mcp-db-agent: Instructions file for Claude Code

CLAUDE.md

mcp-db-agent CLAUDE.md is an instructions file for Claude Code from Jarvis-27/mcp-db-agent. It costs 2,777 tokens per session, scanned A, original, MIT.

A set of instructions for working on an MCP server that lets AI clients ask questions about PostgreSQL databases in plain English. PostgreSQL is a database system, and MCP is a standard connection method for AI tools.

In plain words
What is it for?
Installing dependencies, running unit tests, understanding the server’s local and hosted modes, and making changes consistently in the repository.
Why use it?
It gives the coding agent the project’s setup commands and testing guidance, including tests that run without an AI model or database.

Instructions file for Claude Code

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

This is Jarvis-27/mcp-db-agent's own configuration. It tells Claude Code how to work on mcp-db-agent 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-agent configures →

Reuse

Borrowing it

Nothing to install: this file belongs to Jarvis-27/mcp-db-agent. 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/Jarvis-27/mcp-db-agent/master/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/Jarvis-27/mcp-db-agent

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-agent CLAUDE.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/jarvis-27/mcp-db-agent/claude-md/github.svg)](https://agentmods.dev/instructions/jarvis-27/mcp-db-agent/claude-md)
Your own site
<a href="https://agentmods.dev/instructions/jarvis-27/mcp-db-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/jarvis-27/mcp-db-agent/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-agent CLAUDE.md

Your own site · 80×15
<a href="https://agentmods.dev/instructions/jarvis-27/mcp-db-agent/claude-md"><img src="https://agentmods.dev/badge/instructions/jarvis-27/mcp-db-agent/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 2,777 This file is loaded in full into every session.
When invoked 2,777 The same file — it is already loaded in full.
Security scan A 1 finding. 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 $0.02777 $0.02777
Opus 5 $0.01388 $0.01388
Sonnet 5 $0.00555 $0.00555
Haiku 4.5 $0.00278 $0.00278

Measured 9d ago against content hash a0a8f2fda256, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-09, from the pricing page.

Security

Grade A, and why

mcp-db-agent CLAUDE.md scanned grade A with 1 finding 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 9d 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.

Makes network callslowCapability

Not a fault in itself. Listed so you know the mod talks to something, and to what.

curl -X POST http://localhost:8000/api/v1/users/register \
CLAUDE.md · 234 lines

How it starts

The opening of the file, as written. The whole thing — 234 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.

What This Project Is

An MCP (Model Context Protocol) server that exposes PostgreSQL databases as natural-language queryable endpoints. Any MCP client (Claude Desktop, Cursor, VS Code Copilot) can connect and ask questions in plain English. The server introspects the schema, generates SQL via an LLM, validates it for safety, executes it, and returns structured JSON — with a self-correction retry loop if execution fails.

Two deployment modes:

  • Stdio / single-user (uv run src/server.py): local dev, Claude Desktop, VS Code Copilot.
  • Hosted / multi-tenant (uvicorn src.app:app): multiple users register their own database, receive an API key, and connect to a shared HTTP endpoint.

Commands

Package manager: uv only — do not use pip or Poetry.

# Install all dependencies (including dev)
uv sync

# Run all unit tests (no LLM calls, no DB required)
uv run pytest -m "not integration"

# Run a single test file
uv run pytest tests/test_sql_validator.py

# Run a single test by name
uv run pytest tests/test_sql_executor.py::test_execute_aggregation_count

# Run integration tests (needs API keys in .env and a seeded demo.db)
uv run pytest -m integration

# Lint and format
uv run ruff check .
uv run ruff format .

# Type check
uv run mypy src --ignore-missing-imports

# Run the MCP server (stdio transport for Claude Desktop)
uv run src/server.py

# Run hosted HTTP server (multi-tenant)
uv run uvicorn src.app:app --reload

# Debug with MCP Inspector (requires Node.js)
npx @modelcontextprotocol/inspector uv run src/server.py

# Seed the local demo database
uv run scripts/seed_demo_db.py

# Database migrations (Alembic)
uv run alembic upgrade head          # apply all pending migrations
uv run alembic check                 # verify schema is at head
uv run alembic downgrade -1          # roll back one migration

Architecture

Read the full file on GitHub · 234 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. 9d ago First seen · 234 lines · 2,777 tokens per session scan A a0a8f2fda256

Subscribe to this mod's changes

mcp-db-agent CLAUDE.md is an instructions file published in the GitHub repository Jarvis-27/mcp-db-agent (0 stars, last pushed 1mo ago), licensed MIT. It adds 2,777 tokens to every session, about $0.0139 per session on Opus 5. A static security scan graded it A with 1 finding (makes network calls). 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 · 5,153 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

deepseek-harness AGENTS.md

AGENTS.md instructions for deepseek-ai/deepseek-harness, covering agents.md, pre-stable apis and released session data, repository layout, commands and host sandbox failures.

deepseek-ai/deepseek-harness · 3,735 tokens