feat: Initial implementation of mentor-mcp-server Implements a Model Context Protocol (MCP) server that provides AI-powered mentorship and feedback tools. Core Features: - TypeScript implementation with ES modules - MCP server setup with stdio transport - Deepseek API integration with rate limiting and retry logic - Secure environment configuration management - Comprehensive utility functions for file and prompt handling Tools: - second-opinion: Provides critical analysis of user requests - Input validation - Rate limiting - Error handling - Sanitized inputs - Structured prompt templates Infrastructure: - Atomic design directory structure - Type-safe implementation - Proper error handling - Security measures (input sanitization, rate limiting) - Development scripts and configuration Security Features: - API key protection - Input sanitization - Rate limiting - Error message sanitization - Secure file path validation This implementation follows MCP best practices and provides a foundation for adding additional tools: - code-review - design-critique - writing-feedback - brainstorm-enhancements	2025-01-25 18:58:47 -08:00

Author

SHA1

Message

Date

cyanheads

ed5afdd56c

feat: upgrade to deepseek-reasoner with Chain of Thought

- Switch to deepseek-reasoner model for improved analysis
- Add Chain of Thought (CoT) reasoning capabilities
- Update types to support reasoning_content in responses
- Update second-opinion tool to showcase CoT reasoning
- Add max_tokens configuration for response length control
- Update documentation and examples

The deepseek-reasoner model provides step-by-step reasoning before
generating final responses, improving the quality and transparency
of the analysis. The reasoning is now exposed in tool responses
under the 'reasoning' field.

2025-01-25 19:14:26 -08:00

cyanheads

a6edebbf8e

refactor: update Deepseek API implementation

- Switch to OpenAI SDK for Deepseek API calls
- Add openai package dependency
- Update configuration for Deepseek API
- Update environment variable examples
- Improve error handling for API responses

This change improves reliability and maintainability by using the official SDK
with proper typing and error handling.

2025-01-25 19:09:41 -08:00

cyanheads

8968a96a98

feat: Initial implementation of mentor-mcp-server

Implements a Model Context Protocol (MCP) server that provides AI-powered mentorship and feedback tools.

Core Features:
- TypeScript implementation with ES modules
- MCP server setup with stdio transport
- Deepseek API integration with rate limiting and retry logic
- Secure environment configuration management
- Comprehensive utility functions for file and prompt handling

Tools:
- second-opinion: Provides critical analysis of user requests
  - Input validation
  - Rate limiting
  - Error handling
  - Sanitized inputs
  - Structured prompt templates

Infrastructure:
- Atomic design directory structure
- Type-safe implementation
- Proper error handling
- Security measures (input sanitization, rate limiting)
- Development scripts and configuration

Security Features:
- API key protection
- Input sanitization
- Rate limiting
- Error message sanitization
- Secure file path validation

This implementation follows MCP best practices and provides a foundation for adding additional tools:
- code-review
- design-critique
- writing-feedback
- brainstorm-enhancements

2025-01-25 18:58:47 -08:00

3 Commits