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/harryvaldez/mcp-sql-server/agents-mdgit clone --depth 1 https://github.com/harryvaldez/mcp-sql-serverWrote 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/harryvaldez/mcp-sql-server/agents-md)<a href="https://agentmods.dev/instructions/harryvaldez/mcp-sql-server/agents-md"><img src="https://agentmods.dev/badge/instructions/harryvaldez/mcp-sql-server/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 | $0.00631 | $0.00631 |
| Opus 5 | $0.00316 | $0.00316 |
| Sonnet 5 | $0.00126 | $0.00126 |
| Haiku 4.5 | $0.00063 | $0.00063 |
Grade A, and why
mcp-sql-server 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 3d 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 — 66 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS
Guidance for AI coding agents working in this repository.
Project Snapshot
- Python 3.11+ FastMCP + FastAPI service for dual SQL Server 2019 instances.
- Strong read-only posture with controlled-write guardrails, rate limiting, and diagnostics.
- Runtime entry point: src/server.py.
Fast Start
- Create/activate a virtual environment.
- Install dependencies:
pip install -e .[dev]
- Run checks before proposing changes:
ruff check .pytest -q
Architecture Boundaries
- Service/bootstrap: src/server.py, src/config_loader.py
- SQL access and pooling: src/db/
- Security and policy enforcement: src/middleware/, src/security/
- Tool contracts and registration: src/tools/
- Diagnostics endpoints and summaries: src/diagnostics/
When adding features, keep changes inside the relevant boundary and avoid cross-cutting edits unless required.
Non-Negotiable Guardrails
- Preserve read-only defaults and write controls:
- Policy: config/runtime-policy.yaml
- Denylist: policy/sql-denylist.yaml
- Allowlist: policy/sql-allowlist.yaml
- Keep strict input validation for all tools and SQL-facing parameters.
- Never expose secrets or connection details in logs, diagnostics, or errors.
- Preserve deterministic error contracts and redaction behavior.
- Do not weaken audit logging or rate limiting paths.
Change Workflow
- Read nearby tests first in tests/.
- Implement minimal, focused changes.
- Add/update tests for behavior changes.
- Run
ruff check .andpytest -q. - Update docs if behavior/config changes.
High-Value References
- Contribution process: CONTRIBUTING.md
- Security policy/reporting: SECURITY.md
- Access model and controlled write: docs/access-levels-and-controlled-write.md
- Tool inventory/contracts: docs/mcp-tool-catalog.md
- Docker runtime: docs/run-mcp-server-with-docker.md
- Operational runbooks:
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.
- 3d ago First seen · 66 lines · 631 tokens per session scan A efdace12f810
mcp-sql-server AGENTS.md is an instructions file published in the GitHub repository harryvaldez/mcp-sql-server (0 stars, last pushed 22d ago), licensed MIT. It adds 631 tokens to every session, about $0.0032 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
nimbus-copiloto CLAUDE.md
Claude Code instructions for ruben-salas20/nimbus-copiloto, covering instrucciones del proyecto — nimbus copiloto, qué es este repositorio, tu rol en las sesiones de trabajo, la regla número uno and cuándo sí escribes código.
fastmcp CLAUDE.md
Claude Code instructions for PrefectHQ/fastmcp, covering fastmcp development guidelines, required development workflow, repository structure, core mcp objects and development rules.
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
substack-gateway-oss CLAUDE.md
Instructions for jakub-k-slys/substack-gateway-oss, covering claude.md, commands, install dependencies (dev included, all workspace members), run the server (dev mode with reload) and lint.
mcp-turso-cloud CLAUDE.md
Instructions for spences10/mcp-turso-cloud, covering claude.md, unbreakable rules, project overview, development commands and architecture & key concepts.
intpot AGENTS.md
Instructions for tugrulguner/intpot, covering agents.md, what intpot is, layout, coding guidelines and workflow.