Borrowing it
Nothing to install: this file belongs to ChingEnLin/SQMCPaL. 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/ChingEnLin/SQMCPaL/main/CLAUDE.mdgit clone --depth 1 https://github.com/ChingEnLin/SQMCPaLWrote 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/chingenlin/sqmcpal/claude-md)<a href="https://agentmods.dev/instructions/chingenlin/sqmcpal/claude-md"><img src="https://agentmods.dev/badge/instructions/chingenlin/sqmcpal/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/chingenlin/sqmcpal/claude-md"><img src="https://agentmods.dev/badge/instructions/chingenlin/sqmcpal/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 | $0.01018 | $0.01018 |
| Opus 5.5 | $0.00407 | $0.00407 |
| Sonnet 5.5 | $0.00204 | $0.00204 |
| Haiku 4.5 | $0.00102 | $0.00102 |
Grade A, and why
SQMCPaL 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 2mo 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 — 39 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
Purpose
Read-only MCP server exposing your Azure Database for PostgreSQL Flexible Servers to any MCP client, authenticating via your existing az login session — for individual local dev use. SQL sibling of QueryMCPal (Cosmos Mongo API) and BlobMCPal (Azure Storage).
Tech stack
- Python >=3.11 (Docker image and ruff/mypy target 3.12), packaged with hatchling.
- MCP:
mcp[cli]>=2.0using theMCPServerdecorator API over stdio. - Data:
psycopg(v3) against PostgreSQL Flexible Server. - Azure:
azure-identity(DefaultAzureCredential) + raw ARM viarequestsfor server discovery. cachetoolsfor TTL caching of ARM responses.
Run / build / test
- Run from source:
uvx sqmcpal(orsqmcpalconsole script afterpip install -e .). - Dev setup:
uv venv --python 3.12 && uv pip install -e ".[dev]" && pre-commit install. - Self-check:
python test_sqmcpal.py— asserts the read-only SQL guard. The only test; the DB layer is verified by connecting to a real server. - Lint/type checks:
pre-commit run --all-files, i.e.ruff check,ruff format --check,mypy --strict. - Smoke test: pipe an MCP
initializeJSON-RPC message intosqmcpaland expectserverInfo.name = "sqmcpal"(see README). - Build Docker image:
docker build --platform linux/arm64 -t sqmcpal:dev .(uselinux/amd64on Intel/Linux).
Architecture
src/sqmcpal/:
server.py— MCP entrypoint (main). One@app.tool()function per tool; schemas are derived from type hints and docstrings, so the docstring is the tool description the model reads. Owns the result cap and the single in-processsession.azure_service.py—DefaultAzureCredentialauth, ARM-based flexible-server discovery across subscriptions, and the Entra token used as the DB password. Login role is read from the token's ownupnclaim.pg_service.py— read-only PostgreSQL ops (catalog, describe, query, count, distinct); caches connections per (host, database, user) and reconnects when the token nears expiry. Ownsassert_read_only.context.py—SessionContextdataclass holding active server/database/schema.
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.
- 2mo ago First seen · 39 lines · 1,018 tokens per session scan A 378c4748fafd
SQMCPaL CLAUDE.md is an instructions file published in the GitHub repository ChingEnLin/SQMCPaL (0 stars, last pushed 3mo ago), licensed MIT. It adds 1,018 tokens to every session, about $0.0041 per session on Opus 5.5. 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.
SQMCPaL CLAUDE.md compared with instructions from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| SQMCPaL CLAUDE.mdChingEnLin/SQMCPaL | Instructions file | 0 | 3mo ago | MIT | A | 1,018 | Claude Code |
| vscode buildNext.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 9,719 | GitHub Copilot |
| next.js AGENTS.mdvercel/next.js | Instructions file | 143k | yesterday | MIT | A | 7,461 | Codex, OpenCode |
| langchain AGENTS.mdlangchain-ai/langchain | Instructions file | 149k | yesterday | MIT | A | 4,680 | Codex, OpenCode |
| vscode oss-third-party-notices.instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 5,516 | GitHub Copilot |
| vscode copilot-instructions.mdmicrosoft/vscode | Instructions file | 195k | yesterday | MIT | A | 3,093 | GitHub Copilot |
| deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness | Instructions file | 274k | 2d ago | MIT | A | 4,313 | Codex, OpenCode |