mcp-sqlserver CLAUDE.md

A project guide for mcp-sqlserver, a program that lets AI assistants work with Microsoft SQL Server databases through the Model Context Protocol. It documents the project’s code, tools, dependencies, and development conventions.

In plain words
What is it for?
Use it when developing or maintaining the mcp-sqlserver package, including database schema tools, queries, table changes, stored procedures, performance checks, and server administration features.
Why use it?
It gives an AI assistant the context needed to change the server safely and consistently. It also records important requirements such as the Node.js version, TypeScript settings, and import rules.

Instructions file

Install

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.

agentmods
npx agentmods add instructions/gunvertugberk/mcp-sqlserver/claude-md
Clone the repo
git clone --depth 1 https://github.com/gunvertugberk/mcp-sqlserver
Per session 1,726 This file is loaded in full into every session.
When invoked 1,726 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

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.

ModelPer sessionOnce invoked
Fable 5 $0.01726 $0.01726
Opus 5 $0.00863 $0.00863
Sonnet 5 $0.00345 $0.00345
Haiku 4.5 $0.00173 $0.00173

Measured 2d ago against content hash 90e8b931bc08, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

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 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.

Origin

Copies of this mod

1 near-identical copy found in the catalogue:

CLAUDE.md · 98 lines

How it starts

The opening of the file, as written. The whole thing — 98 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mcp-sqlserver — Project Guide for Claude

This file tells Claude (and any AI assistant using Claude Code / MCP) how to work in this repo. Read it in full before making changes. For deeper rules, follow the links at the bottom — each file is a focused, bite-sized ruleset.

What this project is

@tugberkgunver/mcp-sqlserver is a Model Context Protocol (MCP) server for Microsoft SQL Server. It exposes 39 tools across 7 categories (schema discovery, query, DDL, stored procedures, performance, DBA diagnostics, developer utilities, server management) so AI assistants can talk to SQL Server with enterprise-grade security controls.

  • Package: @tugberkgunver/mcp-sqlserver on npm
  • Repo: gunvertugberk/mcp-sqlserver on GitHub
  • Current version: see package.json (version) and src/server.ts (McpServer version string) — keep them in sync
  • License: MIT

Stack

  • Language: TypeScript 5.8, strict: true
  • Runtime: Node.js >=18
  • Module system: Node16 ESM — imports must use .js extension even when importing .ts files (see coding-standards.md)
  • Target: ES2022
  • Key deps: @modelcontextprotocol/sdk, mssql (tedious), yaml, zod
  • Optional dep: msnodesqlv8 for Windows SSPI auth

Commands

npm install          # install dependencies
npm run build        # tsc → dist/
npm run dev          # tsc --watch
npm test             # vitest run (238 tests)
npm run test:watch   # vitest in watch mode
npm start            # node dist/index.js (after build)
npm start -- --config ./mssql-mcp.yaml
npm start -- --http 3000

Testing: Vitest with 238 tests across 10 files covering security utils, formatters, and all 38 tool handlers. Run npm test before every commit.

Directory map

src/
├── index.ts               # CLI entry: arg parsing, transport (stdio/http), graceful shutdown
├── server.ts              # createServer(config) — wires all tool groups, registers list_servers
├── config.ts              # AppConfig types, loadConfig(), resolveServer(), single+multi-server loading
├── database.ts            # Connection pool per serverName, buildSqlConfig() per auth type, executeQuery()
├── utils/
│   ├── security.ts        # escapeIdentifier, validateQuery, isDatabaseAllowed, isSchemaAllowed,
│   │                      # applyMasking, ensureRowLimit, SecurityError
│   └── formatter.ts       # formatResultSet (markdown), formatResultSetJson, ISO date handling
└── tools/
    ├── schema.ts          # 9 schema discovery tools
    ├── query.ts           # execute_query, execute_mutation
    ├── ddl.ts             # execute_ddl (admin / allowDDL only)
    ├── procedure.ts       # list_procedures, describe_procedure, execute_procedure
    ├── performance.ts     # query plans, active queries, table/index/server/db stats, missing indexes
    ├── dba.ts             # wait stats, deadlocks, blocking, backups, query store, rebuild index, health
    └── utility.ts         # compare_schemas, generate_code, ER diagram, sample/test data, export_query

Read the full file on GitHub · 98 lines

Changes

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.

  1. 2d ago First seen · 98 lines · 1,726 tokens per session scan A 90e8b931bc08

Subscribe to this mod's changes

mcp-sqlserver CLAUDE.md is an instructions file published in the GitHub repository gunvertugberk/mcp-sqlserver (3 stars, last pushed 4mo ago), licensed MIT. It adds 1,726 tokens to every session, about $0.0086 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.

Related

Other instructions, from other repositories

DevoxxGenieIDEAPlugin AGENTS.md

Instructions for devoxx/DevoxxGenieIDEAPlugin, covering agents.md, project overview, build & development commands, building and testing.

devoxx/DevoxxGenieIDEAPlugin · 2,849 tokens

DevoxxGenieIDEAPlugin CLAUDE.md

Instructions for devoxx/DevoxxGenieIDEAPlugin, covering claude.md, project overview, threading constraints, workflow rules and git workflow.

devoxx/DevoxxGenieIDEAPlugin · 1,285 tokens

mcp-documentation-server copilot-instructions.md

Instructions for andrea9293/mcp-documentation-server, covering mcp documentation server - ai coding agent instructions, architecture overview, core components, server entry point (src/server.ts) and embedding providers (src/embedding-provider.ts).

andrea9293/mcp-documentation-server · 1,147 tokens

DevoxxGenieIDEAPlugin GEMINI.md

Instructions for devoxx/DevoxxGenieIDEAPlugin, a project described as: DevoxxGenie is an agentic plugin for IntelliJ IDEA that uses local LLM's (Ollama, LMStudio, GPT4All, Jan and Llama.cpp) and Cloud based LLMs to help review, test, explain your project code. Latest version now also supports Spec Driven Development…

devoxx/DevoxxGenieIDEAPlugin · 257 tokens

opencode-bar AGENTS.md

Instructions for opgginc/opencode-bar, covering important restriction, coding rules, branding guides, ui styling rules and explicit 'used' or 'left'.

opgginc/opencode-bar · 11,821 tokens

optio CLAUDE.md

Instructions for jonwiggins/optio, covering claude.md, what is optio?, architecture, pod-per-repo with worktrees and worktree lifecycle.

jonwiggins/optio · 6,856 tokens