Berth is a Model Context Protocol server that provides AI assistants with secure, structured access to PostgreSQL, SQLite, and MySQL databases, allowing for various database operations while enforcing a safety model.
From the registry: Database management — query, schema inspection, migrations for PostgreSQL, MySQL, SQLite.
$ pip install berth-mcphttps://pypi.org/project/berth-mcp/Please install the `berth` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install berth-mcp** — Install the berth-mcp Python package from PyPI (add [mysql] extra for MySQL support). Run: `pip install berth-mcp` (https://pypi.org/project/berth-mcp/)
Canonical MCP server config (stdio transport):
- command: `berth`
- args: []
- optional environment variables:
- `BERTH_BACKUP_DIR`: Sandbox directory for backup/restore paths. Defaults to the current working directory. (example: `<your-backup-dir>`)
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.BERTH_BACKUP_DIRrequiredSandbox directory for backup and restore paths. All paths are validated to stay within this directory.MCP server for interacting with the Supabase platform