universal-db-mcp: Instructions file for Claude Code

CLAUDE.md

universal-db-mcp CLAUDE.md is an instructions file for Claude Code from joyous-coder/universal-db-mcp. It costs 1,227 tokens per session, scanned A, original, MIT.

A set of project instructions for AI coding agents working on the universal-db-mcp database server. It documents the project structure, supported database connections, release process, and coding constraints.

In plain words
What is it for?
Use it when developing, reviewing, releasing, or preparing changes for universal-db-mcp, including its tests, commits, tags, and package publishing.
Why use it?
It gives an agent the project context and rules needed to make safer changes and follow the repository's release procedure.

Instructions file for Claude Code

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

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

Reuse

Borrowing it

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

agentmods badge for universal-db-mcp CLAUDE.md

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

agentmods 80×15 button for universal-db-mcp CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/joyous-coder/universal-db-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/joyous-coder/universal-db-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 1,227 This file is loaded in full into every session.
When invoked 1,227 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 $0.01227 $0.01227
Opus 5.5 $0.00491 $0.00491
Sonnet 5.5 $0.00245 $0.00245
Haiku 4.5 $0.00123 $0.00123

Measured 2mo ago against content hash 9c781b8f5315, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

universal-db-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 2mo 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 · 83 lines

How it starts

The opening of the file, as written. The whole thing — 83 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

This file provides AI coding agents with project-specific context and work constraints.

Project Snapshot

  • Name: @joyous-coder/universal-db-mcp
  • Purpose: MCP server connecting Claude Desktop (or any MCP client) to 17 database types (MySQL/PostgreSQL/Oracle/SQL Server/DM/Kingbase/GaussDB/MongoDB/Redis/SQLite/ClickHouse/etc.)
  • Language: TypeScript (Node 20+)
  • Runtime modes: stdio (Claude Desktop) | HTTP REST | MCP SSE / Streamable HTTP
  • Latest release: see GitHub Releases (v3.2.1 as of 2026-07-25)

Release Process

This project publishes via GitHub Actions + NPM Trusted Publishing (OIDC). No NPM_TOKEN secret required.

Full step-by-step guide: see CONTRIBUTING.md § "📦 发布流程".

Quick summary:

  1. Bump version in package.json + add CHANGELOG entry → git commit → git tag vX.Y.Z
  2. git push origin main + git push origin vX.Y.Z
  3. gh release create vX.Y.Z --notes-file release-notes.md --verify-tag
  4. .github/workflows/publish.yml (trigger: release: created) auto-runs npm publish --provenance --access public
  5. Verify via gh release view vX.Y.Z + check npmjs.com

If workflow doesn't auto-trigger (rare):

gh workflow run publish.yml --ref vX.Y.Z

Do NOT use manual npm login + npm publish — bypasses Trusted Publishing OIDC and breaks the provenance chain.

Release notes format (avoid duplicate version title):

  • release-notes.md 文件不要用 # vX.Y.Z Release Notes 这种头,因为 gh release create --notes-file 已经会自动把 tag 名 vX.Y.Z 加到标题里。直接以 ## 摘要 / ## 改动 / ## 测试 等正文 section 开头即可,避免双重标题。
  • v4.0.5 案例:publish workflow 报告 403 失败,但 npm 实际接受 — 因为 npmjs OIDC 不让重发已 publish 的版本。核对 npmjs npm view @scope/pkg@latest dist-tags 确认实际状态,不要只看 workflow run 结论。

AI Work Constraints

When working on this codebase, AI agents (Claude Code, etc.) must follow these rules:

Pre-commit / Pre-PR

  • All tests pass: npm test exits 0 (don't ship green CI breakages)
  • TypeScript compiles: npm run build exits 0
  • No untracked working tree: git status clean before commit
  • CHANGELOG.md updated: if the change affects user-visible behavior, add an entry under "未发布" (unreleased) or the current dev version

Read the full file on GitHub · 83 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. 2mo ago First seen · 83 lines · 1,227 tokens per session scan A 9c781b8f5315

Subscribe to this mod's changes

universal-db-mcp CLAUDE.md is an instructions file published in the GitHub repository joyous-coder/universal-db-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 1,227 tokens to every session, about $0.0049 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

universal-db-mcp CLAUDE.md compared with instructions from other repositories

universal-db-mcp CLAUDE.md next to 6 instructions from other repositories
ModTypeStarsLast pushLicenceScanTokensWorks with
universal-db-mcp CLAUDE.mdjoyous-coder/universal-db-mcpInstructions file01mo agoMITA1,227Claude Code
vscode buildNext.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA9,719GitHub Copilot
next.js AGENTS.mdvercel/next.jsInstructions file144ktodayMITA8,130Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA5,685GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchainInstructions file150ktodayMITA4,680Codex, OpenCode
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harnessInstructions file283ktodayMITA4,342Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscodeInstructions file196ktodayMITA3,153GitHub Copilot