Mentor MCP

v1.0.0Coding Agentsstable

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.

ai-mentorllmllm-agentmcpmentor
Share:
31
Stars
0
Downloads
0
Weekly
0/5

What is Mentor MCP?

Mentor MCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 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 bra...

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.

This server falls under the Coding Agents category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • A Model Context Protocol server providing LLM Agents a secon

Use Cases

Code review feedback
Design critique
AI-powered brainstorming
cyanheads

Maintainer

LicenseApache 2.0
Languagetypescript
Versionv1.0.0
UpdatedMar 26, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx mentor

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use Mentor MCP

Mentor MCP Server gives LLM agents a second opinion by routing review requests through DeepSeek's Reasoning R1 model, a chain-of-thought reasoner that is particularly strong at structured critique. It exposes four tools — code review, design critique, writing feedback, and idea brainstorming — so agents or developers can request expert-level analysis on any artifact without leaving their current AI environment. The server acts as a reasoning layer on top of the primary model, catching issues that generalist LLMs tend to miss in security, architectural coherence, and documentation clarity.

Prerequisites

  • Node.js 18 or higher installed
  • A DeepSeek API key (sign up at platform.deepseek.com)
  • An MCP-compatible client such as Claude Desktop, Claude Code, or Cursor
  • npm or git available to install from source
1

Clone the repository

Mentor MCP Server is installed from source. Clone the repository and enter the project directory.

git clone https://github.com/cyanheads/mentor-mcp-server.git
cd mentor-mcp-server
2

Install dependencies and build

Install npm dependencies and compile the TypeScript source.

npm install && npm run build
3

Set required environment variables

Export your DeepSeek API key and optionally set the model and token limits. DEEPSEEK_API_KEY is required; the model defaults to deepseek-reasoner.

export DEEPSEEK_API_KEY=your_deepseek_api_key_here
export DEEPSEEK_MODEL=deepseek-reasoner
export DEEPSEEK_MAX_TOKENS=8192
4

Configure your MCP client

Add the mentor server to your MCP client configuration, passing the API key as an environment variable.

5

Test the server

Ask your AI assistant to review a code snippet. The request will be routed through DeepSeek R1 and a structured critique will be returned.

Mentor MCP Examples

Client configuration

Add Mentor MCP Server to claude_desktop_config.json with your DeepSeek API key passed as an environment variable.

{
  "mcpServers": {
    "mentor": {
      "command": "node",
      "args": ["/path/to/mentor-mcp-server/dist/index.js"],
      "env": {
        "DEEPSEEK_API_KEY": "your_deepseek_api_key_here",
        "DEEPSEEK_MODEL": "deepseek-reasoner",
        "DEEPSEEK_MAX_TOKENS": "8192"
      }
    }
  }
}

Prompts to try

Use these prompts to get deep, reasoning-model-powered reviews of code, designs, writing, and ideas.

- "Review this TypeScript authentication module for security vulnerabilities and code quality"
- "Critique this REST API design for consistency and scalability issues"
- "Give feedback on this technical documentation for clarity and completeness"
- "Brainstorm enhancements for a user authentication system that currently only supports email/password"
- "Review this React dashboard component for accessibility and performance problems"

Troubleshooting Mentor MCP

Requests fail with a 401 Unauthorized error from DeepSeek

Verify that DEEPSEEK_API_KEY is set correctly in the MCP client's env block. Keys from platform.deepseek.com must be active and have sufficient credits. Test independently with: curl -H 'Authorization: Bearer YOUR_KEY' https://api.deepseek.com/models

Responses time out on long code reviews

Increase the DEEPSEEK_TIMEOUT environment variable (default is 30000ms). For large files, set it to 120000 or higher: export DEEPSEEK_TIMEOUT=120000

The build step fails with TypeScript errors

Ensure you are using Node.js 18 or higher. Run 'node --version' to check. Delete node_modules and package-lock.json, then re-run 'npm install && npm run build'.

Frequently Asked Questions about Mentor MCP

What is Mentor MCP?

Mentor MCP is a Model Context Protocol (MCP) server that 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. It connects AI assistants to external tools and data sources through a standardized interface.

How do I install Mentor MCP?

Follow the installation instructions on the Mentor MCP GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with Mentor MCP?

Mentor MCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is Mentor MCP free to use?

Yes, Mentor MCP is open source and available under the Apache 2.0 license. You can use it freely in both personal and commercial projects.

Browse More Coding Agents MCP Servers

Explore all coding agents servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "mentor": { "command": "npx", "args": ["-y", "mentor"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use Mentor MCP?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides