code_reviewLABSCO SUMMARY
Its value is that the reviewer is a different model.
An agent asked to check its own work tends to agree with itself; routing the review to Deepseek's reasoning model breaks that loop, which is the entire premise. Costs land on your Deepseek account per call, and the timeout defaults to 30000 milliseconds — worth raising before you send a long file for review.
What it is
An MCP server that gives an LLM agent access to a different model for review work. Each tool frames a specific kind of critique — code, design, prose, or feature ideas — and routes it to Deepseek's reasoning model through the Deepseek API, so the answer comes from a second model rather than the one already in the conversation.
What you get
- A code review over a file with the language named, covering bugs, style and best practices, performance and security —
code_review - A design critique for a named design type such as a web UI, covering patterns, accessibility and consistency —
design_critique - Writing feedback for a named writing type such as documentation, covering grammar, clarity and structure —
writing_feedback - Feature enhancement brainstorming around a concept, with feasibility and user-value assessment —
brainstorm_enhancements - A second-opinion path for approaches you are unsure about, with worked examples in the repository for each tool showing the request format and a sample response
Requirements
A Deepseek API key. DEEPSEEK_API_KEY and DEEPSEEK_MODEL are both required, with deepseek-reasoner as the documented model; DEEPSEEK_MAX_TOKENS defaults to 8192, DEEPSEEK_MAX_RETRIES to 3, and DEEPSEEK_TIMEOUT to 30000 milliseconds. Build from a clone with npm install and npm run build, then register build/index.js with node and put the variables in the client's env block. The package is mentor-mcp-server 1.0.0, Apache 2.0 licensed.
Setup effort
Build from source — git clone https://github.com/cyanheads/mentor-mcp-server.git
USE CASES
01
Getting code checked by something other than the author
Send the file and its language for a review covering bugs, security and performance, instead of asking the same agent to grade itself.
02
Sanity-checking an approach before building it
Ask for a second opinion on the design or architecture while it is still cheap to change.
03
Tightening documentation before it ships
Send the draft with its writing type for grammar, clarity and structural feedback.
04
Opening up a feature that feels finished
Hand over the concept and get enhancement ideas with feasibility and user-value assessment attached.
4 tools
Listed in project docs. Your client may show a different list.
design_critiquewriting_feedbackbrainstorm_enhancementsBEFORE YOU INSTALL
What to know first
Tools you get
4 tools named in the project's documentation.
Requires
- node on PATH
- DEEPSEEK_API_KEY in your environment
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
You clone and build this one yourself.
Server setup
TERMINAL
git clone https://github.com/cyanheads/mentor-mcp-server.git
cd mentor-mcp-server
npm install
npm run buildMCP Clients
Any MCP client
Needs Node.js and npm. After building, add this to your MCP client settings. <YOUR_PATH_TO_MENTOR_MCP_SERVER> is the folder you cloned into.
ANY MCP CLIENT · JSON
{
"mcpServers": {
"mentor": {
"command": "node",
"args": [
"<YOUR_PATH_TO_MENTOR_MCP_SERVER>/build/index.js"
],
"env": {
"DEEPSEEK_API_KEY": "<YOUR_DEEPSEEK_API_KEY>",
"DEEPSEEK_MODEL": "deepseek-reasoner",
"DEEPSEEK_MAX_TOKENS": "8192",
"DEEPSEEK_MAX_RETRIES": "3",
"DEEPSEEK_TIMEOUT": "30000"
}
}
}
}
