What is aa-mcp CLAUDE.md?

Developer instructions for an MCP server that connects to American Airlines’ AAdvantage APIs. MCP is a standard way for an AI assistant to call external tools; these instructions cover the server’s architecture, login-session authentication, and multiple accounts.

Use it when developing, configuring, authenticating, or debugging the AA MCP server and its AAdvantage account access.

It explains how the server communicates with American Airlines and how its browser-based session credentials are handled. This helps developers understand the integration before changing or troubleshooting it.

How thehesiod/aa-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to thehesiod/aa-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/thehesiod/aa-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/thehesiod/aa-mcp

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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/thehesiod/aa-mcp/claude-md.svg)](https://agentmods.dev/instructions/thehesiod/aa-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/thehesiod/aa-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/thehesiod/aa-mcp/claude-md.svg" alt="Measured on agentmods" height="20"></a>

Per session 2,327 This file is loaded in full into every session.

When invoked 2,327 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	$0.02327	$0.02327
Opus 5	$0.01163	$0.01163
Sonnet 5	$0.00465	$0.00465
Haiku 4.5	$0.00233	$0.00233

Measured 7d ago against content hash dbe3e782d2d5, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-07, from the pricing page.

Security

Grade A, and why

aa-mcp 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 7d 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.

CLAUDE.md · 132 lines

How it starts

The opening of the file, as written. The whole thing — 132 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AA MCP Server

Architecture

MCP server that talks directly to aa.com's internal JSON APIs using session cookies extracted from a Chromium login. No scraping, no headless browser at runtime — all API calls are pure HTTP via curl_cffi with Chrome TLS impersonation. Runs as stdio transport.

src/aa_mcp_server/
  server.py         — MCP tool definitions (FastMCP)
  api.py            — AAAPI: typed wrappers around each /loyalty/api/* and /api/loyalty/* endpoint
  auth.py           — AASession: cookie jar persistence + CDP extraction
  auth_browser.py   — aa-auth-browser console script (launches Chromium with --remote-debugging-port)

Key Patterns

Authentication (PingFederate + Akamai Bot Manager)

aa.com login is PingFederate-backed (login.aa.com/loyalty/pf-ws/authn/flows/). After login, www.aa.com gets two cookies:
- access_token — RS256 JWT, ~45 min expiry, sub is the AAdvantage number, issued by https://login.aa.com/loyalty.
- refresh_token — opaque PingFederate format, ~30 day TTL.
All AAdvantage APIs are cookie-authenticated, not Bearer-authenticated. The JWT just rides along in the cookie jar.
aa.com is fronted by Akamai Bot Manager. Stdlib HTTP (httpx, requests) gets TLS-dropped at the edge. We use curl_cffi with impersonate="chrome131" — same pattern as costco-mcp.
The browser sends a x-xsrf-token header on /loyalty/api/* calls. Its value mirrors the XSRF-TOKEN cookie.

Multi-account

Sessions: ~/.aa-mcp/accounts/<name>/session.json per account.
Chromium profiles: ~/.aa-mcp/chrome-profiles/<name>/ (separate so cookies don't collide).
Config (default account + account list) at ~/.aa-mcp/config.json.
Every MCP tool takes an optional account parameter. Omit to use default.
_apis dict in server.py caches AAAPI instances; eviction on save_session_from_browser.

Cookie extraction (CDP)

The flow is one-time per ~30 days:

aa-auth-browser <account> launches the user's Chromium with --remote-debugging-port=9224 --user-data-dir=~/.aa-mcp/chrome-profiles/<account>.
User logs in once. Profile retains cookies between launches.
save_session_from_browser (MCP tool) or aa-mcp-server --extract-session <name> connects to http://127.0.0.1:9224/json/version to discover the WebSocket URL, opens a CDP WebSocket, calls Network.getAllCookies, filters to aa.com domains, persists.

Read the full file on GitHub · 132 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.

7d ago First seen · 132 lines · 2,327 tokens per session scan A dbe3e782d2d5

Subscribe to this mod's changes

aa-mcp CLAUDE.md is an instructions file published in the GitHub repository thehesiod/aa-mcp (0 stars, last pushed 4mo ago), licensed MIT. It adds 2,327 tokens to every session, about $0.0116 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.

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

aa-mcp: Instructions file for Claude Code