Getting it into your agent
It runs from inside its repository, so the clone comes first — what it calls does not travel with the file alone.
git clone --depth 1 https://github.com/hostinger/api-mcp-servernpx agentmods add skills/hostinger/api-mcp-server/wordpressWrote 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/hostinger/api-mcp-server/wordpress)<a href="https://agentmods.dev/skills/hostinger/api-mcp-server/wordpress"><img src="https://agentmods.dev/badge/skills/hostinger/api-mcp-server/wordpress/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.
<a href="https://agentmods.dev/skills/hostinger/api-mcp-server/wordpress"><img src="https://agentmods.dev/badge/skills/hostinger/api-mcp-server/wordpress.svg" alt="Reviewed on agentmods" width="80" 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 | $0.00048 | $0.05114 |
| Opus 5.5 | $0.00019 | $0.02046 |
| Sonnet 5.5 | $0.00010 | $0.01023 |
| Haiku 4.5 | $0.00005 | $0.00511 |
Grade A, and why
headless-step-provision-wordpress 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 today.
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 — 313 lines — stays where its author put it; the contents beside it link to each section on GitHub.
headless-step-provision-wordpress
Create the headless WordPress backend for <domain> and prove it is ready. One platform call lays
every headless site out identically: WordPress in public_html/cms, Hostinger AI Assistant + MCP
adapter, site marked headless. Out: site.json.
WordPress + WooCommerce? This same recipe serves it. When the brief's Suggested backend is
**WordPress + WooCommerce**, provision the WordPress site exactly as below, then run the optional WooCommerce tail in Step 5 (install + activate thewoocommerceplugin and verify the store endpoints; the catalog is seeded in content-model via the per-site WP MCP). WooCommerce is a plugin on this WordPress install, not a separate backend:site.json → backendstays"wordpress"and the store is recorded undersite.json → woocommerce. For a plain WordPress brief, skip Step 5 entirely.
All operations below go through the Hostinger connector (execute).
Fire vs join (background provision). Step 1, plus the queuing call —
hosting_websites_start-setupfor a fresh site (Step 2) orwordpress_installations_installto swap an empty headless shell (Step 2b) — are the fire half: once the job is queued, recordprovision.in_progressand return to do prepare work (see the router../SKILL.md). The readiness poll at the end of Step 2 / 2b, plus Steps 3–6, are the join half — run them when an instance-barrier step needs the backend (or immediately, if the agent can't interleave). An already-completedsite with WordPress at/cmsdetected in Step 1 means provision is already done: recordprovision.completedand adopt it.
Step 1 — Detect before you create (never provision twice)
hosting_websites_list { "domain": "<domain>" }— substring filter, so exact-match the row'sdomain. If a row exists, noteusername,order_id,website_type.- No exact row → nothing exists on this domain → create fresh (Step 2).
- A row exists. If
website_typeis notheadless, stop and tell the user — this domain already hosts a different kind of site (plain WordPress, Node.js, builder, …); never overwrite it. If it isheadless, work out whether WordPress is already installed or the shell is still empty (see the router's Onboarding handoff): checkhosting_websites_list-setups { "domain": "<domain>" }(exact row) andwordpress_installations_list { username, domain, ownership: "all" }(exact row):- Setup
running→ provisioning is underway → skip to Step 2's poll. - Setup
failed→ tell the user and point them at hPanel; do not call start-setup again yourself. - A WordPress install with
directory: "cms"already present (or setuptype: headless_wordpress) → already provisioned → skip to Step 3 (adopt it). - A
headlesssite with no/cmsinstall (an empty headless shell — setuptype: headless_empty, typically from onboarding) → swap it to WordPress (Step 2b). Do not callstart-setupagain — the website already exists; you only install WordPress into it.
- Setup
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.
- today Changed · +63 lines 14c64232c8c8
- 2d ago First seen · 250 lines · 48 tokens per session scan A 6b0fa1e6b220
headless-step-provision-wordpress is a skill published in the GitHub repository hostinger/api-mcp-server (163 stars, last pushed today), licensed MIT. It adds 48 tokens to every session and 5,114 once invoked, about $0.0002 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 2026-10-20.
Other skills, from other repositories
adapter-aws-lambda
Deploy tRPC on AWS Lambda with awsLambdaRequestHandler() from @trpc/server/adapters/aws-lambda for API Gateway v1 (REST, APIGatewayProxyEvent) and v2 (HTTP, APIGatewayProxyEventV2), and Lambda Function URLs. Enable response streaming with awsLambdaStreamingRequestHandler() wrapped in awslambda.streamifyResponse().…
adapter-fetch
Deploy tRPC on WinterCG-compliant edge runtimes with fetchRequestHandler() from @trpc/server/adapters/fetch. Supports Cloudflare Workers, Deno Deploy, Vercel Edge Runtime, Astro, Remix, SolidStart. FetchCreateContextFnOptions provides req (Request) and resHeaders (Headers) for context creation. The endpoint option…
mirrord-temporal
Helps DevOps engineers configure mirrord Operator's Temporal task queue splitting feature end-to-end. Generates the MirrordSplitConfig and MirrordPropertyList Kubernetes CRD YAMLs, the matching mirrord.json splitqueues section with messagefilter and jqfilter, and Helm value guidance. Use this skill whenever the user…
Contract Testing with Pact
Consumer-driven contract testing skill using Pact, covering consumer tests, provider verification, Pact Broker integration, and CI/CD workflows.
API Rate Limiting Testing
Testing API rate limiting implementations including throttling behavior, burst handling, rate limit headers, and distributed rate limiting patterns.
API Versioning Testing
Testing API versioning strategies including URL path, header, and query parameter versioning with backward compatibility validation.