Enables the server to fetch and index WordPress plugin source code directly from public and private GitHub repositories.
Indexes block registrations and Gutenberg-specific JavaScript APIs, allowing AI tools to correctly reference editor namespaces and block variations.
Provides a searchable index of WooCommerce hooks, including dynamic names and callback signatures, to ensure accuracy in e-commerce development tasks.
Indexes every action, filter, and API call from WordPress core to provide AI assistants with a verified database for searching and validating hook names.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@wp-devdocs-mcpsearch for hooks to modify the woocommerce checkout billing fields"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
wp-devdocs-mcp
Give your AI coding assistant a verified WordPress hook database instead of letting it guess.
wp-devdocs-mcp is a local MCP server that indexes every action, filter, block registration, and JS API call from WordPress, WooCommerce, Gutenberg, or any plugin you work with. It gives AI tools like Claude Code a verified database to search and validate against instead of relying on training data.
Works with Claude Code, Cursor, Windsurf, and any MCP-compatible client.
Why This Exists
AI coding assistants are changing how we build WordPress plugins. Tools like Claude Code, Cursor, and Windsurf can scaffold entire plugins in minutes — but they all share the same blind spot: hook names come from training data, not from the actual source code.
Most of the time this works fine. Models like Claude Sonnet nail common hooks almost every time. But "most of the time" isn't good enough when you're shipping production code, and not every model is Claude Sonnet. Across the landscape of LLMs doing code generation today:
Some models invent hooks that don't exist —
woocommerce_email_after_order_detailssounds right but isn't realSome use deprecated namespaces —
wp.editor.InspectorControlsinstead ofwp.blockEditor.InspectorControlsMost miss newer hooks — suggesting
pre_get_postsfor WooCommerce order queries when HPOS useswoocommerce_order_list_table_prepare_items_query_argsParameters get mixed up — wrong argument count or order in callback signatures
No model knows your custom plugins — private or proprietary hooks are invisible to every model's training data
The core issue is simple: we can't rely 100% on any model to produce correct WordPress hook names from memory alone. Even the best models benefit from verification, and the rest genuinely need it. You only find out about hallucinated hooks when the code doesn't work — and in an agentic workflow where the AI writes, tests, and iterates autonomously, one bad hook name can send it down a rabbit hole of debugging something that was never going to work.
The Solution
Feed the LLM real data. Instead of hoping the model remembers the right hook name, give it a verified database to query.
wp-devdocs-mcp parses the actual source code of any WordPress plugin and builds a searchable index of every hook with its exact name, type, parameters, file location, and surrounding code context. Your AI assistant queries this index before writing code — so every hook name in the generated code is verified against the real source.
This fits naturally into agentic coding workflows. When Claude Code (or any MCP-compatible assistant) needs to use a WordPress hook, it:
Searches the indexed database for relevant hooks
Validates the exact hook name exists before writing it into code
Reads the context — parameters, docblock, surrounding code — to use it correctly
No hallucination. No guessing. No debugging phantom hooks.
What gets indexed:
Type | Examples |
PHP actions |
|
PHP filters |
|
JS hooks |
|
Block registrations |
|
JS API usages |
|
Markdown documentation | Handbooks parsed into searchable pages (since v1.1.0) |
What the AI gets for each hook:
Exact name (with dynamic name detection for hooks like
woocommerce_thankyou_{$payment_method})Type (action / filter / js_action / js_filter)
Parameters and count
File path and line number
Enclosing function and class
Docblock
Code window (8 lines before, 4 after)
Source plugin name
Quick Start
Install
npm install -g wp-devdocs-mcpOr run directly with npx (no install needed):
npx wp-devdocs-mcpIndex Sources
# Add all preset sources at once (since v1.1.0)
wp-hooks quick-add-all
# Or add individual presets (since v1.1.0)
wp-hooks quick-add wp-core
wp-hooks quick-add woocommerce
wp-hooks quick-add gutenberg-source
wp-hooks quick-add plugin-handbookOr add sources manually:
# WooCommerce (uses trunk branch)
wp-hooks source:add \
--name woocommerce \
--type github-public \
--repo https://github.com/woocommerce/woocommerce \
--subfolder plugins/woocommerce \
--branch trunkThat's it. 3,500+ hooks indexed in under a minute.
Connect to Your AI Assistant
Add the MCP server to your configuration. Create or edit .mcp.json in your project root (or ~/.claude/.mcp.json globally):
{
"mcpServers": {
"wp-devdocs": {
"command": "npx",
"args": ["wp-devdocs-mcp"]
}
}
}Now when you ask Claude Code to write WordPress plugin code, it will automatically search and validate hook names against your indexed sources before generating code.
The server auto-updates stale sources (>24h) in the background on each start. Disable with WP_MCP_AUTO_UPDATE=false. (since v1.1.0)
Available Presets (since v1.1.0)
Pre-configured sources you can add with a single command:
Preset | What It Indexes |
| WordPress core hooks (wordpress-develop, trunk) |
| Gutenberg plugin source code |
| Gutenberg/block editor documentation |
| WooCommerce plugin hooks (plugins/woocommerce) |
| Plugin developer handbook |
| REST API documentation |
| WP-CLI reference |
| Advanced administration handbook |
Indexing Sources
WordPress Core
npx wp-hooks source:add \
--name wordpress \
--type github-public \
--repo https://github.com/WordPress/wordpress-develop \
--branch trunkExpected output:
Source "wordpress" added successfully.
Indexing "wordpress"...
Fetching source: wordpress (github-public)...
Indexing source: wordpress from ~/.wp-devdocs-mcp/cache/WordPress--wordpress-develop
Found 2025 files to check in wordpress
Indexing complete:
Files processed: 2025
Files skipped: 0
Hooks inserted: 3459
Hooks updated: 0
Hooks unchanged: 0
Blocks indexed: 0
APIs indexed: 140Gutenberg
npx wp-hooks source:add \
--name gutenberg \
--type github-public \
--repo https://github.com/WordPress/gutenberg \
--branch trunkWooCommerce
npx wp-hooks source:add \
--name woocommerce \
--type github-public \
--repo https://github.com/woocommerce/woocommerce \
--subfolder plugins/woocommerce \
--branch trunkAny Public Plugin
# Example: Advanced Custom Fields
npx wp-hooks source:add \
--name acf \
--type github-public \
--repo https://github.com/AdvancedCustomFields/acf
# Example: WPGraphQL
npx wp-hooks source:add \
--name wpgraphql \
--type github-public \
--repo https://github.com/wp-graphql/wp-graphqlYour Private Plugins
For private GitHub repos, store your token in an environment variable (never in the config):
export GITHUB_TOKEN=ghp_xxxxxxxxxxxx
npx wp-hooks source:add \
--name my-private-plugin \
--type github-private \
--repo https://github.com/yourorg/your-plugin \
--token-env GITHUB_TOKENLocal Plugin Development
Point directly at a folder on your machine — great for plugins you're actively developing:
npx wp-hooks source:add \
--name my-local-plugin \
--type local-folder \
--path /path/to/wp-content/plugins/my-pluginDocumentation Sources (since v1.1.0)
Index markdown handbooks and documentation alongside source code:
npx wp-hooks source:add \
--name my-docs \
--type github-public \
--repo https://github.com/org/docs-repo \
--content-type docsSource Options
Option | Description |
| Unique name for this source (required) |
|
|
| GitHub repository URL |
| Only index a subfolder within the repo |
| Git branch (default: |
| Environment variable name holding a GitHub token (private repos) |
| Local folder path |
|
|
| Register the source without indexing it yet |
What Gets Indexed
Source code (--content-type source, default):
PHP hooks:
do_action(),apply_filters(),*_ref_array()variantsJS hooks:
addAction(),addFilter(),applyFilters(),doAction()Block registrations:
registerBlockType(),registerBlockVariation()JS API usages:
wp.blocks.*,wp.blockEditor.*,wp.data.*, etc.
Documentation (--content-type docs) (since v1.1.0):
Markdown handbooks parsed into searchable pages with metadata, code examples, and categorization
Specialized parsers for block editor docs, plugin handbook, REST API reference, WP-CLI handbook, and admin handbook
Each hook record includes: exact name, type, parameters, file path, line number, enclosing function/class, docblock, surrounding code context, and dynamic name detection.
MCP Tools
Seven tools are exposed to your AI assistant (four original + three added in v1.1.0):
search_hooks
Full-text search with BM25 ranking across all indexed hooks. Supports filters for type, source, dynamic hooks, and removed hooks.
validate_hook
Exact-match check — returns VALID with file locations, NOT_FOUND with similar suggestions, or REMOVED for deprecated hooks. This is how the AI confirms a hook name before using it in code.
get_hook_context
Returns the full code window around a hook: the line itself, 8 lines before, 4 lines after, the docblock, enclosing function, and class. Gives the AI enough context to use the hook correctly.
search_block_apis
Searches block registrations (registerBlockType, etc.) and JavaScript API usages (wp.blockEditor.*, wp.data.*, etc.). Only matches on structured fields (block name, API call, namespace) — not surrounding code — to prevent false positives.
search_docs (since v1.1.0)
Full-text search across indexed WordPress documentation. Supports filters for document type (guide, tutorial, reference, API, howto, FAQ), category, and source.
get_doc (since v1.1.0)
Retrieve the full content of a specific documentation page by its ID. Returns the page title, content, metadata, code examples, and related links.
list_docs (since v1.1.0)
Browse available documentation with optional filters for type, category, and source. Useful for discovering what documentation is indexed.
CLI Reference
Source management:
wp-hooks source:add Add a source and index it
wp-hooks source:list List all sources with indexed status
wp-hooks source:remove Remove a source and all its data
Presets (since v1.1.0):
wp-hooks quick-add <name> Add a preset source
wp-hooks quick-add-all Add all preset sources
Indexing:
wp-hooks index Re-index all sources (or --source <name>, --force)
wp-hooks update Fetch and re-index stale sources (--source, --force) (since v1.1.0)
Search:
wp-hooks search <query> Search hooks (--type, --source, --include-removed)
wp-hooks search-blocks <q> Search block registrations and JS APIs
wp-hooks search-docs <q> Search documentation (--type, --category, --source) (since v1.1.0)
wp-hooks validate <name> Check if a hook name exists (exit code 0/1)
Maintenance:
wp-hooks stats Hook/block/API/doc counts per source
wp-hooks rebuild-index Rebuild FTS indexes if out of syncCLI Examples
# Search for checkout-related hooks
npx wp-hooks search "woocommerce_checkout"
# Search only filters
npx wp-hooks search "woocommerce_product" --type filter
# Validate a specific hook name
npx wp-hooks validate "woocommerce_before_order_itemmeta"
# Search for Gutenberg block APIs
npx wp-hooks search-blocks "InspectorControls"
# Search documentation (since v1.1.0)
npx wp-hooks search-docs "custom post type"
# Add all presets at once (since v1.1.0)
npx wp-hooks quick-add-all
# Re-index a specific source after updates
npx wp-hooks index --source woocommerce
# Update stale sources (since v1.1.0)
npx wp-hooks update
# Force full re-index (ignore file modification cache)
npx wp-hooks index --force
# See what you have indexed
npx wp-hooks statsHow It Works
Sources are registered via the CLI — each points to a GitHub repo or local folder
Indexing clones/pulls the repo, scans PHP and JS/TS files, and extracts hooks using regex-based parsers
Documentation indexing (since v1.1.0) parses markdown handbooks using specialized parsers that extract metadata, code examples, and categorization
Storage uses SQLite with FTS5 full-text search and WAL mode for fast concurrent reads
Incremental updates skip files that haven't changed (mtime + content hash)
Soft-delete tracking marks hooks that were previously indexed but no longer found as
removedAuto-update (since v1.1.0) refreshes stale sources (>24h) in the background on server start
The MCP server exposes the database as tools over stdio — your AI assistant queries it in real-time
Data Storage
All data lives in ~/.wp-devdocs-mcp/:
~/.wp-devdocs-mcp/
hooks.db # SQLite database (FTS5, WAL mode)
cache/ # Cloned repositoriesVersion History
v1.1.0
Documentation indexing — 7 specialized parsers for WordPress handbooks (block editor, plugin, REST API, WP-CLI, admin, general)
3 new MCP tools —
search_docs,get_doc,list_docsfor querying indexed documentationPreset system — 8 pre-configured sources with
quick-addandquick-add-allCLI commandsAuto-update — background refresh of stale sources (>24h) on each server start (opt-out:
WP_MCP_AUTO_UPDATE=false)update— manual fetch and re-index of stale sourcessearch-docs— search documentation from the terminal--content-type— distinguish between source code and documentation sourcesEnhanced — shows content type and last-indexed time
v1.0.1
Bug fixes (transaction-wrapped deletions, prepared statement cache, cross-platform paths)
JSDoc annotations, ESLint 9 integration
v1.0.0
Initial release — PHP/JS hook extraction, block registration tracking, SQLite FTS5 search, incremental indexing, 4 MCP tools (
search_hooks,validate_hook,get_hook_context,search_block_apis)
Requirements
Node.js 20+
Git
~500MB disk space per large plugin source (WooCommerce, Gutenberg)
License
MIT
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.