advanced-reason

Advanced Reason MCP is a Node.js-based tool that leverages the Gemini API to perform advanced reasoning and reflective analysis. It is designed to help you perform complex tasks that require multi-step reasoning, critique, and iteration by interacting with Gemini and Open Router capabilities. The MCP server exposes a local/MCP-friendly interface that can be wired into your existing MCP ecosystem, enabling you to submit prompts and receive structured, reasoned outputs that incorporate critique and self-reflection. You’ll primarily interact with it by ensuring your Gemini API key, Open Router API key, and an optional Open Router model are configured in the environment.

To use it, configure the server as described in the installation notes, start the server, and point your MCP client at the advanced-reason endpoint. The tool will use Gemini for reasoning and, if needed, the Open Router model for additional model guidance or critique. The included configuration supports setting the API keys and the Open Router model to control runtime behavior. When running, you can leverage the server’s capabilities for long-running reflection tasks, structured reasoning chains, and iterative improvement of responses.

Prerequisites:

• Node.js 20.17 or higher
• npm (comes with Node.js)
• Gemini API key
• Open Router API key

Installation steps:

1. Clone the repository and navigate to it:

git clone git@github.com:Kuon-dev/advanced-reason-mcp.git
cd advanced-reason-mcp

2. Install dependencies:

npm install

3. Build the project to generate the dist directory:

node ./bin/build.mjs

4. Create a configuration entry for MCP (see example below) and ensure the dist/index.js is present:

{
  "advanced-reason-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"
    }
  }
}

5. Run the MCP server through your MCP manager using the configured entry.

Environment variables:

• GEMINI_API_KEY: Your Gemini API key used for reasoning tasks.
• OPENROUTER_API_KEY: API key for Open Router access (optional but recommended for enhanced capabilities).
• OPENROUTER_MODEL: Open Router model to use (defaults to deepseek/deepseek-r1:free if not set).

Tips and caveats:

• Ensure the dist/index.js path in your mcp configuration points to the built file.
• Long-running tasks may timeout if outputs become extremely large; consider adjusting timeouts in your MCP client settings.
• Keep your API keys secure and do not commit them to version control.
• If you modify the config, reload the MCP server to apply changes.