This is a read-only MCP server for WordPress + WooCommerce that lets you query store data and blog content via the official REST APIs. It never creates, modifies, or deletes any data.
list_products: Search and browse WooCommerce products by name/SKU or filter by status (draft, pending, private, publish). Returns product ID, name, SKU, price, stock status, and permalink. Supports pagination.
get_product: Retrieve full details for a single WooCommerce product by its ID.
list_orders: View recent WooCommerce orders (newest first), optionally filtered by status (pending, processing, on-hold, completed, cancelled, refunded, failed). Supports pagination.
sales_report: Get WooCommerce sales totals — gross sales, order count, and items sold — for a given period (week, month, last_month, or year).
search_posts: Search published WordPress blog posts via the public WordPress REST API (no WooCommerce credentials required). Supports pagination.
Provides read-only access to WooCommerce store data: list/search products, get product details, list orders, and retrieve sales reports.
Allows searching published blog posts via the public WordPress REST API. No authentication required.
Click on "Deploy 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., "@woocommerce-mcp What were last month's sales totals?"
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.
A small, read-only Model Context Protocol server for WordPress + WooCommerce. It lets Claude (or any MCP client) answer questions about a live store — products, orders, sales, and blog posts — over the official REST APIs. No writes, no plugins to install on the store: it talks to the existing WordPress/WooCommerce REST endpoints.
Built and maintained by WPPoland, a senior WordPress developer working with WordPress since 2006. If you need this wired into a real store stack, we build WooCommerce ERP and API integrations and enterprise e-commerce architecture (headless, integrations, AI-ready data).
Tool | What it does | Needs WooCommerce keys |
| List / search products (name, sku, price, stock, permalink) | yes |
| Full details for one product by id | yes |
| Recent orders, newest first, optional status filter | yes |
| Sales totals for a period (week / month / last_month / year) | yes |
| Search published blog posts (public WP REST API) | no |
Everything is read-only. The server never creates, edits, or deletes anything in the store.
Related MCP server: WooCommerce MCP Server by CData
From npm (package name is scoped - the unscoped woocommerce-mcp name is locked on the registry):
npm install -g @wppoland/woocommerce-mcp
# or: npx @wppoland/woocommerce-mcpFrom source:
git clone https://github.com/wppoland/woocommerce-mcp.git
cd woocommerce-mcp
npm install
npm run buildSet three environment variables:
Var | Required | Example |
| yes |
|
| for |
|
| for |
|
Create the WooCommerce keys in WooCommerce → Settings → Advanced → REST API → Add key with Read permission. search_posts works without keys against any public WordPress site.
The keys are sent to your own store over HTTPS as REST query auth. Use HTTPS, and give the key Read access only.
Add to your MCP client config (e.g. claude_desktop_config.json):
{
"mcpServers": {
"woocommerce": {
"command": "node",
"args": ["/absolute/path/to/woocommerce-mcp/dist/index.js"],
"env": {
"WP_URL": "https://shop.example.com",
"WC_CONSUMER_KEY": "ck_xxx",
"WC_CONSUMER_SECRET": "cs_xxx"
}
}
}
}Then ask things like "What were last month's WooCommerce sales?" or "List the 5 most recent orders that are on hold."
WooCommerce MCP open source (read-only): release and ops guide - npm scope, registry, Glama, and how we ship updates without write tools
Field notes published on DEV (not duplicates of wppoland.com pages):
A read-only MCP server for WooCommerce: what AI agents actually need from a store
Syncing a wholesaler's API into WooCommerce without overselling or melting the server
Twelve months after migrating wppoland.com from WordPress to Astro on Cloudflare Pages
Show HN: discussion
npm run check # builds, then asserts all five tools register (no network/credentials needed)Node 18+ (uses the built-in fetch).
Logs go to stderr so they never corrupt the stdio MCP protocol on stdout.
API errors are surfaced with the store's message; credentials are never echoed.
MIT © WPPoland
WooCommerce sales totals for a period (week, month, last_month, year). Gross sales, orders, items.
| Name | Required | Description | Default |
|---|---|---|---|
| period | No | Reporting period (default week) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. It discloses the return metrics (gross sales, orders, items) and period options. However, it does not mention read-only status, response format, or potential errors, though the simple nature reduces need.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Extremely concise: one sentence front-loaded with key details (platform, purpose, periods, metrics). No unnecessary words.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple single-parameter tool with no output schema, the description covers the essential: what it does, what periods are available, and what data is returned. No gaps.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100% with period parameter fully described. The description restates the enum values but adds no additional meaning beyond the schema. Baseline 3 is appropriate as description does not improve understanding.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states it returns WooCommerce sales totals for a period, listing specific metrics (gross sales, orders, items) and periods. It explicitly distinguishes from sibling tools like get_product and list_orders, which focus on individual items or order lists.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies use when sales aggregations are needed but does not specify when to avoid it or contrast with alternatives (e.g., list_orders for detailed view). No explicit guidance on context or prerequisites.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Search published WordPress blog posts (public REST API, no WooCommerce keys required).
| Name | Required | Description | Default |
|---|---|---|---|
| search | Yes | Search term | |
| per_page | No | Results per page (default 10) |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description must carry the full burden of behavioral disclosure. It does disclose that the API is public and that no WooCommerce keys are needed, which is useful. However, it does not mention other behavioral traits such as rate limits, pagination behavior, or what happens if no results are found. The transparency is adequate but minimal.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence of 13 words, extremely concise. It front-loads the key information: what the tool does and a critical constraint (no WooCommerce keys). No unnecessary words are present, making it highly efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the low complexity (2 parameters, no output schema, no enums, no nested objects), the description is minimal but partially complete. It covers the core functionality and a key context point (public API, no keys). However, it does not describe the return format or any output behavior, which would be helpful given the lack of output schema. For a simple tool, it is adequate but could be more complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema already has 100% coverage, describing the 'search' and 'per_page' parameters. The description does not add any additional meaning to these parameters beyond what is in the schema. Therefore, the description adds no extra value to parameter understanding, resulting in a baseline score of 3.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the verb 'Search' and the resource 'published WordPress blog posts'. It also specifies that this is a public REST API with no WooCommerce keys required, which distinguishes it from the sibling tool 'sales_report' that may require such keys. The purpose is specific and unambiguous.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides some context about when to use this tool (public search without WooCommerce keys) but does not explicitly state when not to use it or mention alternatives. It implies that if WooCommerce keys are needed, another tool like 'sales_report' should be used, but this is not directly stated. Usage guidance is present but incomplete.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.1search_postsget_productlist_orderslist_productssearch_postsv0.1.0get_productlist_orderslist_productssales_reportsearch_postsScored across 2 tools
The two tools serve entirely different purposes: one provides WooCommerce sales reports, the other searches WordPress blog posts. There is zero overlap in functionality, making it impossible to confuse them.
Tool names use different patterns: 'sales_report' is a noun phrase, while 'search_posts' follows a verb_noun pattern. This inconsistency makes the set feel ad hoc rather than systematically named.
With only 2 tools for a 'woocommerce-mcp' server, the count is far too low. While a minimal server could be justified, the expected scope for WooCommerce typically includes many more operations (e.g., products, orders, customers).
The tool surface is severely incomplete for WooCommerce. Key operations like managing products, orders, or customers are entirely missing, and the inclusion of a general WordPress search tool unrelated to e-commerce does not address the core domain.
Federated commerce search across independent WooCommerce merchants. Keyless, read-only MCP server.
Unified MCP server for 70+ eCommerce platforms: products, orders, customers, and more.
Read-only MCP server for ClassQuill, a tutoring-business-management platform.
The HubSpot MCP Server acts as a bridge that enables AI assistants and Large Language Models to securely interact with HubSpot CRM data through natural conversation, without requiring users to understand complex API structures. It provides read-only access to standard CRM objects (contacts, companies, deals, tickets, products, invoices, and more) and their associations, secured via OAuth 2.0, allowing AI agents to perform tasks like summarizing deals, fetching company updates, and looking up record changes.
