Mentor MCP Server

@cyanheads

代码仓库

基本信息

分类

开发工具

许可证

Apache-2.0

传输方式

stdio

作者

cyanheads

关于 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.

#mcp#mentor#llm #llm-agent#ai-mentor#model-context-protocol

Mentor MCP Server 配置

暂无标准配置

该服务器的 README 中没有可解析的 MCP 配置块，请前往代码仓库查看安装说明。

代码仓库

Mentor MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is mentor-mcp-server?

Mentor-mcp-server is a Model Context Protocol server that gives LLM Agents expert second opinions via the Deepseek-reasoning (R1) API. It provides code review, design critique, writing feedback, and idea brainstorming for developers and teams.

How to use mentor-mcp-server?

Clone the repository, install dependencies with npm install, and build with npm run build. Configure it by adding a mentor entry to your MCP client settings with your DEEPSEEK_API_KEY and optional model parameters, then invoke the provided tools (e.g., code_review, design_critique).

Key features of mentor-mcp-server

Comprehensive code reviews with bug detection
UI/UX design critiques and pattern recommendations
Writing feedback and documentation improvement
Feature enhancement brainstorming and feasibility analysis
Security and performance vulnerability assessment
Accessibility evaluation and consistency checks

Use cases of mentor-mcp-server

Review a TypeScript file for bugs, style, and security issues.
Get UI/UX feedback on a web design before implementation.
Improve technical documentation with grammar and clarity suggestions.
Brainstorm enhancements for a user authentication system.
Receive a second opinion on architectural decisions or planning.

常见问题

What API key is required?

A Deepseek API key is required. Set it as the `DEEPSEEK_API_KEY` environment variable.

What model does mentor-mcp-server use by default?

The default model is `deepseek-reasoner`, configurable via the `DEEPSEEK_MODEL` environment variable.

What tools are available?

Four tools: `code_review`, `design_critique`, `writing_feedback`, and `brainstorm_enhancements`. Each accepts specific arguments like file path or text.

How do I configure environment variables?

Add variables `DEEPSEEK_API_KEY`, `DEEPSEEK_MODEL`, `DEEPSEEK_MAX_TOKENS`, `DEEPSEEK_MAX_RETRIES`, and `DEEPSEEK_TIMEOUT` to the `env` block in your MCP client settings.

What are the runtime dependencies?

Node.js and npm. The project is written in TypeScript and uses the Model Context Protocol. All other dependencies are installed via `npm install`.

开发工具分类下的更多 MCP 服务器

Launchdog

Devin Starks

Launch your product from your AI agent. Connect Claude Code, Codex, Cursor or ChatGPT to Launchdog over MCP and your agent drafts the listing, picks a launch week and books it. 50 launches a week, ranked only by human vo

FARPY

mangomunchr

Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

Meticulous

LastPing

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci

Vibgrate MCP

Vibgrate

Query your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up