What is db-mcp AGENTS.md?

Project instructions for db-mcp, a server that lets people query databases with natural language. The project is a monorepo, meaning one repository contains several related packages, including Python code, shared models, and a Next.js interface.

Use it when modifying db-mcp's core code, shared data models, user interface, documentation, or database-query features.

It gives a coding agent the project structure, technology choices, supported databases, and key rules needed to change the repository consistently.

How apelogic-ai/db-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to apelogic-ai/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/apelogic-ai/db-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/apelogic-ai/db-mcp

Made for: Codex, OpenCode.

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/apelogic-ai/db-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/apelogic-ai/db-mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/apelogic-ai/db-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/apelogic-ai/db-mcp/agents-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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/apelogic-ai/db-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/apelogic-ai/db-mcp/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,444 This file is loaded in full into every session.

When invoked 1,444 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.

Model	Per session	Once invoked
Fable 5.1	$0.01444	$0.01444
Opus 5.5	$0.00578	$0.00578
Sonnet 5.5	$0.00289	$0.00289
Haiku 4.5	$0.00144	$0.00144

Measured 2mo ago against content hash 8346982979dc, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

db-mcp AGENTS.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.

AGENTS.md · 169 lines

How it starts

The opening of the file, as written. The whole thing — 169 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

This file mirrors the repo guidance in CLAUDE.md and serves as the main agent handbook for working on db-mcp. Do not remove CLAUDE.md.

Project Overview

db-mcp is an MCP (Model Context Protocol) server that enables Claude Desktop to query databases using natural language. It was extracted from the semantic-grid project as a standalone component.

Core capabilities:

Introspects database schemas automatically
Builds a semantic understanding of data through interactive onboarding
Generates and validates SQL from natural language
Supports multiple database backends

Repository Structure (Monorepo)

packages/
  core/    # Main application package (db-mcp)
  models/  # Shared data models (db-mcp-models)
  ui/      # Next.js UI application

Key paths:

packages/core/src/db_mcp/ - primary Python source
packages/models/src/db_mcp_models/ - shared Pydantic models
packages/ui/ - Next.js UI
docs/ - design documents

Technology Stack

Python 3.13+
FastMCP (>=2.0.0)
Pydantic AI with MCPSamplingModel
SQLAlchemy 2.0, SQLGlot
Click + Rich for CLI
OpenTelemetry for observability

Supported databases: PostgreSQL, ClickHouse, Trino, MySQL, SQL Server

Key Modules (Core)

cli.py - CLI entry point
server.py - FastMCP server initialization and tool registration
config.py - Settings and connection management
dialect.py - SQL dialect detection
db/ - database abstraction and introspection
tools/ - MCP tools (database, generation, onboarding, validation, training)
onboarding/ - schema discovery and documentation workflow
training/ - query examples and feedback
tasks/ - query/task history storage
vault/ - storage backends (local filesystem, S3)
console/ - trace viewer UI
validation/ - SQL validation and cost estimation
bicp/ - BICP agent for UI communication
ui_server.py - FastAPI server for UI + BICP endpoint
migrations/ - data migrations for connection storage
metrics/ - business metrics storage and retrieval

Read the full file on GitHub · 169 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.

2mo ago First seen · 169 lines · 1,444 tokens per session scan A 8346982979dc

Subscribe to this mod's changes

db-mcp AGENTS.md is an instructions file published in the GitHub repository apelogic-ai/db-mcp (6 stars, last pushed 6mo ago), licensed MIT. It adds 1,444 tokens to every session, about $0.0058 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.

Building agents Databases

db-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
db-mcp AGENTS.mdapelogic-ai/db-mcp	Instructions file	6	6mo ago	MIT	A	1,444	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	275k	2d ago	MIT	A	4,313	Codex, OpenCode

db-mcp: Instructions file for Codex