db-mcp-server: Instructions file for Claude Code

CLAUDE.md

db-mcp-server CLAUDE.md is an instructions file for Claude Code from vika2603/db-mcp-server. It costs 780 tokens per session, scanned A, original, MIT.

Repository instructions for a Rust MCP server that gives AI assistants database tools for SQLite, PostgreSQL, and MySQL. It supports local standard-input communication and HTTP with server-sent events, a way to stream responses over HTTP.

In plain words
What is it for?
Use them when building or testing database operations, working on transport or authentication, changing MCP services, or running database-specific integration tests.
Why use it?
They explain the server layers, supported databases, authentication, commands, and tests so changes follow the intended structure.

Instructions file for Claude Code

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

This is vika2603/db-mcp-server's own configuration. It tells Claude Code how to work on db-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 db-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to vika2603/db-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/vika2603/db-mcp-server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/vika2603/db-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 db-mcp-server CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/vika2603/db-mcp-server/claude-md.svg)](https://agentmods.dev/instructions/vika2603/db-mcp-server/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/vika2603/db-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/vika2603/db-mcp-server/claude-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 780 This file is loaded in full into every session.
When invoked 780 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 $0.00780 $0.00780
Opus 5 $0.00390 $0.00390
Sonnet 5 $0.00156 $0.00156
Haiku 4.5 $0.00078 $0.00078

Measured 6d ago against content hash 9e0c0b7783a7, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

db-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 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 · 55 lines

How it starts

The opening of the file, as written. The whole thing — 55 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.

Build and Development Commands

cargo build                              # Debug build
cargo build --release                    # Release build
cargo test                               # Run all tests
cargo test --test sqlite_writable_test   # Run a single integration test file
cargo test --lib                         # Run unit tests only
cargo test test_name                     # Run tests matching a name
cargo clippy                             # Lint
cargo fmt                                # Format
cargo fmt -- --check                     # Check formatting without modifying

Some integration tests require external databases via environment variables:

  • TEST_MYSQL_URL - MySQL connection URL for transaction/MySQL-specific tests

Architecture

Rust MCP server exposing SQL database operations (SQLite, PostgreSQL, MySQL) as tools for AI assistants via the rmcp framework.

Layer Structure

  1. Transport (src/transport/) - stdio or HTTP+SSE entry points. HTTP supports Bearer token auth (src/auth.rs).
  2. MCP Service (src/mcp/service.rs) - DbService is the central struct. Uses rmcp's #[tool_router] and #[tool_handler] macros to register 14 tools and implement ServerHandler. Each tool method delegates to a handler in src/tools/.
  3. Tool Handlers (src/tools/) - Business logic per tool category. Each handler receives shared Arc<ConnectionManager> and Arc<TransactionRegistry>.
  4. Database Layer (src/db/) - ConnectionManager holds named DbPool instances (enum over sqlx pool types). TransactionRegistry tracks active transactions with timeout cleanup. database_pool.rs manages lazy per-database pools for server-level connections.

Key Design Patterns

  • Connections are read-only by default. Write requires ?writable=true in the connection URL.
  • SQL validation uses sqlparser AST analysis (src/tools/sql_validator.rs, src/tools/guard.rs) to block dangerous operations (DROP, TRUNCATE, unqualified DELETE/UPDATE) before execution.
  • Tool input/output types live alongside their handler in src/tools/*.rs, using schemars::JsonSchema for MCP schema generation. All JsonSchema structs MUST have #[schemars(transform = schemars::transform::RestrictFormats::default())] to strip format fields (e.g. "format": "uint32") that break stdio-based MCP clients.
  • DbPool enum wraps sqlx's typed pools; src/db/executor.rs dispatches queries across database backends.
  • src/db/types.rs handles cross-database type mapping and value conversion.
  • Config parsing (src/config.rs) uses clap with env var fallbacks (MCP_DATABASE, MCP_TRANSPORT, etc.).

Read the full file on GitHub · 55 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. 6d ago First seen · 55 lines · 780 tokens per session scan A 9e0c0b7783a7

Subscribe to this mod's changes

db-mcp-server CLAUDE.md is an instructions file published in the GitHub repository vika2603/db-mcp-server (5 stars, last pushed 6mo ago), licensed MIT. It adds 780 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.

Related

Other instructions, from other repositories

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 · 5,182 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

vscode oss-third-party-notices.instructions.md

Instructions for microsoft/vscode, covering vs code oss third-party-notices pipeline, architecture, pipeline flow in ci, applying the notice (cutover) and fallback chain (never fail the build).

microsoft/vscode · 5,001 tokens

langchain AGENTS.md

AGENTS.md instructions for langchain-ai/langchain, covering global development guidelines for the langchain monorepo, corridor security analysis, project architecture and context, monorepo structure and development tools & commands.

langchain-ai/langchain · 4,469 tokens

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 tokens