What is goodreads-mcp AGENTS.md?

Repository instructions for AI coding agents and contributors working on a Goodreads library tool. They explain the project, its layout, deployment targets, available tool, and strict limits on using Goodreads data.

Use them before modifying the repository, especially when working on Goodreads data access, deployment, project structure, or the tool exposed to Model Context Protocol clients such as Claude Code and Codex.

They give agents the rules and background needed to change the project safely, including which data sources are allowed and which methods are forbidden.

How simhskal/goodreads-mcp configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to simhskal/goodreads-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/simhskal/goodreads-mcp/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/simhskal/goodreads-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/simhskal/goodreads-mcp/agents-md/github.svg)](https://agentmods.dev/instructions/simhskal/goodreads-mcp/agents-md)

Your own site

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

Per session 1,514 This file is loaded in full into every session.

When invoked 1,514 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	$0.01514	$0.01514
Opus 5.5	$0.00606	$0.00606
Sonnet 5.5	$0.00303	$0.00303
Haiku 4.5	$0.00151	$0.00151

Measured 5d ago against content hash f79cd2815e99, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

goodreads-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 · 140 lines

How it starts

The opening of the file, as written. The whole thing — 140 lines — stays where its author put it; the contents beside it link to each section on GitHub.

AGENTS.md

Brief for AI agents and new contributors working in this repository. Read this file end-to-end before making changes, then consult PLAN.md for product rationale and CONTRIBUTING.md for review rules.

What this project is

Goodreads MCP exposes a reader's own Goodreads library to Model Context Protocol clients (Claude Code, Codex, and others) without collecting a Goodreads password.

Goodreads retired its public API, so all data arrives through two sanctioned channels:

Channel	Gives	Limits
Per-shelf RSS feeds	Live shelf data: title, author, ISBN, ratings, dates	~100 most recent items per shelf; RSS key
Goodreads CSV export	Complete library history including reviews	Manual, human-in-the-loop export

Open Library is used only to enrich ISBN metadata in get_book.

Hard boundaries — do not cross

These are non-negotiable and PRs violating them are rejected:

No Goodreads passwords or session cookies. Ever, in any code path.
No scraping and no private/internal Goodreads APIs (including the internal AppSync GraphQL endpoint) in the hosted paths.
No real secrets or real library exports in the repo. Test fixtures must use invented data. The RSS key is a secret: never log it, echo it, or embed it in a URL that gets written to logs or error messages.
Keep the data layer pluggable. If Goodreads retires RSS, Hardcover's GraphQL API is the intended migration target, so provider-specific logic stays behind the core data-source interfaces rather than leaking into servers.

Repository layout

pnpm workspace, TypeScript, ESM throughout. Node.js 20+.

packages/core           RSS parsing, CSV import, library queries, stats, Open Library
packages/server-local   stdio MCP server, published to npm as `goodreads-mcp`
packages/server-vercel  Vercel OAuth 2.1 provider, Postgres storage, onboarding UI
api/server.ts           Single-user Vercel Streamable HTTP endpoint (rewritten from /mcp)
public/index.html       Static landing page for the Vercel deployment

Read the full file on GitHub · 140 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 Changed · -2 lines · -50 tokens per session f79cd2815e99
2mo ago First seen · 142 lines · 1,564 tokens per session scan A d1b79091901f

Subscribe to this mod's changes

goodreads-mcp AGENTS.md is an instructions file published in the GitHub repository simhskal/goodreads-mcp (0 stars, last pushed 5d ago), licensed MIT. It adds 1,514 tokens to every session, about $0.0061 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.

goodreads-mcp AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
goodreads-mcp AGENTS.mdsimhskal/goodreads-mcp	Instructions file	0	5d ago	MIT	A	1,514	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	today	MIT	A	7,461	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	5,649	GitHub Copilot
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	today	MIT	A	4,680	Codex, OpenCode
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	3,093	GitHub Copilot
vscode model-prompts.instructions.mdmicrosoft/vscode	Instructions file	195k	today	MIT	A	2,022	GitHub Copilot

goodreads-mcp: Instructions file for Codex