Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add neverinfamous/mysql-mcp --skill mysqlgit clone --depth 1 https://github.com/neverinfamous/mysql-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/neverinfamous/mysql-mcp/mysql)<a href="https://agentmods.dev/skills/neverinfamous/mysql-mcp/mysql"><img src="https://agentmods.dev/badge/skills/neverinfamous/mysql-mcp/mysql/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/neverinfamous/mysql-mcp/mysql"><img src="https://agentmods.dev/badge/skills/neverinfamous/mysql-mcp/mysql.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00059 | $0.01236 |
| Opus 5 | $0.00030 | $0.00618 |
| Sonnet 5 | $0.00012 | $0.00247 |
| Haiku 4.5 | $0.00006 | $0.00124 |
Grade A, and why
mysql scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 10d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
How it starts
The opening of the file, as written. The whole thing — 71 lines — stays where its author put it; the contents beside it link to each section on GitHub.
MySQL / MariaDB Production Standards
MySQL and MariaDB are relationship-driven databases, but AI agents MUST adhere to these strict behavioral boundaries when executing queries, utilizing the mysql-mcp server, or generating application code.
[!NOTE] Actively target 8.4 LTS or 9.0+ for production environments. Both MySQL 9.0+ and MariaDB now feature native
VECTORdata types and search capabilities.
1. Query Safety & Execution Rules
- Absolute Parameterization: You MUST ALWAYS use parameterized queries (
?). Under zero circumstances are you permitted to string-interpolate or concatenate variables into a raw SQL string. This is to enforce strict SQL-injection prevention. - Guarded Reads: Every top-level
SELECTstatement MUST contain aLIMITclause. Never useSELECT *in production code; always enumerate required columns explicitly. - Safe Destructive Ops:
DELETEandUPDATEqueries MUST include aWHEREclause. - DDL Destructive Ops:
TRUNCATE TABLE,DROP TABLE,DROP DATABASE,ALTER TABLE ... DROP COLUMN, andALTER TABLE ... RENAME COLUMNMUST require explicit user confirmation before execution. Never infer intent for these. - Action Scoping: Limit operations to single-statements. Do not stack multiple statements (
query1; query2;) in a single payload unless executing a batch migration. - Performance Validation: ALWAYS run
EXPLAIN(orEXPLAIN ANALYZEin MySQL 9.0+ for JSON output) before suggesting index optimizations or query rewrites to the user.
2. Connections & Transactions
- Connection Pooling: Always assume and design for connection pooling. Code evaluating database connections should handle acquiring from and releasing to a pool, avoiding connection leaks.
- Sizing Formula:
pool_size = (max_connections - reserved_admin) / app_instances. - Multiplexing: Utilize ProxySQL to handle connection multiplexing and read/write splitting. CRITICAL: Avoid anti-patterns that pin connections and kill multiplexing efficiency (e.g., long-running transactions, temporary tables,
SET @var, and caching prepared statements on the client without closing them).
- Sizing Formula:
- Data Mutability Scopes: Whenever executing writes spanning across multiple tables (e.g., inserts requiring foreign key links), they MUST be wrapped in a transaction block. You MUST implement a
ROLLBACKin everycatchblock for these operations.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 10d ago First seen · 71 lines · 59 tokens per session scan A 2e25fb007e32
mysql is a skill published in the GitHub repository neverinfamous/mysql-mcp (10 stars, last pushed 3d ago), licensed MIT. It adds 59 tokens to every session and 1,236 once invoked, about $0.0003 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other skills, from other repositories
dory
Use Dory as the official AI-native SQL workspace for agents. Use when the user asks to inspect or analyze databases, explore unknown schemas, debug data issues, run read-only SQL through Dory MCP, manage Dory Agent Runs, create or update SQL workspace tabs, work with saved queries, preserve query results, or hand SQL…
sqlike
Check SQL with sqlike — deterministic static analysis (validity, anti-patterns, rewrites, index advice) and query-equivalence verification. Use whenever you write, edit, review, or rewrite a SQL query, or need to prove two queries return the same results. Requires the sqlike MCP server (@sqlike/mcp) or the sqlike CLI…
graphjin-eval
Create, extend, run, baseline, and diagnose GraphJin agent evaluations through the graphjin eval CLI.
graphjin-env
Use when setting up a training or evaluation loop against a GraphJin agent environment — running the container, reading /health, driving episodes hosted or step-by-step or with your own agent over MCP, splitting train from eval, exporting trajectories, and deciding whether two rewards can be compared.
gonavi-cli
Operate databases through the GoNavi headless CLI — the gonavi executable shipped in verified GitHub Release archives. Covers listing/adding/importing saved connections, running SQL queries against saved connections or ad-hoc connection files, exporting result sets to csv/json/md/html/xlsx, batch-executing SQL files…
transactional-patterns
Use when working with @Transactional, multi-step database operations, distributed transactions, or any code that needs atomicity guarantees. Covers propagation rules, isolation levels, read-only optimization, and common pitfalls.