mentor

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.

Installation

Run this command in your terminal to add the MCP server to Claude Code.

Run in terminal:

View docs

Command

claude mcp add --transport stdio cyanheads-mentor-mcp-server node build/index.js \
  --env DEEPSEEK_MODEL="deepseek-reasoner" \
  --env DEEPSEEK_API_KEY="your_api_key" \
  --env DEEPSEEK_TIMEOUT="30000" \
  --env DEEPSEEK_MAX_TOKENS="8192" \
  --env DEEPSEEK_MAX_RETRIES="3"

How to use

mentor is an MCP server that provides AI-powered second-opinion mentorship for LLM agents. It leverages the Deepseek API to offer expert guidance across code reviews, design critiques, writing feedback, and brainstorming enhancements. With MCP, clients can request specialized analyses from the mentor server, which can examine source code, design documents, writing samples, or feature ideas and return actionable insights, recommendations, and potential improvements. The server exposes tools under the mentor name, such as code_review, design_critique, writing_feedback, and brainstorm_enhancements, each designed to handle structured inputs and return structured feedback suitable for integration into development workflows.

How to install

Prerequisites:

Node.js and npm installed on your system
Access to the repository source for mentor-mcp-server

Installation steps:

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

Run the server (development or production as desired)

npm run start

(Optional) Development workflow

npm run dev

Notes:

Ensure your environment has the required API key and model details if you plan to use Deepseek integration.
The README indicates the server is TypeScript-based and uses npm scripts for common tasks like build, start, and dev.

Additional notes

Tips and considerations:

Ensure DEEPSEEK_API_KEY is kept secure and not committed to version control.
The MCP configuration example uses the server’s build/index.js entry point; ensure the build step outputs to that path.
If you modify environment variables, update the MCP client configuration accordingly.
Common issues may include network timeouts or API quota limits; adjust DEEPSEEK_TIMEOUT or token limits as needed.
The tools (code_review, design_critique, writing_feedback, brainstorm_enhancements) expect structured JSON/XML-like argument payloads as shown in the README examples.
When integrating with MCP clients, ensure the command and arguments align with how your deployment environment executes the Node server.

Related MCP Servers

obsidian

383

Obsidian Knowledge-Management MCP (Model Context Protocol) server that enables AI agents and development tools to interact with an Obsidian vault. It provides a comprehensive suite of tools for reading, writing, searching, and managing notes, tags, and frontmatter, acting as a bridge to the Obsidian Local REST API plugin.

mcp-manager

285

simple web ui to manage mcp (model context protocol) servers in the claude app

Matryoshka

106

MCP server for token-efficient large document analysis via the use of REPL state

codemesh

The Self-Improving MCP Server - Agents write code to orchestrate multiple MCP servers with intelligent TypeScript execution and auto-augmentation

toolkit

A Model Context Protocol server providing LLM Agents with system utilities and tools, including IP geolocation, network diagnostics, system monitoring, cryptographic operations, and QR code generation.

mcp-agent

Lightweight, focused utilities to manage connections and execute MCP tools with minimal integration effort. Use it to directly call tools or build simple agents within your current architecture.