About MCP Project
AbadIA-MCP combines an AI agent with an MCP server to play and solve the classic game The Abbey of Crime. It bridges LLM strategic reasoning to commands for the game emulator.
Key features
- 01AI agent for The Abbey of Crime
- 02MCP bridge to emulator commands
- 03Separate server and agent processes
Use cases
- 01Play The Abbey of Crime with an AI agent
- 02Translate strategic reasoning into emulator commands
MCP support
The MCP server bridges the LLM's strategic reasoning and low-level commands for the game emulator.
Configuration
Local server config is the same for every client. Copy it into your client’s MCP config file.
We haven’t collected a package or remote endpoint for this server. Follow the instructions in the project README.
Tools
Local servers expose tools only once running on your machine, and the maintainer has not provided a tool list.
Details
From the project READMEAbadIA-MCP: An AI Agent for "The Abbey of Crime"
Overview
This project implements an AI agent that plays and solves the classic video game "The Abbey of Crime". It uses a Model Control Program (MCP) server as a bridge between the strategic reasoning of the LLM and the low-level commands of the game emulator.
Getting Started
Prerequisites
- Python 3.9+
- An emulator running "The Abbey of Crime" (AbadIA-Server).
Installation
- Clone the repository:
git clone https://github.com/LaAbadIAdelCrimen/AbadIA-MCP.git cd AbadIA-MCP - Setup environment:
python3 -m venv .venv source .venv/bin/activate pip install -r requirements.txt
Running the System
- Start the MCP Server:
python server/main.py - Start the AI Agent:
python agent.py
Documentation Roadmap
- Technical Specs: See docs/SPECS.md for API, movement, and data models.
- Project Wiki: See docs/wiki/index.md for game lore, HE v3 concepts, and research.
- Developer Guidelines: See
docs/mcp_server_guidelines.md. - Deepwiki Harness: See docs/harness/ralph-graph-vault-workflow.md — how we install
/ralph+ Graph Vault and run the loop to build the deepwiki.
License
Distributed under the MIT License.
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.