What is ghost-mcp-secure AGENTS.md?

A security-focused connection to Ghost, a publishing and content-management system. It is read-only by default and can expose selected writing, publishing, member, payment and system actions when separately enabled.

Reading Ghost content and, when the relevant permissions are enabled, managing posts, pages, tags, images, publishing, members, monetization and system settings.

It reduces the risk of an agent changing or deleting site content and other data without explicit permission.

How cuonghapvn/ghost-mcp-secure configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to cuonghapvn/ghost-mcp-secure. 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/cuonghapvn/ghost-mcp-secure/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/cuonghapvn/ghost-mcp-secure

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/cuonghapvn/ghost-mcp-secure/agents-md/github.svg)](https://agentmods.dev/instructions/cuonghapvn/ghost-mcp-secure/agents-md)

Your own site

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

Per session 1,684 This file is loaded in full into every session.

When invoked 1,684 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	$0.01684	$0.01684
Opus 5.5	$0.00674	$0.00674
Sonnet 5.5	$0.00337	$0.00337
Haiku 4.5	$0.00168	$0.00168

Measured yesterday against content hash 5038ea03e80a, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ghost-mcp-secure 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 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.

AGENTS.md · 75 lines

How it starts

The opening of the file, as written. The whole thing — 75 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Ghost MCP Secure — hướng dẫn cho AI

Tổng quan

MCP server cho Ghost CMS (blog cuongn.com), "secure-by-default": mặc định chỉ đọc, mỗi nhóm quyền ghi (post/page/tag/ảnh, publish, delete, members, monetization, system) chỉ mở khi đặt cờ env riêng. Hai cách chạy cùng một mã: local qua stdio (src/index.js, Claude Desktop/Code) và remote qua Streamable HTTP + OAuth 2.1 (src/http-server.js, claude.ai / ChatGPT connector). Người dùng: anh Cường; mã nguồn công khai (MIT, có README/REMOTE/SECURITY tiếng Anh cho cộng đồng).

Công ty: tech — Lumen Technologies (Cuong Holdings). Manifest: company.json.
Production: https://ghost-mcp-secure-production.up.railway.app (endpoint MCP /mcp, health /healthz) — Railway project superb-smile, service ghost-mcp-secure, build từ Dockerfile, 1 replica (session trong bộ nhớ). Deploy bằng npm run deploy:railway (cần railway login và bí mật trong env — chỉ anh chạy). GitHub Actions deploy có sẵn nhưng inert (chưa đặt DEPLOY_RAILWAY/DEPLOY_CLOUD_RUN). Chưa xác nhận Railway có tự deploy khi push main → coi push là deploy, cần anh duyệt.
Stack: Node ≥ 18 (ESM, không build step), 2 dependency pin cứng @modelcontextprotocol/sdk 1.29.0 + zod. Máy Mac hiện chưa npm ci (không có node_modules).

Cấu trúc

src/index.js          entrypoint LOCAL (stdio)
src/http-server.js    entrypoint REMOTE: HTTP + OAuth, GET /healthz → "ok", GET / landing, /mcp, /sse (legacy)
src/core.js           lắp server dùng chung hai entrypoint
src/oauth.js          OAuth 2.1 + PKCE stateless (node:crypto)
src/config.js         đọc env, cờ quyền, PUBLIC_URL — NGUỒN CHÍNH về cờ và mặc định
src/helpers.js        dựng kết quả, slim object, upload
src/ghost-client.js   client Ghost Admin API (JWT 5 phút, không dependency)
src/tools/            site, content, images, members, monetization, system — mỗi file một nhóm quyền
test/smoke-remote.mjs smoke test OAuth + MCP chạy local (cần node_modules, tự spawn server với credential giả)
deploy/railway.sh     deploy Railway một lệnh; deploy/cloud-run.sh, setup-gcp-wif.sh — Cloud Run (chưa dùng)
.github/workflows/    deploy-railway.yml, deploy-cloud-run.yml — gated bằng biến repo, hiện skipped
Dockerfile, railway.json, app.json   image + cấu hình Railway/Cloud Run
README.md, REMOTE.md, SECURITY.md    tài liệu công khai (tiếng Anh)
tools/health.py       lệnh health (Python stdlib)
docs/ROADMAP.md       lộ trình và trạng thái
logs/                 log và báo cáo của agent (không đưa vào git)
company.json          manifest cho HQ

Read the full file on GitHub · 75 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.

yesterday First seen · 75 lines · 1,684 tokens per session scan A 5038ea03e80a

Subscribe to this mod's changes

ghost-mcp-secure AGENTS.md is an instructions file published in the GitHub repository cuonghapvn/ghost-mcp-secure (0 stars, last pushed 2d ago), licensed MIT. It adds 1,684 tokens to every session, about $0.0067 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 2026-11-09.

Security Writing and docs

ghost-mcp-secure AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
ghost-mcp-secure AGENTS.mdcuonghapvn/ghost-mcp-secure	Instructions file	0	2d ago	MIT	A	1,684	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

ghost-mcp-secure: Instructions file for Codex