mysql · Oracle
MySQL CLI for AI Agents
Run non-interactive MySQL queries while isolating credentials and database writes.
Install for an Agent
Choose an official installation path that matches the runtime. Pin a version for team or CI use, then record the version before the first task.
Structured Output for Reliable Automation
Prefer a machine-readable format. Treat stdout as the result channel and stderr as diagnostics so the agent can parse failures separately.
R0–R3 Command Risk Guide
Risk is assigned per command. R0 is local or remote read-only, R1 is reversible local write, R2 changes remote state, and R3 can be irreversible or production-impacting.
Read-only does not mean public
R0 only means the command does not change local or remote state. A read-only command may still return secrets, identity data, configuration, or production data. Expose only the minimum needed for the task, and never place it in logs, prompts, or commits.
How the Agent Readiness Score Is Built
Readiness describes how reliably an agent can operate the tool. It does not make every command safe and it does not replace an independent execution test.
Documentation indicates an agent-readiness score of 83/100. A bounded local smoke test is recorded for 8.0.45; review its limitations before relying on untested commands.
Generate a Skill or Agent Policy
Choose an agent and safety mode to generate a copyable artifact with installation, allowed commands, approval boundaries, and the evidence limitation.
---
name: mysql-cli-agent-workflow
description: Use MySQL CLI for MySQL queries, schema inspection, batch SQL with explicit command risk and evidence boundaries.
---
# MySQL CLI agent workflow
Use this skill when the task needs MySQL queries, schema inspection, batch SQL, tabular export.
## Evidence boundary
- Registry confidence: `verified`
- Documentation checked: `2026-07-10`
- Locally tested version: `8.0.45`
- Treat only the recorded executed checks as independently verified; every unlisted command remains documentation-only.
## Executed smoke checks
- `mysql --version` — passed; exit 0. The recorded smoke check completed successfully.
- `mysql --help` — passed; exit 0. The recorded smoke check completed successfully.
## Installation
- Homebrew client (macos, linux): `brew install mysql-client`
## Authentication
- Methods: option file, login path, password, TLS certificate
- Secret environment variables: `MYSQL_PWD`
- Minimum permissions: Use a read-only user, require TLS, and prefer a protected option file over command-line passwords.
- Credential storage: For headless runs, inject MYSQL_PWD from the CI or platform secret manager at process start. For local interactive use, prefer the CLI or operating-system credential store when the official client supports one. Never save values in repository files.
- Never print, persist, or commit credential values.
## Allowed commands (read-only)
- `mysql --batch --raw --execute "SELECT * FROM table_name LIMIT 20" DATABASE` — R0: Reads a bounded result set without an interactive prompt.
## Commands requiring explicit approval (read-only)
- None recorded.
## Forbidden commands (read-only)
- R2 `mysql --execute "UPDATE table_name SET ... WHERE ..." DATABASE` — Changes remote database records.
- R3 `mysql --execute "DROP DATABASE database_name"` — Permanently deletes a database.
## Execution rules
1. Mode boundary: R0 exact commands may be used; R1, R2, and R3 commands are forbidden.
2. Confirm the selected account, project, context, database, namespace, or environment before any command.
3. Prefer structured output using `--batch`, `--raw`, `--skip-column-names`.
4. Capture the exact command, exit code, stdout, and stderr separately.
5. A generated prefix policy must prompt unless that exact prefix is explicitly marked suffix-safe; do not infer safety from the executable name.
6. Never broaden credentials or disable safety controls to make a command succeed.
## Official sources
- [MySQL command-line client documentation](https://dev.mysql.com/doc/refman/8.0/en/mysql.html)
Verification History and Official Evidence
CLI Finder records documentation review separately from real execution. Installation, help, exit codes, and output cannot be called Verified until they were run.