Coding Tools MCP runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 28 Oct 2026.
Desktop MCP workspace for AI agents: file edits, commands, Git status, resumable history sessions.
We read the source, 3 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
process = subprocess.Popen(**popen_kwargs)
popen_shell = True
child = spawn(candidate.command, candidate.args, { stdio: "inherit" });
const SUFFIX: &str = ".trycloudflare.com";
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Persistent cloud workspaces for AI agents: run commands, edit files, use git and a browser.
Local shell history and AI agent sessions over MCP: search commands, failures, risk and git changes
Shared records for AI agents: engineering decisions, bug history, rules, and work state through MCP.
SysML v2 and KerML for coding agents: workspace diagnostics and edits, execution, REPL sessions.
Local Git-history memory for coding agents: reverts, suppressions, hotspots, and annotations.
Session memory for AI coding agents: records decisions and dead ends, flags what went stale.
A visible desktop browser for coding agents, with a separate workspace for each project.
MCP server for terminal commands, file operations, and process management
Answers built from our own checks of this server.