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.
curl -O https://raw.githubusercontent.com/phatngoit/MCP-DB/master/CLAUDE.mdgit clone --depth 1 https://github.com/phatngoit/MCP-DBWrote 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.
[](https://agentmods.dev/instructions/phatngoit/mcp-db/claude-md)<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.
<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>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 | $0.01922 | $0.01922 |
| Opus 5.5 | $0.00769 | $0.00769 |
| Sonnet 5.5 | $0.00384 | $0.00384 |
| Haiku 4.5 | $0.00192 | $0.00192 |
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.
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 inschema.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 theDbConnectorinterface fromtypes.ts;mongodb.tsadditionally implementsMongoDbConnector.src/tools/register-tools.ts— Registers all 14 MCP tools on theMcpServer(8 shared/SQL tools for Oracle+MSSQL, 6 MongoDB-specific tools). Each tool follows therunAuditedwrapper: run action → audit → returnok()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.
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.
- 1mo ago First seen · 136 lines · 1,922 tokens per session scan A b2ea8f18f81e
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.
Other instructions, from other repositories
plan-forge caching.instructions.md
Caching patterns for .NET — IDistributedCache, Redis, in-memory, cache-aside, TTL strategies.
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).
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.
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).
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.
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).