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.
npx agentmods add skills/s3yed/appie-kit/agentic-webdesign-wordpress-mcpnpx skills add S3YED/appie-kit --skill agentic-webdesign-wordpress-mcpgit clone --depth 1 https://github.com/S3YED/appie-kitWrote 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.
[](https://agentmods.dev/skills/s3yed/appie-kit/agentic-webdesign-wordpress-mcp)<a href="https://agentmods.dev/skills/s3yed/appie-kit/agentic-webdesign-wordpress-mcp"><img src="https://agentmods.dev/badge/skills/s3yed/appie-kit/agentic-webdesign-wordpress-mcp.svg" alt="Measured on agentmods" height="20"></a>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 | $0.00055 | $0.01251 |
| Opus 5 | $0.00028 | $0.00626 |
| Sonnet 5 | $0.00011 | $0.00250 |
| Haiku 4.5 | $0.00006 | $0.00125 |
Grade A, and why
agentic-webdesign-wordpress-mcp 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 6d 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.
How it starts
The opening of the file, as written. The whole thing — 103 lines — stays where its author put it; the contents beside it link to each section on GitHub.
WordPress MCP — AI Agent Ecosystem
Overview
WordPress 7.0 (April 9, 2026) shipped native MCP adapter — the biggest update in WordPress history. Combined with a fast-growing third-party ecosystem, AI agents can now interact with any WordPress site through structured, permission-controlled MCP tools.
WordPress 7.0 Core (Free, Built-in)
What ships in core:
- Native AI Client — WordPress can call AI providers
- Abilities API — granular capability-based access control (replaces role-based permissions)
- Connectors UI — manage AI provider credentials in admin
- MCP Adapter — adapts every registered ability into MCP tools/resources/prompts
- Expanded REST API — analytics, user management, content scheduling endpoints. Response compression + conditional GET.
How it works for AI agents:
- WordPress site exposes MCP endpoint (built into core)
- AI agent (Claude, Cursor, Codex) connects via MCP
- Agent discovers capabilities: create drafts, audit content, manage taxonomies
- All operations respect WordPress roles and permissions
MCP Client Configuration
STDIO transport (local WP-CLI):
{
"mcpServers": {
"wordpress": {
"command": "wp",
"args": ["--path=/path/to/wp", "mcp-adapter", "serve", "--server=mcp-adapter-default-server", "--user=admin"]
}
}
}
HTTP transport via remote proxy:
npx @automattic/mcp-wordpress-remote --url https://yoursite.com --user admin --app-password "XXXX XXXX XXXX XXXX"
MCP endpoint: https://yoursite.com/wp-json/mcp/mcp-adapter-default-server
Headless pattern:
WordPress (MCP backend) → Next.js/Astro/Vite frontend → AI agent at content layer
Third-Party Tools
WP Navigator (wpnav.ai)
- 93 specialized MCP tools — organized in dynamic toolsets for context efficiency
- 8×4 permission matrix: None / Read / Suggest / Write across 8 categories
- Plan-Diff-Apply workflow: AI previews changes as diffs → review → approve/apply
- Instant kill switch: one-click termination of all AI sessions
- Builder cookbooks: compact references for Gutenberg, Elementor, WPBakery
- Audit trail: every AI action logged with who/what/when
- Status: MVP coming mid-2026 (waitlist)
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.
- 6d ago First seen · 103 lines · 55 tokens per session scan A 76e11e18bfb5
agentic-webdesign-wordpress-mcp is a skill published in the GitHub repository S3YED/appie-kit (7 stars, last pushed 10d ago), licensed MIT. It adds 55 tokens to every session and 1,251 once invoked, about $0.0003 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.
Other skills, from other repositories
generate-translations
Use when new translation keys are added to packages to generate new translations strings.
next-upgrade
Upgrade Next.js to the latest version following official migration guides and codemods.
woocommerce-git-draft-pr
Create a high-quality draft PR for the current branch. Use when the user says "create a PR", "draft PR", "open a PR", "make a PR", "push and create PR", or "submit PR".
wordpress-plugin-publish
Use this skill when publishing, submitting, reuploading, verifying, packaging, checking, demoing, or releasing WordPress.org plugins with Pressship. It covers safe Pressship workflows for local plugin directories, WordPress.org SVN checkouts, pending submissions, approved releases, Plugin Check review, package…
staging-subdomain-hunt
Hunt staging via crt.sh when production is WAF-hardened.
wp-action-scheduler
Design and review Action Scheduler jobs in WordPress plugins using Action Scheduler 4.0 public APIs - async, single, recurring, and cron-expression actions; actionschedulerinit load timing; hook/args/group naming; args-aware unique identity and priority; idempotent callbacks; chunked workloads; activation/deactivation…