mwaa-mcp-server: Instructions file for Claude Code

CLAUDE.md

mwaa-mcp-server CLAUDE.md is an instructions file for Claude Code from biswasbiplob/mwaa-mcp-server. It costs 826 tokens per session, scanned A, original, Apache-2.0.

A repository instruction file for the mwaa-mcp-server project, covering its commands, structure, tool-adding rules, and known traps. MWAA is Amazon Managed Workflows for Apache Airflow, and MCP is a way for an assistant to expose tools.

In plain words
What is it for?
Use it when changing this Python server, adding a tool, running its test and lint commands, or working with its AWS and Airflow code.
Why use it?
It gives an agent the project-specific rules it needs before editing code, including how to test changes and where Airflow access belongs.

Instructions file for Claude Code

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

This is biswasbiplob/mwaa-mcp-server's own configuration. It tells Claude Code how to work on mwaa-mcp-server 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 mwaa-mcp-server configures →

Reuse

Borrowing it

Nothing to install: this file belongs to biswasbiplob/mwaa-mcp-server. 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/biswasbiplob/mwaa-mcp-server/main/CLAUDE.md
Clone the repo
git clone --depth 1 https://github.com/biswasbiplob/mwaa-mcp-server

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 mwaa-mcp-server CLAUDE.md

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

Your own site · 80×15
<a href="https://agentmods.dev/instructions/biswasbiplob/mwaa-mcp-server/claude-md"><img src="https://agentmods.dev/badge/instructions/biswasbiplob/mwaa-mcp-server/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 826 This file is loaded in full into every session.
When invoked 826 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00826 $0.00826
Opus 5 $0.00413 $0.00413
Sonnet 5 $0.00165 $0.00165
Haiku 4.5 $0.00083 $0.00083

Measured yesterday against content hash 0ca1d592eb66, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade A, and why

mwaa-mcp-server 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 yesterday.

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.

CLAUDE.md · 65 lines

How it starts

The opening of the file, as written. The whole thing — 65 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md — mwaa-mcp-server

Conventions and traps specific to this repo. Read before you change code here.

Commands

uv run pytest -q              # full suite, must stay green
uv run ruff check .           # lint
uv run ruff format .          # format (single quotes, line length 99)
uv lock                       # re-lock after a version bump

There is no Makefile and no CI. The local run is the only evidence a change works.

Architecture

  • server.py — builds the MCPServer, parses --allow-write, wires the two handler classes.
  • environment_tools.pyEnvironmentTools, the MWAA control plane (boto3 calls).
  • airflow_tools.pyAirflowTools, every Airflow REST call.
  • aws_client.py — the single get_mwaa_client factory. Tests patch this name.
  • consts.py — API path templates and redaction patterns.

Each handler registers its tools inside __init__ with self.mcp.tool(name='...').

All Airflow access goes through invoke_rest_api (ADR 0001). Never add create_cli_token or create_web_login_token.

Adding a tool

  1. Add the path template to consts.py.
  2. Write the failing test in tests/test_airflow_tools.py first.
  3. Add the method to the handler and register it in __init__.
  4. Update the hardcoded tool counts in tests/test_server.py. Three assertions carry a number.
  5. Add the row to the README tool table.
  6. Follow the release steps below.

Write tools must call self._check_write_access() first.

Traps

Tool counts are hardcoded. tests/test_server.py asserts an exact count in three places. A new tool fails those tests until you bump each number.

Unset Field() defaults are not None in tests. Tests call handler methods directly, with no FastMCP in front. An omitted parameter therefore arrives as a Pydantic FieldInfo, not None. Pass limit=None explicitly when a test needs to simulate what a real client sends.

API paths carry no version prefix. invoke_rest_api routes the version itself. /pools works. /api/v2/pools and /v2/pools both answer 404.

Read the full file on GitHub · 65 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. yesterday First seen · 65 lines · 826 tokens per session scan A 0ca1d592eb66

Subscribe to this mod's changes

mwaa-mcp-server CLAUDE.md is an instructions file published in the GitHub repository biswasbiplob/mwaa-mcp-server (0 stars, last pushed 2d ago), licensed Apache-2.0. It adds 826 tokens to every session, about $0.0041 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 2026-09-09.

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

spec-kit AGENTS.md

AGENTS.md instructions for github/spec-kit, covering agents.md, about spec kit and specify, quickstart — add a new integration in 5 steps, integration architecture and integrationmanifest — file tracking.

github/spec-kit · 7,104 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