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 instructions/lukleh/mcp-read-only-sql/agents-mdgit clone --depth 1 https://github.com/lukleh/mcp-read-only-sqlWrote 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/lukleh/mcp-read-only-sql/agents-md)<a href="https://agentmods.dev/instructions/lukleh/mcp-read-only-sql/agents-md"><img src="https://agentmods.dev/badge/instructions/lukleh/mcp-read-only-sql/agents-md.svg" alt="Measured on agentmods" 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 | $0.00767 | $0.00767 |
| Opus 5 | $0.00383 | $0.00383 |
| Sonnet 5 | $0.00153 | $0.00153 |
| Haiku 4.5 | $0.00077 | $0.00077 |
Grade A, and why
mcp-read-only-sql AGENTS.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 2d 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 — 28 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Repository Guidelines
Project Structure & Module Organization
src/mcp_read_only_sql/server.py exposes the MCP entry point, while src/mcp_read_only_sql/connectors/ hosts the PostgreSQL and ClickHouse adapters for both CLI and Python implementations. Cross-cutting helpers (ssh_tunnel.py, ssh_tunnel_cli.py, sql_guard.py, TSV formatting, timeout handling) live in src/mcp_read_only_sql/utils/. Configuration tooling, including DBeaver import and manifest validation, sits in src/mcp_read_only_sql/config/ and src/mcp_read_only_sql/tools/. Tests are grouped in tests/, and Docker fixtures for integration runs reside in docker/. The package ships a sample connections.yaml, and runtime config lives under ~/.config/lukleh/mcp-read-only-sql/.
Build, Test, and Development Commands
uv sync --extra dev— install runtime and development dependencies.uv run mcp-read-only-sqlorjust run— start the MCP server with the resolved runtime config directory.uv run mcp-read-only-sql --write-sample-configorjust write-sample-config— bootstrapconnections.yamlwithout cloning-path assumptions.uv run mcp-read-only-sql import-dbeaver ...orjust import-dbeaver— convert a DBeaver workspace intoconnections.yaml.just validate— lintconnections.yamlagainst the schema and safety checks.just test— spin up Dockerized fixtures and execute the full pytest suite via./run_tests.sh.uv run python -m pytest tests/test_sql_guard.py— run an individual module when iterating quickly.uv run ruff check .— lint the Python tree.uv run ty check— type-check the fullsrc/tree; there are no remaining package excludes.
Coding Style & Naming Conventions
Target Python 3.11+, four-space indentation, and Unix newlines. Lint via uv run ruff check . and keep uv run ty check passing for src/. Modules and callables use snake_case, classes PascalCase (e.g., TestReadOnlyGuards), and immutable settings uppercase (DEFAULT_QUERY_TIMEOUT). Apply type hints on public surfaces and keep docstrings brief, emphasizing read-only guarantees and connector behavior.
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.
- 2d ago First seen · 28 lines · 767 tokens per session scan A 5b577da87f6f
mcp-read-only-sql AGENTS.md is an instructions file published in the GitHub repository lukleh/mcp-read-only-sql (0 stars, last pushed 1mo ago), licensed MIT. It adds 767 tokens to every session, about $0.0038 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
graphjin AGENTS.md
AGENTS.md instructions for dosco/graphjin, covering graphjin agent guide, architectural overview, directory structure & responsibilities, build commands and coding guidelines.
clickhouse-go AGENTS.md
AGENTS.md instructions for ClickHouse/clickhouse-go, a project described as: Golang driver for ClickHouse.
sql-benchmarks-dagster AGENTS.md
Instructions for rctruta/sql-benchmarks-dagster, covering agentic benchmarking protocol, three ways in, the agentic loop (cli form), reading results — pick the right shape and template discovery (rest api).
supabase studio-shortcuts.instructions.md
Instructions for supabase/supabase, covering studio shortcut review rules, core principle, when to flag, preferred pattern and search inputs.
supabase studio-e2e-tests.instructions.md
Instructions for supabase/supabase, covering studio e2e test review rules, selector priority (best to worst), patterns to flag and good practices to encourage.
supabase studio-testing.instructions.md
Instructions for supabase/supabase, covering studio testing review rules, core principle, when to comment, which test type to suggest and reference.