SafeSelect MCP runs on your own machine — the client starts it, so there is no endpoint to ping. Last commit 31 Aug 2026.
Fail-closed, read-only PostgreSQL and MongoDB access for AI agents over MCP.
We read the source, 13 h ago · rules 3dff92dd89df
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
return subprocess.check_output(args, text=True, **kwargs).strip()
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.
cp safeselect "${installed_binary}"
chmod +x "${installed_binary}"
return subprocess.check_output(args, text=True, **kwargs).strip()
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch SafeSelect MCP and you get told the day something new turns up.
Safe, read-only Postgres and MySQL access for AI agents. Audit log + column-level controls.
Safety-railed database access for agents: Postgres, MySQL, Redis. Read-only by default.
MCP server for Oracle, MSSQL, PostgreSQL, MySQL, SQLite, MongoDB, and Qdrant vector search access.
Read-only PostgreSQL, MySQL, SQL Server access via MCP — 24 dialect-aware hosted tools.
RLS/tenant-aware Postgres for AI agents — schema, read-only SQL, NL→SQL with safety rails.
Read-only MongoDB for AI agents — find, aggregate (no write stages), count, stats.
PostgreSQL MCP wrapper with .env credential mapping, tool selection, and safe read-only defaults.
Policy-driven, read-only MCP server for safe database access from AI tools.
Answers built from our own checks of this server.