duckdb-mcp AGENTS.md

duckdb-mcp AGENTS.md is an instructions file for Codex, OpenCode from MMHK/duckdb-mcp. It costs 1,542 tokens per session, scanned A, original, Apache-2.0.

Development instructions for DuckDB MCP, a tool that lets an AI agent work with DuckDB, an embedded database for querying data. They cover installation, building, testing, linting, formatting, and type checking.

In plain words
What is it for?
They help install dependencies, build the project, run unit or end-to-end tests, create database test fixtures, check code quality, and run individual tests.
Why use it?
They give the agent the exact project commands and coding standards needed to change and verify the server.

Instructions file for CodexOpenCode

Written for Codex and OpenCode: the file is AGENTS.md. Also seen: mentions AGENTS.md.

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/mmhk/duckdb-mcp/agents-md
Clone the repo
git clone --depth 1 https://github.com/MMHK/duckdb-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.

agentmods badge for duckdb-mcp AGENTS.md

README.md
[![agentmods](https://agentmods.dev/badge/instructions/mmhk/duckdb-mcp/agents-md.svg)](https://agentmods.dev/instructions/mmhk/duckdb-mcp/agents-md)
Your own site
<a href="https://agentmods.dev/instructions/mmhk/duckdb-mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/mmhk/duckdb-mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>
Per session 1,542 This file is loaded in full into every session.
When invoked 1,542 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
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 $0.01542 $0.01542
Opus 5 $0.00771 $0.00771
Sonnet 5 $0.00308 $0.00308
Haiku 4.5 $0.00154 $0.00154

Measured 5d ago against content hash dc92f5c0bcc3, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-06, from the pricing page.

Security

Grade A, and why

duckdb-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 5d 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 · 215 lines

How it starts

The opening of the file, as written. The whole thing — 215 lines — stays where its author put it; the contents beside it link to each section on GitHub.

DuckDB MCP - Development Guidelines

Build & Test Commands

Core Commands

yarn install          # Install dependencies
yarn build            # Build project (TypeScript compilation)
yarn build:bundle     # Bundle with Rspack for npx distribution (optional)
yarn dev              # Watch mode for development
yarn start            # Run compiled JavaScript

Testing

yarn test             # Run all tests
yarn test:unit        # Run unit tests only
yarn test:e2e         # Run E2E tests only
yarn test:watch       # Watch mode for tests
yarn test:db          # Create test database fixture
yarn coverage         # Generate coverage report

Run a single test:

yarn test tests/unit/database.test.ts
yarn test -- --testNamePattern="should execute a simple query"

Code Quality

yarn lint             # Check linting
yarn lint:fix         # Auto-fix linting issues
yarn format           # Format code with Prettier
yarn format:check     # Check formatting without writing
yarn typecheck        # Run TypeScript type checking

Code Style Guidelines

TypeScript Configuration

  • Target: ES2022
  • Module: NodeNext (ESM)
  • Strict mode: Enabled
  • Universal rules: noImplicitAny, noImplicitReturns, noUnusedLocals, noUnusedParameters

Naming Conventions

  • Classes: PascalCase (e.g., DatabaseClient, FastMCP)
  • interfaces/types: PascalCase with Result suffix for return types
  • functions/variables: camelCase (e.g., executeQuery, maxRows)
  • Constants: UPPER_SNAKE_CASE (e.g., SERVER_VERSION)
  • Files: camelCase for implementation, .test.ts for tests

Import Order

  1. External dependencies (e.g., duckdb, commander)
  2. Internal modules (e.g., ./database.js, ./types.js)
  3. Relative imports using .js extension

Formatting (Prettier)

  • Semi-colons: true
  • Single quotes: true
  • Tab width: 2
  • Trailing commas: es5
  • Print width: 100
  • Arrow parentheses: avoid
  • Line endings: LF

Read the full file on GitHub · 215 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. 5d ago First seen · 215 lines · 1,542 tokens per session scan A dc92f5c0bcc3

Subscribe to this mod's changes

duckdb-mcp AGENTS.md is an instructions file published in the GitHub repository MMHK/duckdb-mcp (0 stars, last pushed 6mo ago), licensed Apache-2.0. It adds 1,542 tokens to every session, about $0.0077 per session on Opus 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.