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/eamonboyle/mssql-mcp/agents-mdgit clone --depth 1 https://github.com/eamonboyle/mssql-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/eamonboyle/mssql-mcp/agents-md)<a href="https://agentmods.dev/instructions/eamonboyle/mssql-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/eamonboyle/mssql-mcp/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 | $0.01107 | $0.01107 |
| Opus 5 | $0.00553 | $0.00553 |
| Sonnet 5 | $0.00221 | $0.00221 |
| Haiku 4.5 | $0.00111 | $0.00111 |
Grade A, and why
mssql-mcp 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 4d 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 — 54 lines — stays where its author put it; the contents beside it link to each section on GitHub.
AGENTS.md
Cursor Cloud specific instructions
This repo is a single Node.js/TypeScript product: the MSSQL MCP Server (@eamonboyle/mssql-mcp). It is an MCP (Model Context Protocol) server that exposes tools/resources/prompts for querying and managing a Microsoft SQL Server database. There is no web UI. Standard commands (build, lint, test, start, watch) live in package.json and are documented in README.md / CONTRIBUTING.md.
Lint / test / build (no database required)
npm run build,npm run lint,npm testall pass with no external services — the unit tests mock the DB (seesrc/__tests__/). Use these for fast validation.- The
preparescript runsnpm run buildautomatically onnpm install, sodist/exists after install.
Full MCP tool E2E (Docker + SQL required)
After the database is up, run npm run test:e2e to exercise every registered MCP tool against AppDB / ReportingDB and print a per-tool PASS/FAIL report.
cp .env.example .env # if needed
npm run db:up # start Docker MSSQL + seed (skip if already healthy)
npm run test:e2e # builds, starts HTTP server (ENABLE_DDL=true), runs all tools
Scripts: scripts/e2e-mcp-tools.sh (orchestrator) and scripts/e2e-mcp-tools.mjs (harness). Details: docs/dev-database.md.
Cloud agent checklist:
- Start Docker if needed (
dockerd; usesg docker -c '...'when the socket requires thedockergroup). npm run db:up— if the volume is corrupt,npm run db:reset.npm run test:e2e— exit code 0 means all tools passed.- Server log on failure:
/tmp/mssql-mcp-e2e-server.log
Running the server end-to-end (needs a SQL Server)
Use the repo's Docker Compose stack (seeded AppDB + ReportingDB). Details: docs/dev-database.md.
cp .env.example .env # if you do not already have a .env
npm run db:up # starts mssql-mcp-dev, waits, applies docker/mssql/init/*.sql
npm start # loads .env via dotenv (stdio). For HTTP: MCP_TRANSPORT=http npm start
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.
- 4d ago First seen · 54 lines · 1,107 tokens per session scan A 608685a31963
mssql-mcp AGENTS.md is an instructions file published in the GitHub repository eamonboyle/mssql-mcp (5 stars, last pushed 3d ago), licensed MIT. It adds 1,107 tokens to every session, about $0.0055 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
seekstone CLAUDE.md
Instructions for shaqmughal/seekstone, covering claude.md, what this repo is, commands, the harness itself (run after npm install) and architecture.
plan-forge database.instructions.md
Database patterns for .NET — Dapper/EF Core, parameterized queries, migration strategy.
llm-safe-sql AGENTS.md
AGENTS.md instructions for hyuga611/llm-safe-sql, covering notes for coding agents, what this project is, rules that are not style preferences, where things are and before you say you are done.
pg-dash CLAUDE.md
Claude Code instructions for indiekitai/pg-dash, covering pg-dash claude.md, 项目结构, 构建与测试, 发版纪律（强制） and 发版检查清单（每次 npm publish 前必须按序执行）.
shop-ce AGENTS.md
AGENTS.md instructions for o3-shop/shop-ce, covering agent notes for o3-shop (shop-ce), docker setup, running tests and database.
jdbc-driver CLAUDE.md
Claude Code instructions for keboola/jdbc-driver, covering claude.md, project overview, build & test commands, jdbc driver and vscode sqltools extension.