Borrowing it
Nothing to install: this file belongs to MahmoudHassanMustafa/querybridge-mcp. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.
curl -O https://raw.githubusercontent.com/MahmoudHassanMustafa/querybridge-mcp/main/CLAUDE.mdgit clone --depth 1 https://github.com/MahmoudHassanMustafa/querybridge-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/instructions/mahmoudhassanmustafa/querybridge-mcp/claude-md)<a href="https://agentmods.dev/instructions/mahmoudhassanmustafa/querybridge-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/mahmoudhassanmustafa/querybridge-mcp/claude-md/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/instructions/mahmoudhassanmustafa/querybridge-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/mahmoudhassanmustafa/querybridge-mcp/claude-md.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 | $0.01999 | $0.01999 |
| Opus 5 | $0.01000 | $0.01000 |
| Sonnet 5 | $0.00400 | $0.00400 |
| Haiku 4.5 | $0.00200 | $0.00200 |
Grade A, and why
querybridge-mcp CLAUDE.md 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 — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Operational notes for agents working in this repo. Read CONVENTIONS.md for the full set of rules; this file is the 60-second briefing.
Quick orientation
- What it is. An MCP server connecting Claude (and other MCP clients) to MySQL. Ships two transports: stdio (default) and Streamable HTTP (with bearer auth). 40 tools across 9 families (see
README.md→ Tools). - Stack. TypeScript, Node ≥ 20, pnpm (not npm —
packageManagerfield inpackage.json), Vitest,mysql2/promise,ssh2,@modelcontextprotocol/sdk. - Architecture.
Transport → Tools → Infrastructure. Enforced by.dependency-cruiser.cjs;CONVENTIONS.md§1 has the prose. Don't import upward. - Entry points.
src/server/index.tsdispatches stdio vs HTTP.src/tools/index.tsis the tool-registry barrel.
Commands
pnpm install # also installs the husky pre-commit hook via `prepare`
pnpm build # tsc
pnpm lint # eslint + dep-cruiser (architecture enforcement)
pnpm test # unit tests (Vitest)
pnpm test:integration # MySQL Testcontainers — needs Docker running
pnpm format # prettier --write across the repo
pnpm format:check # prettier --check (no writes) — what CI would run
pnpm lint && pnpm test covers everything CI does. The pre-commit hook handles the formatting + ESLint pass on staged files automatically — no need to remember pnpm format before each commit.
Release flow
Changesets-driven. Never bump versions manually.
- Any user-visible change → add
.changeset/<short-name>.mdwith the appropriate bump (patch/minor/major) and a clear changelog entry. - Merging to main triggers the Changesets bot to open or update a "Version Packages" PR.
- Merging the Version Packages PR pushes a
vX.Y.Ztag →release.ymlpublishes to npm (with Sigstore provenance) and GHCR (multi-arch + SBOM).
Hard rules
- Never commit
config.json. It contains DB credentials.config.example.jsonis the sanitized template. - Never skip pre-commit hooks (
--no-verify). The hook (.husky/pre-commit) runslint-staged, which callseslint --fix --max-warnings=0andprettier --writeon staged files only. Fast (~1s typical) and fixable — if it fails, fix the root cause instead of bypassing. - Never reach for
mysql2outsidesrc/connection.ts,src/db/cancel.ts, orsrc/tools/query-tools.ts. Pool hardening (LOCAL_FILESblock, SSL setup,SET SESSION transaction_read_only) only happens inbuildPoolOptions. Bypassing it loses defenses.dep-cruiserenforces. - Every new tool ships with an integration test.
MockRunnerunit tests are not enough — real MySQL catches behavior the mock doesn't (CONVENTIONS.md §8). - Read-only by default. Two layers, both required:
getConnectionConfig().readonlyflag check ANDisReadOnlyQuery()SQL whitelist. Don't skip either. config.jsonis gitignored but.changeset/config.jsonis not — the gitignore has a!.changeset/config.jsonnegation. Don't break 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.
- 10d ago First seen · 70 lines · 1,999 tokens per session scan A acb2bc0bc9fb
querybridge-mcp CLAUDE.md is an instructions file published in the GitHub repository MahmoudHassanMustafa/querybridge-mcp (1 stars, last pushed 22d ago), licensed MIT. It adds 1,999 tokens to every session, about $0.0100 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 instructions, from other repositories
data-scientist copilot-instructions.md
Repository instructions for a data-science workflow in GitHub Copilot, covering datasets, statistics, and analysis files.
next.js AGENTS.md
AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.
codex AGENTS.md
AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.
vscode buildNext.instructions.md
Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).
spec-kit AGENTS.md
AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.
vscode oss-third-party-notices.instructions.md
Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).