Fire in da houseTop Tip:Paying $100+ per month for Perplexity, MidJourney, Runway, ChatGPT and other tools is crazy - get all your AI tools in one site starting at $15 per month with Galaxy AI Fire in da houseCheck it out free

new-mcp

MCP.Pizza Chef: bartekke8it56w2

The new-mcp is an MCP server integrating Google's Gemini API to enable advanced analytical thinking and sequential problem-solving. It supports breaking down complex problems into manageable steps, planning with iterative revisions, and providing meta-commentary on its reasoning process. Features include confidence level indicators, alternative solution paths, and branching thoughts exploration, making it ideal for scenarios requiring deep analysis and adaptive problem-solving without code generation.

Use This MCP server To

Break down complex problems into sequential steps Plan and revise project designs iteratively Analyze ambiguous problems with adaptive reasoning Generate meta-commentary on reasoning processes Suggest alternative approaches to problem-solving Explore branching thoughts for decision making

README

Model Context Protocol - Gemini Thinking Server

This is an implementation of the Model Context Protocol (MCP) that integrates with Google's Gemini API to provide analytical thinking capabilities without code generation.

Overview

The Gemini Thinking Server is a specialized MCP server that leverages Google's Gemini model to provide sequential thinking and problem-solving capabilities. It allows for:

  • Breaking down complex problems into steps
  • Planning and design with room for revision
  • Analysis that might need course correction
  • Problems where the full scope might not be clear initially

Features

  • Gemini-Powered Thinking: Utilizes Gemini's analytical capabilities to generate thoughtful responses
  • Meta-Commentary: Provides insights into the reasoning process
  • Confidence Levels: Indicates how confident Gemini is in its analysis
  • Alternative Paths: Suggests different approaches to the problem
  • Branching Thoughts: Allows exploration of different thought paths
  • Revision Capability: Supports revising previous thoughts
  • Session Persistence: Save and resume analysis sessions

Installation

# Clone the repository
git clone <repository-url>

# Install dependencies
npm install

# Build the project
npm run build

Usage

Environment Setup

Before running the server, you need to set up your Gemini API key:

export GEMINI_API_KEY=your_api_key_here

Running the Server

node dist/gemini-index.js

Tool Parameters

The geminithinking tool accepts the following parameters:

  • query (required): The question or problem to analyze
  • context (optional): Additional context information
  • approach (optional): Suggested approach to the problem
  • previousThoughts (optional): Array of previous thoughts for context
  • thought (optional): Your current thinking step (if empty, will be generated by Gemini)
  • nextThoughtNeeded (required): Whether another thought step is needed
  • thoughtNumber (required): Current thought number
  • totalThoughts (required): Estimated total thoughts needed
  • isRevision (optional): Whether this revises previous thinking
  • revisesThought (optional): Which thought is being reconsidered
  • branchFromThought (optional): Branching point thought number
  • branchId (optional): Branch identifier
  • needsMoreThoughts (optional): If more thoughts are needed

Session Management

The tool also supports session management commands:

  • sessionCommand: Command to manage sessions ('save', 'load', 'getState')
  • sessionPath: Path to save or load the session file (required for 'save' and 'load' commands)
Example: Saving a Session
{
  "sessionCommand": "save",
  "sessionPath": "/path/to/save/session.json",
  "query": "dummy",
  "thoughtNumber": 1,
  "totalThoughts": 1,
  "nextThoughtNeeded": false
}
Example: Loading a Session
{
  "sessionCommand": "load",
  "sessionPath": "/path/to/load/session.json",
  "query": "dummy",
  "thoughtNumber": 1,
  "totalThoughts": 1,
  "nextThoughtNeeded": false
}
Example: Getting Session State
{
  "sessionCommand": "getState",
  "query": "dummy",
  "thoughtNumber": 1,
  "totalThoughts": 1,
  "nextThoughtNeeded": false
}

Example

Here's an example of how to use the tool:

{
  "query": "How might we design a sustainable urban transportation system?",
  "context": "The city has 500,000 residents and currently relies heavily on personal vehicles.",
  "approach": "Consider environmental, economic, and social factors.",
  "thoughtNumber": 1,
  "totalThoughts": 5,
  "nextThoughtNeeded": true
}

Response Format

The server responds with:

{
  "thought": "The generated thought from Gemini",
  "thoughtNumber": 1,
  "totalThoughts": 5,
  "nextThoughtNeeded": true,
  "branches": [],
  "thoughtHistoryLength": 1,
  "metaComments": "Meta-commentary about the reasoning",
  "confidenceLevel": 0.85,
  "alternativePaths": ["Alternative approach 1", "Alternative approach 2"]
}

Example Clients

Several example clients are provided to demonstrate different use cases:

  • sample-client.js: Basic client example
  • example-usage.js: Specific usage example
  • codebase-analysis-example.js: Example for codebase analysis
  • session-example.js: Example demonstrating session persistence
  • advanced-filtering-example.js: Example demonstrating advanced semantic filtering

To run the session example:

node dist/session-example.js

To run the advanced filtering example:

node dist/advanced-filtering-example.js

License

MIT

new-mcp FAQ

How does new-mcp utilize Google's Gemini model?
new-mcp leverages Gemini's analytical capabilities to perform stepwise thinking, problem-solving, and planning without generating code.
Can new-mcp handle problems with unclear or evolving scopes?
Yes, it supports adaptive analysis and course correction for problems where the full scope is not initially clear.
What is meta-commentary in new-mcp?
Meta-commentary provides insights into the reasoning process, helping users understand how conclusions are reached.
How does new-mcp indicate confidence in its analysis?
It provides confidence levels alongside its responses to show how certain the model is about its conclusions.
Does new-mcp suggest alternative solutions?
Yes, it offers alternative paths and approaches to problems to aid in comprehensive decision-making.
Is new-mcp focused on code generation?
No, it is designed specifically for analytical thinking and problem-solving without generating code.
How can branching thoughts be used in new-mcp?
Branching thoughts allow exploration of different lines of reasoning or solutions within a problem space.
What types of workflows benefit most from new-mcp?
Workflows involving complex problem decomposition, iterative planning, and adaptive analysis benefit greatly from new-mcp.