MCP-DB: Instructions file for Claude Code

CLAUDE.md

MCP-DB CLAUDE.md is an instructions file for Claude Code from phatngoit/MCP-DB. It costs 1,922 tokens per session, scanned A, original, MIT.

Repository instructions for MCP-DB, a TypeScript command-line application that connects coding agents to databases through MCP, a standard way for tools to exchange context with AI assistants.

In plain words
What is it for?
Use them when building, type-checking, linting, formatting, testing, or debugging the MCP-DB command-line application.
Why use it?
They document the required Node.js version, development commands, project architecture, request flow, and testing approach.

Instructions file for Claude Code

Written for Claude Code: the file is CLAUDE.md. Also seen: reads .claude/ paths; mentions CLAUDE.md; mentions Claude Code.

This is phatngoit/MCP-DB's own configuration. It tells Claude Code how to work on MCP-DB 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 MCP-DB configures →

Reuse

Borrowing it

Nothing to install: this file belongs to phatngoit/MCP-DB. 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/phatngoit/MCP-DB/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/phatngoit/MCP-DB

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 MCP-DB CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/phatngoit/mcp-db/claude-md/github.svg)](https://agentmods.dev/instructions/phatngoit/mcp-db/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/phatngoit/mcp-db/claude-md"><img src="https://agentmods.dev/badge/instructions/phatngoit/mcp-db/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 MCP-DB CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/phatngoit/mcp-db/claude-md"><img src="https://agentmods.dev/badge/instructions/phatngoit/mcp-db/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,922 This file is loaded in full into every session.
When invoked 1,922 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 $0.01922 $0.01922
Opus 5.5 $0.00769 $0.00769
Sonnet 5.5 $0.00384 $0.00384
Haiku 4.5 $0.00192 $0.00192

Measured 1mo ago against content hash b2ea8f18f81e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

MCP-DB 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 1mo 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 · 136 lines

How it starts

The opening of the file, as written. The whole thing — 136 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.

Commands

Requires Node.js >=20.10.

npm install          # Install dependencies
npm run build        # Compile TypeScript → dist/ (uses tsconfig.build.json)
npm run dev          # Run CLI directly via tsx (no compile step)
npm run typecheck    # Type-check without emitting (uses tsconfig.json)
npm run lint         # ESLint on src/**/*.ts
npm run format       # Prettier on all TS/MD/JSON/YAML files
npm test             # Run Vitest test suite
vitest run --reporter=verbose  # Run tests with full output

To run a single test file:

npx vitest run src/core/security.test.ts

For local development testing of CLI commands (no global install needed):

node dist/cli.js start
node dist/cli.js validate-config
node dist/cli.js test-connections

Or using tsx without a build step:

npm run dev -- start
npm run dev -- validate-config

Architecture

This is an ESM-only TypeScript package ("type": "module"). Imports must use .js extensions even for .ts source files (NodeNext module resolution).

Request flow

CLI (src/cli.ts)
  → loadConfig (src/config/load-config.ts) parses YAML + Zod validation
  → startStdioServer / startHttpServer (src/server.ts)
      → ConnectorRegistry (src/core/registry.ts) creates connector instances
      → registerDbTools (src/tools/register-tools.ts) wires MCP tools to registry
           → security.ts: validateSqlQuery / validateMongoPipeline / assertAllowedObject
           → audit.ts: writes JSONL audit log if configured
           → format.ts: formats QueryResult as markdown table

Key layers

  • src/config/ — YAML loading (load-config.ts) and Zod schema (schema.ts). Config defaults are defined in schema.ts (e.g., defaultMaxRows: 100, queryTimeoutMs: 10000).
  • src/types.ts — All shared interfaces: DbConnector, AppConfig, SecurityConfig, connection configs per DB type.
  • src/core/ — Cross-cutting concerns: registry.ts (connector lifecycle), security.ts (SQL/MongoDB validation, masking, allowlists), audit.ts (JSONL append), format.ts (markdown table output), errors.ts (UserInputError/PermissionError).
  • src/connectors/ — One file per DB type (oracle.ts, mssql.ts, mongodb.ts). Each implements the DbConnector interface from types.ts; mongodb.ts additionally implements MongoDbConnector.
  • src/tools/register-tools.ts — Registers all 14 MCP tools on the McpServer (8 shared/SQL tools for Oracle+MSSQL, 6 MongoDB-specific tools). Each tool follows the runAudited wrapper: run action → audit → return ok() or error.
  • src/setup/wizard.ts — Interactive setup wizard; generates .mcp.json, .codex/config.toml, .gemini/settings.json, .kimi/mcp.json, mcp-db.local.yml, .env, .gitignore.

Read the full file on GitHub · 136 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. 1mo ago First seen · 136 lines · 1,922 tokens per session scan A b2ea8f18f81e

Subscribe to this mod's changes

MCP-DB CLAUDE.md is an instructions file published in the GitHub repository phatngoit/MCP-DB (1 stars, last pushed 2mo ago), licensed MIT. It adds 1,922 tokens to every session, about $0.0077 per session on Opus 5.5. 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

plan-forge caching.instructions.md

Caching patterns for .NET — IDistributedCache, Redis, in-memory, cache-aside, TTL strategies.

srnichols/plan-forge · 733 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 · 9,649 tokens

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 · 7,549 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, cache eligibility and rollout and applying the notice (cutover).

microsoft/vscode · 5,262 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 · 4,680 tokens

vscode copilot-instructions.md

Copilot instructions for microsoft/vscode, covering vs code copilot instructions, project overview, root folders, core architecture (src/ folder) and built-in extensions (extensions/ folder).

microsoft/vscode · 2,731 tokens