JorgeDelAngel03/MCP
3.1
If you are the rightful owner of MCP and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to dayong@mcphub.com.
The Decision Maker MCP Server is a Python-based server designed to enhance the capabilities of Large Language Models (LLMs) by providing tools for decision-making, randomness, and data persistence.
Tools
5
Resources
0
Prompts
0
🤖 Decision Maker MCP Server
🎯 Project Overview
This repository contains a Model Context Protocol (MCP) server written in Python, designed to be used by Large Language Models (LLMs) like Claude. The server extends the LLM's capabilities by providing tools for impartial decision-making, weighted randomization, and data persistence (memory).
The core goal is to enable the AI agent to:
- Access a source of genuine randomness (which LLMs lack).
- Handle complex probability calculations (e.g., weighted selections).
- Maintain a persistent history of all decisions made.
✨ Core Features
| Feature | Tool(s) | Description |
|---|---|---|
| Data Persistence | consultar_historial | Automatically records every decision to a historial.json file. Allows the LLM to access past decisions for context and memory. |
| Weighted Decisions | elegir_ponderado | Selects an item from a list based on user-defined probabilities (weights), perfect for risk analysis or preference-based choices. |
| Specialized Randomness | seleccionar_pokemon_ponderado | Selects Pokémon from the Kanto region (151) with probabilities based on their rarity (Legendaries 1x chance, Base Stage 10x chance). |
| Basic Impartiality | tirar_moneda, tirar_dado_personalizado | Simple, unbiased tools for binary choices and custom dice rolls. |
⚙️ Setup and Installation
Prerequisites
- Python 3.10+
- The
mcplibrary (FastMCP)
Install the necessary Python package:
pip install fastmcp