What is amazon_ads_mcp AGENTS.md?

Development instructions for an Amazon Ads MCP project, a Python service that connects AI assistants to Amazon Advertising tools through the Model Context Protocol.

Use them to install dependencies, start the service with Docker, connect it to Claude, check the MCP connection, run linting, and run the full test suite.

They give coding agents a required setup and validation routine, helping prevent untested or incorrectly configured changes from being committed.

amazon_ads_mcp AGENTS.md — Instructions file for Codex and OpenCode by NetzSicht: Development instructions for an Amazon Ads MCP project, a…

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/netzsicht/amazon_ads_mcp/agents-md

Clone the repo

git clone --depth 1 https://github.com/NetzSicht/amazon_ads_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/netzsicht/amazon_ads_mcp/agents-md.svg)](https://agentmods.dev/instructions/netzsicht/amazon_ads_mcp/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/netzsicht/amazon_ads_mcp/agents-md"><img src="https://agentmods.dev/badge/instructions/netzsicht/amazon_ads_mcp/agents-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 4,736 This file is loaded in full into every session.

When invoked 4,736 The same file — it is already loaded in full.

Security scan B 2 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.

Model	Per session	Once invoked
Fable 5	$0.04736	$0.04736
Opus 5	$0.02368	$0.02368
Sonnet 5	$0.00947	$0.00947
Haiku 4.5	$0.00474	$0.00474

Measured 5d ago against content hash 2022cdb2085b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade B, and why

amazon_ads_mcp AGENTS.md scanned grade B with 2 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.

Asks for rootmediumPrivilege escalation

A mod that escalates privileges can change anything on the machine, not only the project.

chmod 755 /app/.cache/amazon-ads-mcp

Makes network callslowCapability

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

curl -H "Amazon-Advertising-API-ClientId: $AMAZON_ADS_CLIENT_ID" \

AGENTS.md · 592 lines

How it starts

The opening of the file, as written. The whole thing — 592 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Amazon Ads MCP Development Guidelines

Audience: LLM-driven engineering agents and human developers

Amazon Ads MCP is a Python framework (Python ≥3.10) for integrating Amazon Advertising API with Model Context Protocol (MCP) servers. This project provides a complete toolkit for building AI-powered advertising applications with comprehensive campaign management, reporting, and optimization capabilities.

Do This First (for Agents)

Ensure Python ≥3.10 and uv are installed
uv sync to install dependencies
Start the server: docker-compose up -d
Connect Claude to the MCP server (HTTP):
- claude mcp add amazon-ads-mcp -- python -m amazon_ads_mcp.server.mcp_server --transport http --port 9080
Verify: claude mcp list and use /mcp inside Claude

Required Development Workflow

CRITICAL: Always run these commands in sequence before committing:

# Install dependencies
uv sync                              # Install dependencies

# Validate code
uv run ruff check --fix             # Lint and auto-fix
uv run pytest                        # Run full test suite

All must pass - tests/linting must be clean before committing.

Agent Ops (LLM Guidance)

Preambles: Send a brief 1–2 sentence note before running tool commands.
Plans: Use TodoWrite for multi-step work; keep exactly one in_progress step.
Edits: Use Edit or MultiEdit to modify files; keep changes focused and avoid unrelated edits.
Testing: Run the smallest relevant tests first; do not fix unrelated failures.
Sandboxing: Assume workspace-write FS and restricted network; prefer local resources over external APIs unless keys are present.

Agent Success Playbook

Follow these steps for reliable outcomes in Claude contexts:

Understand & Plan

Clarify task type: API integration, MCP connectivity, Docker, tests, or GitHub workflow.
Post a short preamble and, for multi-step work, create a minimal TodoWrite with exactly one in_progress step.

Connect & Verify (MCP + Server)

Start server: docker-compose up -d (Amazon Ads MCP at http://localhost:9080).
Add MCP to Claude (HTTP):
- claude mcp add amazon-ads-mcp -- python -m amazon_ads_mcp.server.mcp_server --transport http --port 9080
Verify in Claude: claude mcp list then /mcp → run a tool (e.g., list profiles).

Read the full file on GitHub · 592 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.

5d ago First seen · 592 lines · 4,736 tokens per session scan B 2022cdb2085b

Subscribe to this mod's changes

amazon_ads_mcp AGENTS.md is an instructions file published in the GitHub repository NetzSicht/amazon_ads_mcp (1 stars, last pushed 10mo ago), licensed MIT. It adds 4,736 tokens to every session, about $0.0237 per session on Opus 5. A static security scan graded it B with 2 findings (asks for root, makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

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 · 5,182 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

amazon_ads_mcp AGENTS.md