Pure-Python client harness and MCP server exposing the Commander X16 emulator's stdio debugger to MCP-speaking clients
Wellknown found it in public sources; nobody has proven control of it yet. Claiming takes one click if the repository is under your GitHub account, or a small file on your domain otherwise. Verified owners get the badge, 15-minute checks, status alerts, edits that outrank crawled data, and a ranking boost.
Agents can do it too: POST https://wellknown.network/api/v1/claims with {"agent":"x16-emulator-mcp","method":"well_known_file"} — machine-readable steps at claim.json, guide at /docs/claim.
Everything here was measured by our prober or read from a registry. Nothing is self-reported.
Attributed to the source that supplied each field. Treated as claims, not facts.
# x16-emulator-MCP [](https://www.python.org/) [](LICENSE) [](https://github.com/acscpt/x16-emulator-MCP/actions/workflows/tests.yml) [](https://codecov.io/gh/acscpt/x16-emulator-MCP) x16-emulator-MCP is a Python [Model Context Protocol (MCP)](https://modelcontextprotocol.io) server that lets an AI application boot, drive, and interrogate a real [Commander X16](https://github.com/X16Community) emulator through its headless `-debugstdio` debugger. The agent works the way a person would at a debugger: set breakpoints and memory watchpoints, run, read registers, memory, and VRAM, evaluate conditions, and look at the screen. Ask an AI agent something like: > A routine is clobbering zero-page `$70` and I don't know which one. Put a write watchpoint on it, run, and tell me what writes there. A moment later the answer comes back in the tool-result pane: `$0070 written as $aa by the instruction at $0502`. Catching the program counter behind a stray write is the loop the project is built for. x16-emulator-MCP drives a [fork of the Commander X16 emulator](https://github.com/acscpt/x16-emulator) that carries the headless debugger protocol it speaks. Install and configure the emulator before using the server; the [installation guide](docs/installation.md) walks through it. ## What the AI agent can do with it The server exposes the debugger as a set of typed tools; the [tool reference](docs/tool-reference.md) documents each with a worked example. - Boot a headless X16 session against a ROM, optionally loading a PRG at the BASIC prompt, and keep several independent sessions open at once, each addressed by a session id. - Set execution breakpoints and read or write…
Mapped onto the structured taxonomy from declared text and observed tool names. Confidence shown for derived entries.
Every source is kept verbatim. Field changes are logged as events.