Mo5 Mcp Server

io.github.thlg057Published by GitHub account thlg057v1.0.2Updated Oct 24, 2026

MCP server for Thomson MO5 C development, 6809, CMOC, SDK, toolchain.

VerifiedSTDIODesktop onlyKnowledge & MemoryDeveloper Tools

Overview

AI-generated overview

A local MCP server that connects an AI assistant to a MO5 RAG knowledge base and build tools for Thomson MO5 6809 development.

What you can do
Search MO5 technical documentation semantically and browse indexed documents, tags and indexing status through the RAG server. Activate a preconfigured expert Thomson MO5 prompt for development questions. Generate bootable .fd disk images, convert .fd images to .sd for SDDrive, and convert PNG assets into C sprite headers.
When to use it
Useful when developing software for the Thomson MO5 microcomputer with CMOC and the 6809, or when you want an assistant to answer MO5 technical questions from a curated documentation base and produce disk images or sprite headers.
Requirements
Runs locally via npx or from source, so Node.js v18 or higher is needed. The RAG_BASE_URL environment variable is required and points at a MO5 RAG server; a public instance is offered, and self-hosting is optional. Python 3 with Pillow is needed only for the PNG-to-sprite tool. Network access to the RAG server is required.
Before you install
The server sends queries to the RAG server named in RAG_BASE_URL, so documentation content and questions leave the machine; point it only at an instance you trust. Build tools write files such as disk images and C headers to the local machine. The PNG-to-sprite tool depends on a separately installed Python package.

Installation

In SourceWeft

  1. Open Mo5 Mcp Server in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

MO5 MCP Server (RAG Connector)

This MCP server (Model Context Protocol) acts as a bridge between modern AI agents (Claude Desktop, Augment, Cursor) and the Thomson MO5 ecosystem.
It allows access to an expert knowledge base and manipulation of MO5 heritage files.

It provides semantic search tools, documentation resources, and expert prompts to facilitate development around the Thomson MO5 microcomputer.

🏗️ MO5 Development Ecosystem

This server is part of a complete toolchain for modern 6809 development:

🌐 RAG Infrastructure (Artificial Intelligence)

The server relies on a Retrieval-Augmented Generation architecture to provide accurate answers based on real technical documentation.

🚀 Features

  • Semantic Search: Intelligent search within the MO5 technical documentation.
  • Resources Explorer: Direct access to the list of documents, tags, and indexing status.
  • Expert Prompt: A preconfigured "Expert Thomson MO5" mode for the AI.
  • Build Tools: Generate bootable .fd disk images, convert .fd to .sd for SDDrive, and convert PNG assets to C sprite headers.
  • Robustness: Native handling of timeouts (30s) and retry policy for unstable network environments (NAS).

🌐 Public MO5 RAG Server

The MO5 RAG server is now publicly deployed and accessible on the Internet.

👉 https://retrocomputing-ai.cloud/

This MCP server is designed to work out of the box with the public RAG instance.

For most users, this means:

  • no RAG server to install
  • no Docker setup
  • no local infrastructure to maintain

Simply configure the MCP server to point to the public URL and start using it from your coding agent.

Self-hosting a RAG server is still possible if you want to:

  • experiment with the internals
  • customize the knowledge base
  • run everything offline

But it is no longer required for normal usage.

🛠️ Requirements

  • Node.js (v18 or higher)
  • Python 3 with Pillow (pip install Pillow) — required only for the png_to_mo5_sprite tool.

The official public MO5 RAG server is available at: https://retrocomputing-ai.cloud/

You can use this public instance directly, there is no need to host your own RAG server.

📦 Installation & Setup

Option 1 — Via npx (recommended, no installation required)

Configure your agent to run the server directly from npm. No git clone or npm install needed.

json
{  "mcpServers": {    "mo5-server": {      "command": "npx",      "args": [        "-y",        "@thlg057/mo5-rag-mcp"      ],      "env": {        "RAG_BASE_URL": "https://retrocomputing-ai.cloud"      }    }  }}

Option 2 — From source

bash
git clone https://github.com/thlg057/mo5-mcp-server.gitcd mo5-mcp-servernpm install

Then configure your agent:

json
{  "mcpServers": {    "mo5-rag": {      "command": "node",      "args": ["C:\\your\\path\\to\\mo5-mcp-server\\index.js"],      "env": {        "RAG_BASE_URL": "https://retrocomputing-ai.cloud"      }    }  }}

Note for Windows: Use double backslashes \\ or single slashes / in the path to avoid JSON formatting errors.

🤖 Integration into an Agent (e.g., Augment, Claude Desktop)

Add one of the configurations above to your MCP configuration file (e.g., augment_config.json or claude_desktop_config.json).

🧪 Local Testing

It is recommended to test the server before integration to ensure proper communication with the RAG API.

Via the MCP Inspector (Recommended)

bash
# Windows (PowerShell)$env:RAG_BASE_URL="https://retrocomputing-ai.cloud"; npx @modelcontextprotocol/inspector node index.js

Via Command Line

bash
echo {"jsonrpc":"2.0","method":"tools/list","id":1} | node index.js

📂 Project Structure

  • index.js: Main source code of the MCP server.
  • scripts/: Python scripts for build tools (makefd.py, fd2sd.py, png2mo5.py).
  • package.json: Dependencies (MCP SDK).
  • .gitignore: Ignores node_modules and environment files.

🏗️ MO5 Development Ecosystem

This server is part of a suite of tools designed to modernize development on the Thomson MO5:

  • SDK MO5: A C library for CMOC that provides easy access to the hardware (video, keyboard, monitor) without writing assembly.
  • Project Template: A ready-to-use project skeleton with an automated Makefile that compiles, links the SDK, and generates a bootable disk image in a single command. Also includes this MCP server as a dev dependency so your coding agent has full context and build capabilities out of the box.

This project is part of the digital preservation ecosystem for the Thomson MO5 microcomputer.

Source: README.md at commit e41c09c

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v1.0.2LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts