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/aron-valenzuela/mcp-sqlserver/claude-mdgit clone --depth 1 https://github.com/Aron-Valenzuela/MCP-SqlServerWrote 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/aron-valenzuela/mcp-sqlserver/claude-md)<a href="https://agentmods.dev/instructions/aron-valenzuela/mcp-sqlserver/claude-md"><img src="https://agentmods.dev/badge/instructions/aron-valenzuela/mcp-sqlserver/claude-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 | $0.00778 | $0.00778 |
| Opus 5 | $0.00389 | $0.00389 |
| Sonnet 5 | $0.00156 | $0.00156 |
| Haiku 4.5 | $0.00078 | $0.00078 |
Grade A, and why
MCP-SqlServer 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 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 — 107 lines — stays where its author put it; the contents beside it link to each section on GitHub.
CLAUDE.md
This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
Project Overview
This is a Model Context Protocol (MCP) server that allows Claude AI to connect to any SQL Server database. Each user downloads and runs this MCP locally on their own machine.
The user tells Claude which server and database to connect to — no hardcoded connections.
Setup (for each user)
1. Install dependencies
pip install mcp pyodbc anyio
Requires ODBC Driver 17 for SQL Server on the host machine.
2. Configure Claude Desktop
Add this to claude_desktop_config.json (Settings > Developer > Edit Config):
{
"mcpServers": {
"mcp-sqlserver": {
"command": "python",
"args": ["C:/ruta/completa/a/sqlserver-mcp/server.py"]
}
}
}
Replace the path with the actual location of server.py on your machine.
3. Optional: Auto-connect to a default database
Set environment variables to skip the conectar step:
{
"mcpServers": {
"mcp-sqlserver": {
"command": "python",
"args": ["C:/ruta/completa/a/sqlserver-mcp/server.py"],
"env": {
"DB_SERVER": "mi-servidor\\Instancia",
"DB_NAME": "MiBaseDeDatos",
"DB_AUTH_TYPE": "windows"
}
}
}
}
For SQL Server Auth, also set DB_USER and DB_PASSWORD.
Running the Server
The server runs automatically via Claude Desktop (stdio transport). For standalone testing:
python sqlserver-mcp/server.py
Architecture
MCP Server (sqlserver-mcp/server.py)
Single-file server using FastMCP with stdio transport. Exposes 9 tools:
Connection management:
| Tool | Purpose |
|---|---|
conectar(servidor, base_datos, tipo_auth, usuario?, password?) |
Connect to any SQL Server (Windows or SQL Auth) |
estado_conexion() |
Show current connection status |
desconectar() |
Disconnect current session |
Read-only data tools (require active connection):
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 · 107 lines · 778 tokens per session scan A 2dd8782bf366
MCP-SqlServer CLAUDE.md is an instructions file published in the GitHub repository Aron-Valenzuela/MCP-SqlServer (2 stars, last pushed 6mo ago), licensed MIT. It adds 778 tokens to every session, about $0.0039 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.
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.
plsql-intelligence AGENTS.md
Instructions for MuhDur/plsql-intelligence, covering agents.md — plsql-intelligence, founder constraints (plan.md §3, non-negotiable), plan rules to internalize (plan.md §4), rule 1 – absolute (do not ever violate this) and irreversible git & filesystem actions.