Advanced Reasoning with DeepSeek
About
Leverages the deepseek-r1 model to provide structured reasoning capabilities through specialized tools for analytical thinking, reflection with quality scoring, and sequential problem-solving with branching thoughts.
Details
- Author
- kuon-dev
- Repository
- Kuon-dev/advanced-reason-mcp
- GitHub stars
- 17
- Downloads
- 371
- License
- MIT License
- Categories
- Design, Developer Tools, AI, Infrastructure, Frontend, API, Other
Jump to
- Chain sequential thinking with external critique models
- Integrates Gemini and Deepseek via Open Router
- Configurable critique model via environment variable
- Automated reasoning and reflection pipeline
- Built as a lightweight MCP server
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Advanced Reasoning with DeepSeekCommand (node, npx, python, etc.)nodeArguments-
Argument 1
/path/to/your/advanced-reason-mcp/dist/index.js
Environment-
GEMINI_API_KEY
your-api-key-here -
OPENROUTER_MODEL
your-selected-model-here -
OPENROUTER_API_KEY
your-api-key-here
Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
-
Argument 1
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
The tool can be configured through the claude_desktop_config.json settings in your project configuration:
{
"advanced-reflection-reason": {
"command": "node",
"args": ["/path/to/your/advanced-reason-mcp/dist/index.js"],
"env": {
"GEMINI_API_KEY": "your-api-key-here",
"OPENROUTER_API_KEY": "your-api-key-here",
"OPENROUTER_MODEL": "your-selected-model-here"
}
}
}
OPENROUTER_MODEL env variable is optional. Defaults to deepseek/deepseek-r1:free if left empty.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"advanced reasoning with deepseek": {
"env": {
"GEMINI_API_KEY": "your-api-key-here",
"OPENROUTER_MODEL": "your-selected-model-here",
"OPENROUTER_API_KEY": "your-api-key-here"
},
"args": [
"/path/to/your/advanced-reason-mcp/dist/index.js"
],
"command": "node"
}
}
}
Linux
{
"env": {
"GEMINI_API_KEY": "your-api-key-here",
"OPENROUTER_MODEL": "your-selected-model-here",
"OPENROUTER_API_KEY": "your-api-key-here"
},
"args": [
"/path/to/your/advanced-reason-mcp/dist/index.js"
],
"command": "node"
}
Macos
{
"env": {
"GEMINI_API_KEY": "your-api-key-here",
"OPENROUTER_MODEL": "your-selected-model-here",
"OPENROUTER_API_KEY": "your-api-key-here"
},
"args": [
"/path/to/your/advanced-reason-mcp/dist/index.js"
],
"command": "node"
}
Windows
{
"env": {
"GEMINI_API_KEY": "your-api-key-here",
"OPENROUTER_MODEL": "your-selected-model-here",
"OPENROUTER_API_KEY": "your-api-key-here"
},
"args": [
"/path/to/your/advanced-reason-mcp/dist/index.js"
],
"command": "node"
}
Advanced Reason MCP
A tool for advanced reasoning and reflection using the Gemini API.



Requirements
- Node.js 20.17 or higher
- Gemini API key
- Open Router API key
Installation
1. Clone the repository:
git clone git@github.com:Kuon-dev/advanced-reason-mcp.git
cd advanced-reason-mcp
2. Install dependencies
npm install
Building
Build the project using:
node ./bin/build.mjs
This will create the necessary files in the dist directory.
Configuration
The tool can be configured through the claude_desktop_config.json settings in your project configuration:
{
"advanced-reflection-reason": {
"command": "node",
"args": ["/path/to/your/advanced-reason-mcp/dist/index.js"],
"env": {
"GEMINI_API_KEY": "your-api-key-here",
"OPENROUTER_API_KEY": "your-api-key-here",
"OPENROUTER_MODEL": "your-selected-model-here"
}
}
}
OPENROUTER_MODEL env variable is optional. Defaults to deepseek/deepseek-r1:free if left empty.
Limitations
- AI models does not have access to your project context, do be aware
- If the task is too complex, it is possible for the content to get really long, in which the MCP will timeout and return no response
License
This project is MIT licensed.
You can create your own project and modifying it freely without notifying me
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.




