beebjit-mcp
Lets an AI application instantiate, connect to, drive, capture output from, and interrogate a real BBC Micro emulator.
README
beebjit-MCP
beebjit-MCP is a Python-based Model Context Protocol (MCP) server that lets an AI application instantiate, connect to, drive, capture output from, and interrogate a real BBC Micro emulator.
Ask an AI agent something like:
Boot a BBC Model B, then type
PRINT "HELLO"at the BASIC prompt, and read the screen back.
A couple of seconds later HELLO appears in the tool-result pane. That's it.
beebjit-MCP drives Chris Evans' beebjit, a cycle-accurate, high-performance BBC Micro emulator written in C. Install and configure beebjit before using beebjit-MCP. The installation guide walks through it.
What the AI agent can do with it
-
Boot a BBC B, Master 128 (MOS 3.20 or 3.50), or Master Compact session, with or without a disc image. DFS images use
.ssd/.dsd; ADFS images use.adl/.adf. -
Type ASCII into the keyboard and have it land as real BBC keypresses. SHIFT handling, CAPS LOCK control, and special keys like arrows and function keys are all wired.
-
Wait for text to appear on the MODE 7 screen, or for the BASIC
>prompt. -
Read or write BBC Micro RAM, read 6502 register state, and disassemble 6502 instructions.
-
Run a whole BBC BASIC program one-shot and capture the final screen.
-
Tear everything down cleanly when the client disconnects.
Licence
MIT. See LICENSE.
beebjit is GPLv3 and is never bundled in this repository or its release artefacts; the user installs beebjit themselves.
Acknowledgements
Thanks to Chris Evans (scarybeasts@gmail.com), creator and maintainer of beebjit. Without his work, none of this would exist.
Fork Notice
beebjit-MCP currently depends on a fork of beebjit that carries the small set of fixes and flags it needs. See installation for the exact list.
Disclaimer
beebjit-MCP is a separate project from beebjit, and is not affiliated with, sponsored, or endorsed by Chris Evans or the beebjit project.
For the canonical beebjit source and documentation, see scarybeasts/beebjit.
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.