Rowbit runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 8 Nov 2026.
Preview, approve and undo AI agents' writes to MariaDB and MySQL
We read the source, 6 h 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.
let file = home.join(format!("Library/LaunchAgents/{label}.plist"));
stepsEl.innerHTML = STEPS.map(s => `<li>${s}</li>`).join('');
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.
Lints SQL and checks rewrites return the same rows. Postgres, MySQL, MariaDB, SQLite, MSSQL, DuckDB
Guard AI agents' PostgreSQL/MySQL access via MCP: SQL audit, auth, masking, write approval
Database MCP server for MySQL, MariaDB, PostgreSQL & SQLite with PII redaction and write-prevention
Local shared memory for AI coding agents: SQLite notes with writer provenance, undo, search.
Postgres brake for AI agents: risky SQL waits for approval, UPDATE/DELETE get one-command undo.
MySQL migration and query safety review for AI agents: locks, table copies, data loss, injection.
Read-only MySQL/MariaDB for AI agents — query, list/describe tables, health. SQL-guarded.
Query PostgreSQL, MySQL, MariaDB, SQLite and MongoDB with two tools and few tokens.
Answers built from our own checks of this server.