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 agentmods add commands/efilkucf/mysql-mcp-plugin/setupgit clone --depth 1 https://github.com/Efilkucf/mysql-mcp-pluginWhat 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 | $0.00016 | $0.00915 |
| Opus 5 | $0.00008 | $0.00458 |
| Sonnet 5 | $0.00003 | $0.00183 |
| Haiku 4.5 | $0.00002 | $0.00092 |
Grade A, and why
setup scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directorieslowAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
|| find ~/.claude/plugins -name cli.js -path '*mysql*' -not -path '*/node_modules/*' 2>/dev/null | head -1 Downgraded: this mod is about security review, or the phrase is quoted, so it is likely naming the pattern rather than instructing it.
How it starts
The opening of the file, as written. The whole thing — 88 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Walk the user through first-time setup. They may never have seen this plugin before, so explain the model before collecting details.
1. Check whether anything is already configured
Resolve the CLI path, then list:
ls "${CLAUDE_PLUGIN_ROOT}/dist/cli.js" 2>/dev/null \
|| find ~/.claude/plugins -name cli.js -path '*mysql*' -not -path '*/node_modules/*' 2>/dev/null | head -1
node <resolved-path> list
If connections already exist, say so and ask whether they want to add another or just review what's there. Don't run the whole walkthrough at someone who is already set up.
If they have a legacy MYSQL_SERVERS env setup in ~/.claude.json, suggest
/mysql:import instead — it migrates everything in one step.
2. Explain the model — briefly, then stop
Cover these three points in a few sentences each. Do not pad it out.
Capabilities. Each connection declares what SQL is allowed: select,
schema_read, insert, update, delete, ddl, drop, admin. Anything
outside the set is refused before it runs — twice, once by a hook before the tool
is called and once by the server before it executes.
MySQL GRANTs are the real boundary. This is the point people miss, so be direct about it. The capability list catches mistakes — a wrong connection name, a model error, something injected into the conversation. It is not a security boundary. The database's own privileges are. Give this plugin a MySQL account that holds only the privileges you are willing for it to have.
Therefore: do not point it at root. If they are about to, say plainly that
root means the capability setting is the only thing standing between a mistake
and a dropped table, and that one /mysql:grant … drop removes even that. Offer
the alternative:
CREATE USER 'claude_ro'@'%' IDENTIFIED BY '<password>';
GRANT SELECT ON <database>.* TO 'claude_ro'@'%';
Then recommend they come back once that account exists. If they want to proceed with a privileged account anyway, that is their call — note it once and continue without repeating it.
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.
- yesterday First seen · 88 lines · 16 tokens per session scan A 9ec62fd171ad
setup is a command published in the GitHub repository Efilkucf/mysql-mcp-plugin (0 stars, last pushed 19d ago), licensed MIT. It adds 16 tokens to every session and 915 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other commands, from other repositories
checklist
Generate a custom checklist for the current feature based on user requirements.
clarify
Identify underspecified areas in the current feature spec by asking up to 5 highly targeted clarification questions and encoding answers back into the spec.
specify
Create or update the feature specification from a natural language feature description.
analyze
Perform a non-destructive cross-artifact consistency and quality analysis across spec.md, plan.md, and tasks.md after task generation.
constitution
Create or update the project constitution from interactive or provided principle inputs.
converge
Assess the current codebase against the feature's spec, plan, and tasks, then append any remaining unbuilt work as new tasks to tasks.md so implement can complete it.