What is mcp-server-mysql CLAUDE.md?

Project instructions for an MCP server that lets language models access MySQL databases, including commands for building, running, testing, and development.

Use it when developing the server, building TypeScript, starting local or remote modes, setting up the test database, or running unit, integration, end-to-end, and socket tests.

It gives contributors the repository's expected commands and explains its main technologies and test setup.

mcp-server-mysql CLAUDE.md — Instructions file for Claude Code by benborla: Project instructions for an MCP server that lets language…

About the project

mcp-server-mysql is a Model Context Protocol server that lets language models inspect MySQL database schemas and run read-only queries. It is used to give AI assistants controlled access to database information.

benborla/mcp-server-mysql · 2,106 stars · on GitHub

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/benborla/mcp-server-mysql/claude-md

Clone the repo

git clone --depth 1 https://github.com/benborla/mcp-server-mysql

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/benborla/mcp-server-mysql/claude-md.svg)](https://agentmods.dev/instructions/benborla/mcp-server-mysql/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/benborla/mcp-server-mysql/claude-md"><img src="https://agentmods.dev/badge/instructions/benborla/mcp-server-mysql/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 1,792 This file is loaded in full into every session.

When invoked 1,792 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.

Model	Per session	Once invoked
Fable 5.1	$0.01792	$0.01792
Opus 5	$0.00896	$0.00896
Sonnet 5	$0.00358	$0.00358
Haiku 4.5	$0.00179	$0.00179

Measured 6d ago against content hash 0cc9e6335642, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

mcp-server-mysql 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 6d 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 · 250 lines

How it starts

The opening of the file, as written. The whole thing — 250 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 provides MySQL database access to LLMs like Claude, with enhanced write operation support and Claude Code optimizations.

Key Technologies:

TypeScript with ES Modules (NodeNext)
MCP SDK (@modelcontextprotocol/sdk v1.15.1)
mysql2 for database connectivity
Vitest for testing
Express for remote MCP mode (optional)

Build and Development Commands

Building

# Build TypeScript to dist/
pnpm build

# Watch mode (auto-rebuild on changes)
pnpm watch

Running

# Run built version
pnpm start

# Development mode with ts-node
pnpm dev

# Run directly with environment variables
pnpm exec

Testing

# Setup test database (creates mcp_test DB and seeds data)
pnpm run setup:test:db

# Run all tests (includes pretest hook that runs setup:test:db)
pnpm test

# Run specific test suites
pnpm test:unit          # Unit tests only
pnpm test:integration   # Integration tests only
pnpm test:e2e          # End-to-end tests only
pnpm test:socket       # Socket connection tests

# Watch mode for development
pnpm test:watch

# Coverage report
pnpm test:coverage

Test Environment Requirements:

MySQL server running locally or remotely
Test database user: mcp_test with password mcp_test_password
Test database: mcp_test
Configuration via .env.test file

Linting

pnpm lint

Architecture

Core Entry Point

index.ts - Main server file that exports createMcpServer() function
- Supports both stdio and HTTP transport modes
- Handles MCP protocol setup and request routing
- Configures shutdown handlers for graceful cleanup

Key Modules

Configuration (src/config/index.ts)

Loads environment variables via dotenv
Exports connection config, permission flags, and mode detection
Key exports:
- mcpConfig - MySQL connection configuration
- isMultiDbMode - Boolean indicating multi-database mode
- ALLOW_*_OPERATION - Global write permission flags
- SCHEMA_*_PERMISSIONS - Schema-specific permission maps
- MYSQL_DISABLE_READ_ONLY_TRANSACTIONS - Control transaction mode

Read the full file on GitHub · 250 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.

6d ago First seen · 250 lines · 1,792 tokens per session scan A 0cc9e6335642

Subscribe to this mod's changes

mcp-server-mysql CLAUDE.md is an instructions file published in the GitHub repository benborla/mcp-server-mysql (2,106 stars, last pushed 1mo ago), licensed MIT. It adds 1,792 tokens to every session, about $0.0090 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 2026-08-30.

Databases

mcp-server-mysql CLAUDE.md

Getting it into your agent

Wrote this? Show the measurements

What it costs to keep this loaded

Grade A, and why

Nothing flagged

How it starts

CLAUDE.md

Project Overview

Build and Development Commands

Building

Running

Testing

Linting

Architecture

Core Entry Point

Key Modules

What this file has done since we first saw it

Other instructions, from other repositories

lms-front CLAUDE.md

vespertide AGENTS.md

seekstone CLAUDE.md

rails_ai_agents AGENTS.md

pg-dash CLAUDE.md

MCP-SqlServer CLAUDE.md