Ultimate64mcp
U

Ultimate64mcp

This is an MCP server designed for the Commodore 64 Ultimate (the official modern C64 computer). It allows AI assistants (such as Claude, ChatGPT) to remotely control C64 hardware through a REST API, supporting functions such as program loading, memory operations, and disk management.
2.5 points
6.9K

What is the Commodore 64 Ultimate MCP Server?

This is a Model Context Protocol (MCP) server specifically designed for the Commodore 64 Ultimate (the official modern C64 computer) and other Ultimate devices (Ultimate 64, Ultimate II+). It allows AI assistants to interact with your real C64 hardware through natural language, converting AI instructions into REST API calls for the Ultimate device. The Commodore 64 Ultimate is not an emulator but a real C64 computer built using FPGA technology, with USB storage, Ethernet, HDMI output, and a powerful REST API. This MCP server enables you to remotely control these functions through an AI assistant.

How to use the Commodore 64 Ultimate MCP Server?

1. Ensure that your Commodore 64 Ultimate (or other Ultimate device) is connected to the network and the REST API is enabled. 2. Install and run the MCP server (Python script or Docker container). 3. Configure the MCP server connection in an AI assistant (such as Cursor IDE, Claude Desktop). 4. Control your C64 through natural language commands, such as 'Load a game', 'Play SID music', or 'Read memory contents'. The server supports two operating modes: SSE mode for remote/hosted deployment and STDIO mode for local use.

Use cases

• AI-assisted C64 program development and testing • Remote demonstration and teaching of C64 programming • Automated C64 tasks and testing • Generate C64 programs through AI and run them directly on real hardware • Remote access and management of C64 collections • Educational and nostalgia projects that allow AI to interact with vintage computers

Main features

37 dedicated tools
Covers all major functions of the Ultimate device, including program execution, memory operations, disk management, machine control, and configuration management.
Remote program execution
Supports loading and running PRG programs from Base64 encoding, URL links, or local server files without pre - storing them on the Ultimate device.
Dual transfer modes
SSE mode is used for remote/hosted deployment, and STDIO mode is used for local AI client integration to adapt to different usage scenarios.
Dynamic connection management
Allows setting and changing the C64 device connection at runtime without restarting the server, flexibly adapting to changes in the network environment.
Docker container support
Provides a Docker image to simplify the deployment process. The container runs as a non - root user to enhance security.
Direct file upload endpoint
In addition to the MCP protocol, it provides a REST endpoint for direct PRG file upload, supporting large file uploads and automated scripts.
Advantages
Allows AI assistants to interact with real C64 hardware rather than an emulator
Supports multiple Ultimate devices (C64 Ultimate, Ultimate 64, Ultimate II+)
Eliminates the need for manual C64 operations, all done through natural language commands
Remote access capability, allowing you to control your C64 from anywhere
Open - source and extensible, enabling the community to contribute new functions
Good error handling and connection retry mechanism
Limitations
Requires a Commodore 64 Ultimate or other Ultimate hardware device
The device must be connected to the network and the REST API must be accessible
Alpha version, there may be undiscovered bugs
Some advanced functions require Ultimate 64 hardware (such as video streaming)
Large file uploads may be affected by network latency

How to use

Preparation
Ensure that your Commodore 64 Ultimate (or other Ultimate device) is powered on and connected to the network. Confirm in the device menu that the REST API is enabled.
Install and run the server
Install and run the MCP server (Python script or Docker container).
Configure the connection
Configure the MCP server connection in an AI assistant (such as Cursor IDE, Claude Desktop).
Start using
Use natural language commands in the AI assistant to control your C64, such as requesting to load a program, play music, or manage disks.

Usage examples

AI - generated and run C64 programs
The AI writes a simple C64 BASIC program, compiles it into a PRG, uploads it via Base64 encoding, and runs it on real C64 hardware.
Remote game demonstration
Load classic C64 games from an online archive without manual device operation.
SID music on - demand
Select and play a specific SID music file from USB storage.
Disk management automation
Create a new disk image for storing programs or data.

Frequently Asked Questions

What hardware do I need to use this MCP server?
How do I know the IP address of my C64 Ultimate?
What is the difference between SSE mode and STDIO mode? Which one should I choose?
Can I run PRG files directly from the Internet?
What should I do if I encounter the 'No C64 host configured' error?
Is this server secure?
What is the maximum supported file size?
What does the Alpha version mean?

Related resources

GitHub repository
Project source code, issue tracking, and contribution guidelines
Gideon's Logic / Ultimate64.com
Official website of the Ultimate hardware manufacturer, product information and documentation
Ultimate REST API documentation
Complete technical documentation of the Ultimate device REST API
Model Context Protocol specification
Official specification and documentation of the MCP protocol
Commodore official website
Official information about the Commodore 64 Ultimate
CSDB - C64 Scene Database
A large archive of C64 programs, games, and music

Installation

Copy the following command to your Client for configuration
{
  "mcpServers": {
    "ultimate64-mcp": {
      "transport": {
        "type": "sse",
        "url": "http://your-server-address:8000/sse"
      }
    }
  }
}

{
  "mcpServers": {
    "ultimate64-mcp": {
      "command": "python",
      "args": ["/path/to/mcp_ultimate_server.py", "--stdio"],
      "env": {
        "C64_HOST": "192.168.1.64"
      }
    }
  }
}
Note: Your key is sensitive information, do not share it with anyone.

Alternatives

R
Runno
Runno is a collection of JavaScript toolkits for securely running code in multiple programming languages in environments such as browsers and Node.js. It achieves sandboxed execution through WebAssembly and WASI, supports languages such as Python, Ruby, JavaScript, SQLite, C/C++, and provides integration methods such as web components and MCP servers.
TypeScript
4.6K
5 points
N
Netdata
Netdata is an open-source real-time infrastructure monitoring platform that provides second-level metric collection, visualization, machine learning-driven anomaly detection, and automated alerts. It can achieve full-stack monitoring without complex configuration.
Go
6.2K
5 points
M
MCP Server
The Mapbox MCP Server is a model context protocol server implemented in Node.js, providing AI applications with access to Mapbox geospatial APIs, including functions such as geocoding, point - of - interest search, route planning, isochrone analysis, and static map generation.
TypeScript
6.2K
4 points
U
Uniprof
Uniprof is a tool that simplifies CPU performance analysis. It supports multiple programming languages and runtimes, does not require code modification or additional dependencies, and can perform one-click performance profiling and hotspot analysis through Docker containers or the host mode.
TypeScript
7.7K
4.5 points
G
Gk Cli
GitKraken CLI is a command - line tool that provides multi - repository workflow management, AI - generated commit messages and pull requests, and includes a local MCP server for integrating tools such as Git, GitHub, and Jira.
5.6K
4.5 points
M
MCP
A collection of official Microsoft MCP servers, providing AI assistant integration tools for various services such as Azure, GitHub, Microsoft 365, and Fabric. It supports local and remote deployment, helping developers connect AI models with various data sources and tools through a standardized protocol.
C#
6.3K
5 points
C
Claude Context
Claude Context is an MCP plugin that provides in - depth context of the entire codebase for AI programming assistants through semantic code search. It supports multiple embedding models and vector databases to achieve efficient code retrieval.
TypeScript
11.4K
5 points
A
Acemcp
Acemcp is an MCP server for codebase indexing and semantic search, supporting automatic incremental indexing, multi-encoding file processing, .gitignore integration, and a Web management interface, helping developers quickly search for and understand code context.
Python
12.2K
5 points
N
Notion Api MCP
Certified
A Python-based MCP Server that provides advanced to-do list management and content organization functions through the Notion API, enabling seamless integration between AI models and Notion.
Python
18.4K
4.5 points
G
Gitlab MCP Server
Certified
The GitLab MCP server is a project based on the Model Context Protocol that provides a comprehensive toolset for interacting with GitLab accounts, including code review, merge request management, CI/CD configuration, and other functions.
TypeScript
19.9K
4.3 points
M
Markdownify MCP
Markdownify is a multi-functional file conversion service that supports converting multiple formats such as PDFs, images, audio, and web page content into Markdown format.
TypeScript
28.2K
5 points
D
Duckduckgo MCP Server
Certified
The DuckDuckGo Search MCP Server provides web search and content scraping services for LLMs such as Claude.
Python
58.2K
4.3 points
U
Unity
Certified
UnityMCP is a Unity editor plugin that implements the Model Context Protocol (MCP), providing seamless integration between Unity and AI assistants, including real - time state monitoring, remote command execution, and log functions.
C#
24.7K
5 points
F
Figma Context MCP
Framelink Figma MCP Server is a server that provides access to Figma design data for AI programming tools (such as Cursor). By simplifying the Figma API response, it helps AI more accurately achieve one - click conversion from design to code.
TypeScript
53.3K
4.5 points
G
Gmail MCP Server
A Gmail automatic authentication MCP server designed for Claude Desktop, supporting Gmail management through natural language interaction, including complete functions such as sending emails, label management, and batch operations.
TypeScript
18.3K
4.5 points
C
Context7
Context7 MCP is a service that provides real-time, version-specific documentation and code examples for AI programming assistants. It is directly integrated into prompts through the Model Context Protocol to solve the problem of LLMs using outdated information.
TypeScript
80.5K
4.7 points
AIBase
Zhiqi Future, Your AI Solution Think Tank
© 2025AIBase