mcp-wordpress AGENTS.md

Project instructions for mcp-wordpress, a server that lets compatible AI tools work with WordPress through structured tools. The instructions describe its setup, architecture, authentication, testing, and security checks.

In plain words
What is it for?
Running the build and tests, checking health, fixing REST API authentication, reviewing the server architecture, and performing type, lint, and security checks.
Why use it?
They give an agent the project-specific information needed to build, test, troubleshoot, and safely change the WordPress integration.

Instructions file for CodexOpenCode

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/docdyhr/mcp-wordpress/agents-md
Clone the repo
git clone --depth 1 https://github.com/docdyhr/mcp-wordpress

Made for: Codex, OpenCode.

Per session 2,700 This file is loaded in full into every session.
When invoked 2,700 The same file — it is already loaded in full.
Security scan C 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5 $0.02700 $0.02700
Opus 5 $0.01350 $0.01350
Sonnet 5 $0.00540 $0.00540
Haiku 4.5 $0.00270 $0.00270

Measured 2d ago against content hash 521fa467b3a0, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade C, and why

mcp-wordpress AGENTS.md scanned grade C with 1 finding 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 2d 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.

Recursive force deletehighDestructive command

rm -rf with a variable or a broad path is one typo away from removing the wrong tree.

- Cache issues: `rm -rf cache/`
AGENTS.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

mcp-wordpress

MCP (Model Context Protocol) Server for WordPress. TypeScript ESM, 71 WordPress tools across 12 categories, exposed over the MCP SDK to any MCP-compatible client.

Quick Start

npm run build               # cross-platform clean + tsc && tsc-alias — required before most test/CLI scripts (tests run against dist/)
npm test                   # Run tests (npm run test:batch)
npm run dev                # Build + run with DEBUG=true
npm run health              # System check (scripts/health-check.js)
npm run fix:rest-auth      # Fix WordPress 401 errors (scripts/fix-rest-api-auth.sh)
npm run lint                # eslint src/ tests/
npm run typecheck           # tsc --noEmit
npm run security:scan       # blocking production npm-audit gate (scripts/security-audit-gate.js) against security-exceptions.json
npm run security:demo       # AI security-scanner demo (scripts/security-demo.js) — informational only, not a gate

Architecture

Core: MCP Server (src/index.ts) registers 71 WordPress tools via src/server/ToolRegistry.ts. Client: src/client/api.ts (WordPressClient) composes per-resource operation classes (src/client/operations/) via constructor injection; App Passwords, JWT, Basic, and API Key are configurable via .env/mcp-wordpress.config.json — Cookie auth is also implemented but is client/programmatic-only (see Authentication below). Tools: Posts(6) Pages(6) Media(5) Users(6) Comments(7) Taxonomies(10) Site(3) Auth(6) Cache(4) Performance(6) SEO(11) System(1) = 71. Key files: src/client/api.ts, src/server/ToolRegistry.ts, src/tools/, src/config/ServerConfiguration.ts, src/utils/logger.ts.

Full per-directory contracts live in the Child DOX Index below — read the applicable child doc before editing.

Configuration

Multi-Site (mcp-wordpress.config.json, gitignored — never commit real credentials):

{
  "sites": [
    {
      "id": "site1",
      "name": "Site 1",
      "config": {
        "WORDPRESS_SITE_URL": "https://site.com",
        "WORDPRESS_USERNAME": "user",
        "WORDPRESS_APP_PASSWORD": "xxxx xxxx xxxx xxxx"
      }
    }
  ]
}

Read the full file on GitHub · 233 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. 2d ago First seen · 233 lines · 2,700 tokens per session scan C 521fa467b3a0

Subscribe to this mod's changes

mcp-wordpress AGENTS.md is an instructions file published in the GitHub repository docdyhr/mcp-wordpress (106 stars, last pushed 4d ago), licensed MIT. It adds 2,700 tokens to every session, about $0.0135 per session on Opus 5. A static security scan graded it C with 1 finding (recursive force delete). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

Related

Other instructions, from other repositories