tsql-mcp-server: Instructions file for Claude Code

CLAUDE.md

tsql-mcp-server CLAUDE.md is an instructions file for Claude Code from Popplywop/tsql-mcp-server. It costs 798 tokens per session, scanned A, original, MIT.

Repository instructions for an MCP server that connects AI assistants to Microsoft SQL Server databases. It supports database queries, stored procedures, and limited schema inspection through a standard assistant-to-tool connection.

In plain words
What is it for?
Use them when developing, configuring, or testing tools that inspect SQL Server databases or execute approved queries and stored procedures.
Why use it?
They explain the project's .NET structure, connection options, and read-only and SQL-injection safeguards before database work begins.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: mentions CLAUDE.md; mentions Claude Code.

This is Popplywop/tsql-mcp-server's own configuration. It tells Claude Code how to work on tsql-mcp-server itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything tsql-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Popplywop/tsql-mcp-server. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/Popplywop/tsql-mcp-server/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Popplywop/tsql-mcp-server

Made for: Claude Code.

Wrote 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.

agentmods badge for tsql-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/popplywop/tsql-mcp-server/claude-md/github.svg)](https://agentmods.dev/instructions/popplywop/tsql-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/popplywop/tsql-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/popplywop/tsql-mcp-server/claude-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for tsql-mcp-server CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/popplywop/tsql-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/popplywop/tsql-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 798 This file is loaded in full into every session.
When invoked 798 The same file — it is already loaded in full.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
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 5.1 $0.00798 $0.00798
Opus 5 $0.00399 $0.00399
Sonnet 5 $0.00160 $0.00160
Haiku 4.5 $0.00080 $0.00080

Measured 9d ago against content hash b9ae631ed9a5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

tsql-mcp-server 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 9d 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.

CLAUDE.md · 96 lines

How it starts

The opening of the file, as written. The whole thing — 96 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/claude-code) when working with this repository.

Project Overview

This is a Model Context Protocol (MCP) server for SQL Server databases. It allows LLMs to query and inspect SQL Server databases through a standardized protocol using stdio transport.

Tech Stack

  • .NET 10.0 - Target framework
  • ModelContextProtocol SDK (0.5.0-preview.1) - MCP server implementation
  • CommandLineParser - CLI argument parsing
  • Microsoft.Data.SqlClient - SQL Server connectivity

Project Structure

src/
├── Program.cs              # Entry point, host configuration
├── Options.cs              # CLI options (--dsn, --env-var, --read-only)
├── Tools/
│   ├── QueryTool.cs        # ExecuteQuery MCP tool
│   ├── StoredProcedureTool.cs  # ExecuteStoredProcedure MCP tool
│   └── SchemaTool.cs       # Lightweight schema exploration tools
├── Services/
│   ├── QueryService.cs     # Query execution with read-only validation
│   ├── SqlConnectionService.cs
│   ├── SqlConnectionFactory.cs
│   ├── SqlInjectionValidationService.cs
│   └── DatabaseMetadataCache.cs
├── Handlers/
│   └── DatabaseResourceHandler.cs  # MCP resource handlers
└── Models/                 # Data models (TableInfo, ColumnInfo, etc.)
tests/
└── tsql-mcp-server-tests/  # Unit tests (xUnit)

Build & Run Commands

# Build
dotnet build src/tsql-mcp-server.csproj

# Run with connection string
dotnet run --project src/tsql-mcp-server.csproj -- --dsn "Server=...;Database=...;..."

# Run in read-only mode
dotnet run --project src/tsql-mcp-server.csproj -- --dsn "..." --read-only

# Run tests
dotnet test

# Build Docker image
docker build -t tsql-mcp-server .

# Run Docker container
docker run -i tsql-mcp-server --dsn "Server=host.docker.internal;Database=...;..."

Key Features

  1. Read-Only Mode (--read-only): Blocks INSERT, UPDATE, DELETE, TRUNCATE, DROP, ALTER, CREATE, MERGE operations
  2. SQL Injection Prevention: Built-in validation in SqlInjectionValidationService
  3. Stored Procedure Execution: Safe execution with parameterized inputs
  4. Resource Caching: 10-minute TTL cache for schema metadata
  5. Token Optimization: Compact JSON, optional definitions, character limits, schema tools

Read the full file on GitHub · 96 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. 9d ago First seen · 96 lines · 798 tokens per session scan A b9ae631ed9a5

Subscribe to this mod's changes

tsql-mcp-server CLAUDE.md is an instructions file published in the GitHub repository Popplywop/tsql-mcp-server (7 stars, last pushed 7mo ago), licensed MIT. It adds 798 tokens to every session, about $0.0040 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