What is LocalDB-MCP CLAUDE.md?

A repository instruction document for working on a Rust server that connects AI agents to Microsoft SQL Server Express LocalDB on Windows. LocalDB is Microsoft's lightweight local version of SQL Server.

Use it when changing this repository, especially for managing database instances, running SQL scripts, discovering databases, or inspecting schemas.

It gives the coding agent the project's rules, architecture references, security requirements, and testing expectations.

How HermesSilva/LocalDB-MCP configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to HermesSilva/LocalDB-MCP. 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/HermesSilva/LocalDB-MCP/master/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/HermesSilva/LocalDB-MCP

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/hermessilva/localdb-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/hermessilva/localdb-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/hermessilva/localdb-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hermessilva/localdb-mcp/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/hermessilva/localdb-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/hermessilva/localdb-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 862 This file is loaded in full into every session.

When invoked 862 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.

Model	Per session	Once invoked
Fable 5.1	$0.00862	$0.00862
Opus 5	$0.00431	$0.00431
Sonnet 5	$0.00172	$0.00172
Haiku 4.5	$0.00086	$0.00086

Measured 9d ago against content hash 844aa97b2316, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

LocalDB-MCP 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 · 46 lines

How it starts

The opening of the file, as written. The whole thing — 46 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Guide for Claude Code (and any agent) working in this repository.

What this project is

mssql-localdb-mcp — an MCP (Model Context Protocol) server written in Rust that gives AI agents full access to Microsoft SQL Server Express LocalDB on Windows: instance management, T-SQL script execution, discovery of loose databases in project folders, schema introspection.

Reference documents (read before any structural change):

docs/PLANNING.md — roadmap, phases, scope of each milestone.
docs/ARCHITECTURE.md — modules, data flow, technical decisions and why.
docs/MCP_SPEC.md — exact contract of every tool/resource/prompt exposed over MCP (source of truth for names, input/output schemas).
docs/SECURITY.md — threat model and mandatory guardrails.

If one of these documents diverges from the code, the code is wrong (or the doc is stale — update the doc in the same PR).

Non-negotiable rules

Platform: Windows only. Don't add cross-platform cfg "just in case" — LocalDB doesn't exist outside Windows. #[cfg(windows)] is implicit across the whole project, no need to spread the annotation around.
stdout is sacred: the MCP stdio transport uses stdout for the JSON-RPC protocol. No println!, log, or subprocess output can leak to stdout. Logging always goes through tracing configured for stderr.
No SQL Auth: Windows Integrated Authentication only. Don't add a password field to any tool or config. This is a deliberate security decision, not a gap.
Destructive guardrail is mandatory: any tool running DDL/DML classified as destructive (security::classify) needs a confirm: true field in its input. Don't remove that check "to simplify". See docs/SECURITY.md.
Folder scan is allowlist-restricted: db_scan_folder never scans outside the roots configured in config.toml. Don't add a recursive scan of all of C:\ or a fallback of "scan everything if unconfigured".
rmcp is the official SDK: don't swap it for a homegrown MCP protocol implementation or another third-party crate.
Everything in English: this is a public/published project — code, comments, docs, commit messages, and everything protocol-facing (tool descriptions, error messages) are all in English, regardless of the language used in conversation with the user. Commit messages follow Conventional Commits (feat:, fix:, chore:, etc.).

Read the full file on GitHub · 46 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.

9d ago First seen · 46 lines · 862 tokens per session scan A 844aa97b2316

Subscribe to this mod's changes

LocalDB-MCP CLAUDE.md is an instructions file published in the GitHub repository HermesSilva/LocalDB-MCP (1 stars, last pushed 1mo ago), licensed MIT. It adds 862 tokens to every session, about $0.0043 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.

Databases

next.js AGENTS.md

AGENTS.md instructions for vercel/next.js, covering next.js development guide, codebase structure, monorepo overview, core package: packages/next and other important packages.

vercel/next.js · 7,296 tokens

codex AGENTS.md

AGENTS.md instructions for openai/codex, covering rust/codex-rs, the codex-core crate, code review rules, crate api surface and model visible context.

openai/codex · 5,153 tokens

vscode buildNext.instructions.md

Working notes and architecture documentation for the new esbuild-based build system in build/next. Use when making changes to the new build pipeline (transpile/bundle commands, NLS plugin, source-map handling, resource copying, or self-hosting watch tasks).

microsoft/vscode · 6,785 tokens

LocalDB-MCP: Instructions file for Claude Code