build-mcp

build-mcp is a skill for Claude Code from dr-robert-li/cowork-wordpress-expert. It costs 42 tokens per session (2,809 once invoked), scanned C, original, MIT.

A build step that adds the WordPress MCP adapter to a site package. MCP is a way for software tools to communicate with an AI assistant; this step also activates the adapter, exports the database, and records setup details.

In plain words
What is it for?
Use it when preparing a WordPress build that must include the MCP adapter and its configuration metadata.
Why use it?
It removes the manual work of copying, activating, and documenting the adapter during a WordPress build.

Skill for Claude Code

Written for Claude Code: shipped in a Claude Code plugin. Also seen: mentions CLAUDE.md.

Part of the wordpress-expert plugin — 54 skills shipped together

Good fit Use it when preparing a WordPress build that must include the MCP adapter and its configuration metadata.

Compare 6 skills from other repositories ↓
Install with agentmods
npx agentmods add skills/dr-robert-li/cowork-wordpress-expert/build-mcp
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.

Any agent
npx skills add dr-robert-li/cowork-wordpress-expert --skill build-mcp
Clone the repo
git clone --depth 1 https://github.com/dr-robert-li/cowork-wordpress-expert

Made for: Claude Code.

Or install wordpress-expert, the plugin that ships this one along with the rest of its 54 skills.

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.

agentmods badge for build-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/dr-robert-li/cowork-wordpress-expert/build-mcp/github.svg)](https://agentmods.dev/skills/dr-robert-li/cowork-wordpress-expert/build-mcp)
Your own site
<a href="https://agentmods.dev/skills/dr-robert-li/cowork-wordpress-expert/build-mcp"><img src="https://agentmods.dev/badge/skills/dr-robert-li/cowork-wordpress-expert/build-mcp/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.

agentmods 80×15 button for build-mcp

Your own site · 80×15
<a href="https://agentmods.dev/skills/dr-robert-li/cowork-wordpress-expert/build-mcp"><img src="https://agentmods.dev/badge/skills/dr-robert-li/cowork-wordpress-expert/build-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 42 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,809 The whole file, excluding the scripts and references it only reads on demand.
Security scan C 1 finding. 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.

ModelPer sessionOnce invoked
Fable 5.1 $0.00042 $0.02809
Opus 5 $0.00021 $0.01404
Sonnet 5 $0.00008 $0.00562
Haiku 4.5 $0.00004 $0.00281

Measured 11d ago against content hash 66c0427f7b09, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-10, from the pricing page.

Security

Grade C, and why

build-mcp 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 11d 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.

rm -rf "$MCP_ADAPTER_DEST/.git" \
skills/build-mcp/SKILL.md · 242 lines

How it starts

The opening of the file, as written. The whole thing — 242 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Build MCP Skill

Installs the WordPress MCP adapter (pre-compiled, bundled at vendor/mcp-adapter/) into the build's wp-content/plugins/ directory, activates it via WP-CLI so activation is captured in the SQL export, writes a README.md with STDIO transport configuration, and updates build.json with MCP adapter metadata.

Critical sequencing: This skill runs AFTER build-scaffold Section 4 (WP-CLI pipeline including first wp db export) and BEFORE zip packaging. The Docker MySQL container from build-scaffold must still be running when this skill executes — the EXIT trap set in build-scaffold Section 3 must remain active for the duration of this skill.

This skill expects the following variables to already be set by the calling command:

  • BUILD_DIR — absolute path to the build directory (set by build-scaffold Section 2)
  • WP — the WP-CLI command prefix (e.g., wp --path=$BUILD_DIR or the Docker equivalent, set by build-scaffold Section 4)
  • PLUGIN_DIR — absolute path to the CoWork plugin directory (set by COMMAND.md before invoking this skill)

Section 1: MCP Adapter Copy

Copy the pre-compiled MCP adapter from the CoWork plugin's vendor/mcp-adapter/ directory into the build's WordPress plugins directory.

MCP_ADAPTER_SOURCE="${PLUGIN_DIR}/vendor/mcp-adapter"
MCP_ADAPTER_DEST="${BUILD_DIR}/wp-content/plugins/mcp-adapter"

echo "[Build] Installing MCP adapter..."

if [ ! -d "$MCP_ADAPTER_SOURCE" ]; then
  echo "[Build] WARNING: MCP adapter not found at $MCP_ADAPTER_SOURCE"
  echo "[Build] WARNING: Skipping MCP adapter installation. Install manually after import."
  echo "[Build] WARNING: See README.md for manual setup instructions."
  MCP_ADAPTER_INCLUDED=false
  MCP_ADAPTER_ACTIVE=false
else
  mkdir -p "$MCP_ADAPTER_DEST"
  cp -r "$MCP_ADAPTER_SOURCE/." "$MCP_ADAPTER_DEST/"
  # Remove dev artifacts and git files not needed in the build
  rm -rf "$MCP_ADAPTER_DEST/.git" \
         "$MCP_ADAPTER_DEST/.github" \
         "$MCP_ADAPTER_DEST/tests" \
         "$MCP_ADAPTER_DEST/.gitignore" \
         "$MCP_ADAPTER_DEST/phpunit.xml.dist" \
         "$MCP_ADAPTER_DEST/phpcs.xml.dist" \
         "$MCP_ADAPTER_DEST/phpstan.neon.dist" \
         "$MCP_ADAPTER_DEST/composer.json" \
         "$MCP_ADAPTER_DEST/composer.lock" \
         "$MCP_ADAPTER_DEST/package.json" \
         "$MCP_ADAPTER_DEST/package-lock.json" \
         "$MCP_ADAPTER_DEST/CONTRIBUTING.md" \
         "$MCP_ADAPTER_DEST/README-INITIAL.md"
  echo "[Build] MCP adapter copied to wp-content/plugins/mcp-adapter/"
  MCP_ADAPTER_INCLUDED=true
fi

Read the full file on GitHub · 242 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. 11d ago First seen · 242 lines · 42 tokens per session scan C 66c0427f7b09

Subscribe to this mod's changes

build-mcp is a skill published in the GitHub repository dr-robert-li/cowork-wordpress-expert (28 stars, last pushed 6mo ago), licensed MIT. It adds 42 tokens to every session and 2,809 once invoked, about $0.0002 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 skills, from other repositories

systematic-debugging

Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.

obra/superpowers · 21 tokens

local-ai-agents

Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…

microsoft/ai-agents-for-beginners · 200 tokens

next-cache-components-adoption

Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…

vercel/next.js · 95 tokens

insight-error-page

Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…

vercel/next.js · 83 tokens

next-cache-components-optimizer

Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…

vercel/next.js · 170 tokens

next-partial-prefetching-adoption

Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…

vercel/next.js · 103 tokens