mysql · sanjay3290 — Claude Code skill: read-only MySQL queries
This skill runs SELECT queries against several MySQL databases and blocks every write. Handy when you want to inspect a schema or pull data without touching production.
npx skills add sanjay3290/ai-skills --skill mysql -a claude-codeWhat mysql does
The skill drives a Python script, scripts/query.py, that connects to the databases listed in your config and reads only. Each session starts with SET SESSION TRANSACTION READ ONLY, and the validator accepts just SELECT, SHOW, DESCRIBE, EXPLAIN and WITH. Multiple statements in one query get rejected.
Databases live in connections.json inside the skill folder or at ~/.config/claude/mysql-connections.json. Every entry carries a name, description, host, port, database, user and password. The description powers auto-selection: ask about orders and the skill looks for a database whose description mentions orders or transactions. That file holds credentials, so give it 600 permissions with chmod 600 connections.json.
You need Python 3.8+ and mysql-connector-python from requirements.txt. Queries stop after 30 seconds and return at most 10,000 rows, so on wide tables set --limit up front. For local databases you can turn SSL off with "ssl_disabled": true.
What it helps with
- inspect table schemas before writing a migration
- pull a read-only sample from production
- pick the right database by its description
- check what a table holds without a MySQL client
- cap a heavy query by rows and time
Example prompts for the agent
- list the configured MySQL databases
- show the table schema in the production database
- run a SELECT on orders with a limit of 100
How to install mysql
1Skills CLI (Vercel)
npx skills add sanjay3290/ai-skills --skill mysql -a claude-code2Manually: put the files in place
~/.claude/skills/mysql/SKILL.mdCopy the whole skill folder; for one project use .claude/skills/mysql/
1Skills CLI (Vercel)
npx skills add sanjay3290/ai-skills --skill mysql -a codex2Manually: put the files in place
.agents/skills/mysql/SKILL.mdFor all projects use ~/.agents/skills/
1Skills CLI (Vercel)
npx skills add sanjay3290/ai-skills --skill mysql -a cursor2Manually: put the files in place
.cursor/skills/mysql/SKILL.mdCursor also reads .agents/skills/ and .claude/skills/
1GitHub CLI
gh skill install sanjay3290/ai-skills mysql2Manually: put the files in place
.github/skills/mysql/SKILL.md1Skills CLI (Vercel)
npx skills add sanjay3290/ai-skills --skill mysql -a gemini-cli2Platform CLI
gemini skills install https://github.com/sanjay3290/ai-skills --path skills/mysqlManually: put the files in place
.devin/skills/mysql/SKILL.mdThe legacy .windsurf/skills/ path still works
Skills CLI (Vercel)
npx skills add sanjay3290/ai-skills --skill mysql -a opencodeClaude.ai
Zip the folder and upload it in Settings → Capabilities → Skills
Step by step, with commands for each platform: How to install skills in Claude Code: five ways
Questions about mysql
How do I install mysql in Claude?
Run npx skills add sanjay3290/ai-skills --skill mysql -a claude-code. The skill lands at ~/.claude/skills/mysql/SKILL.md.
What does the mysql skill do?
It runs read-only SQL against multiple MySQL databases: listing tables, showing schemas and returning data. Write operations are blocked.
What do I need before the first query?
Python 3.8+, the mysql-connector-python package from requirements.txt, and a connections.json file with your connection details. Since it stores passwords, set permissions to 600.
Source text
SKILL.md · Apache-2.0
---
name: mysql
description: "Execute read-only SQL queries against multiple MySQL databases. Use when: (1) querying MySQL databases, (2) exploring database schemas/tables, (3) running SELECT queries for data analysis, (4) checking database contents. Supports multiple database connections with descriptions for intelligent auto-selection. Blocks all write operations (INSERT, UPDATE, DELETE, DROP, etc.) for safety."
license: Apache-2.0
metadata:
author: sanjay3290
version: "1.0"
---
# MySQL Read-Only Query Skill
Execute safe, read-only queries against configured MySQL databases.
## Requirements
- Python 3.8+
- mysql-connector-python: `pip install -r requirements.txt`
## Setup
Create `connections.json` in the skill directory or `~/.config/claude/mysql-connections.json`.
**Security**: Set file permissions to `600` since it contains credentials:
```bash
chmod 600 connections.json
```
```json
{
"databases": [
{
"name": "production",
"description": "Main app database - users, orders, transactions",
"host": "db.example.com",
"port": 3306,
"database": "app_prod",
"user": "readonly_user",
"password": "your-password",
"ssl_disabled": false
}
]
}
```
### Config Fields
| Field | Required | Description |
|-------|----------|-------------|
| name | Yes | Identifier for the database (case-insensitive) |
| description | Yes | What data this database contains (used for auto-selection) |
| host | Yes | Database hostname |
| port | No | Port number (default: 3306) |
| database | Yes | Database name |
| user | Yes | Username |
| password | Yes | Password |
| ssl_disabled | No | Set to `true` to disable SSL (default: false) |
| ssl_ca | No | Path to CA certificate file |
| ssl_cert | No | Path to client certificate file |
| ssl_key | No | Path to client private key file |
## Usage
### List configured databases
```bash
python3 scripts/query.py --list
```
### Query a database
```bash
python3 scripts/query.py --db production --query "SELECT * FROM users LIMIT 10"
```
### List tables
```bash
python3 scripts/query.py --db production --tables
```
### Show schema
```bash
python3 scripts/query.py --db production --schema
```
### Limit results
```bash
python3 scripts/query.py --db production --query "SELECT * FROM orders" --limit 100
```
## Database Selection
Match user intent to database `description`:
| User asks about | Look for description containing |
|-----------------|--------------------------------|
| users, accounts | users, accounts, customers |
| orders, sales | orders, transactions, sales |
| analytics, metrics | analytics, metrics, reports |
| logs, events | logs, events, audit |
If unclear, run `--list` and ask user which database.
## Safety Features
- **Read-only session**: Connection uses MySQL `SET SESSION TRANSACTION READ ONLY` (primary protection)
- **Query validation**: Only SELECT, SHOW, DESCRIBE, EXPLAIN, WITH queries allowed
- **Single statement**: Multiple statements per query rejected
- **SSL support**: Configurable SSL with CA, client cert, and key support
- **Query timeout**: 30-second max_execution_time enforced (MySQL 5.7.8+)
- **Memory protection**: Max 10,000 rows per query to prevent OOM
- **Column width cap**: 100 char max per column for readable output
- **Credential sanitization**: Error messages don't leak passwords
## Troubleshooting
| Error | Solution |
|-------|----------|
| Config not found | Create `connections.json` in skill directory |
| Authentication failed | Check username/password in config |
| Connection timeout | Verify host/port, check firewall/VPN |
| SSL error | Try `"ssl_disabled": true` for local databases |
| Permission warning | Run `chmod 600 connections.json` |
| max_execution_time not supported | Upgrade to MySQL 5.7.8+ or MariaDB 10.1.1+ |
## Exit Codes
- **0**: Success
- **1**: Error (config missing, auth failed, invalid query, database error)
## Workflow
1. Run `--list` to show available databases
2. Match user intent to database description
3. Run `--tables` or `--schema` to explore structure
4. Execute query with appropriate LIMIT
© sanjay3290 · Apache-2.0 · sanjay3290/ai-skills
Similar skills
All skills for Data and databases →mysql by other authors comes first.