shopware-mcp
Provides tools for interacting with Shopware 6 through its Admin API and Store API, enabling management and analysis of products, orders, customers, categories, promotions, stock, sales channels, scheduled tasks, reports, audits, checkout simulation, and limited optional writes.
Sends monitoring alerts to Slack when orders stop, payments fail, the shop becomes unavailable, or when normal operation resumes, including diagnostic context from watch mode.
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., "@shopware-mcp run a health audit on my shop and flag anything stuck"
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.
Introducing shopware-mcp
A Shopware 6 shop is about two hundred entities behind one Admin API. Ask an
assistant "is everything okay with the shop?" and the honest answer takes seven
searches with Criteria filters, three state machines by their technical names,
a couple of aggregations, and an OAuth token it must never repeat back to you.
Wire a model straight to that API and it gets all of it, including the right to
PATCH a price because a prompt said so.
The Model Context Protocol turned "give the model real tools" into a one-line config change. It says nothing about what a good tool for a shop looks like: which of the two hundred entities matter on a Tuesday morning, what "stuck order" means, or that a stock correction should be shown before it is sent.
shopware-mcp is that layer. One small server that speaks MCP to the host and the Admin API to the shop, and knows Shopware well enough to answer in one call what used to take an afternoon in the admin. It also notices when orders stop coming, and tries the checkout the way a customer would to find out why:
Curated tools | Products, orders and their history, documents, customers, categories, promotions, reviews, payment and shipping methods, plugins, stock, sales channels, scheduled tasks, the shop's trading settings: twenty tools that return compact JSON with exact totals, descriptions written for a model, and Shopware's own Criteria filters. No invented query language. |
The customer's view |
|
A pulse |
|
Ready for the campaign |
|
A watch that says why |
|
Synthetic customers |
|
Ready for AI shoppers |
|
Before the next update |
|
Pages in the chat | In hosts that show MCP Apps (Claude, ChatGPT, VS Code), |
Hosted, nothing to install |
|
What a discount costs |
|
An audit |
|
Reports and a forecast |
|
An escape hatch |
|
A brake | Read-only unless you start it with |
Shops are not identical, so the tool list is not either: at startup the server looks up which extensions are installed and registers extra tools for the ones it knows. A plain shop gets the core set. A shop with more plugins gets a bigger agent, without configuration.
Related MCP server: magento-mcp-server
See it work
Six hours without an order, and why. Sunday evening. The pulse compares the silence with the same hours of the last eight Sundays, which always brought three to seven orders, and puts the odds of chance at about one in 170. The agent then tries to buy something the way a customer would and finds the storefront in maintenance mode. Nothing was ordered, nothing changed.
The checkout as a customer sees it. A customer in Switzerland says a code does not work. A throwaway cart through Shopware's own Store API explains both problems at once: Switzerland is not a country of that channel, and the code's promotion ended in August. Then the search explains why a product never shows up.
Every morning, one page. shopware-mcp brief --html brief.html writes the
pulse, the audit and the last seven days as one self-contained page that loads
nothing from anywhere and follows the reader's dark mode. From cron, with
--slack for a one-paragraph summary in a channel.
Open a real one.
Least privilege in one command. shopware-mcp setup logs in as an admin
once, creates a role with exactly the privileges the tools need, measured
against a real shop and not guessed, and an integration that is not an
administrator. It shows the secret once, verifies both and prints the host
config. Run it again after an upgrade and it brings the role up to date while
the keys stay.
Every recording on this page is real output from the server against a Shopware
6.7.13 test shop with generated demo data, replayed from the transcripts in
docs/demo/. Tool calls and results are verbatim, shortened to
fit the screen. The prose is what an MCP host says with them.
One question, one call. Three paid orders are still waiting for shipment, the storefront is in maintenance, a summer promotion outlived August. The answer names order numbers and amounts, and offers the safe next step.
Numbers the shop computed itself. Totals, channels, states, a monthly timeline and the top product for eight months, from one call. No order was paged through; Shopware's aggregations did the work.
No tool for that? There is a schema for that. Manufacturers have no
dedicated tool. The agent reads the entity's schema, spots mediaId, and
filters on it. The same path reaches every other entity, custom ones included.
Writes show their hand first. With --allow-write, a stock correction
comes back as the request it would send. Only an explicit dryRun: false
touches the shop, and the result is re-read from Shopware.
Ship it, then prove it. A delivery transition is two requests, shown before they are sent: the tracking code onto the delivery, then the state change. The order's history afterwards names the transition, the states and who made it.
A product and its launch code, from one sentence. product_create picks
the shop's default tax and derives the net price, and says so in the dry run.
The promotion arrives inactive, so nobody sees a code before it was checked.
Moderation with a reply. Two reviews wait for approval. The spam stays hidden, the complaint is approved together with the shop's public answer, and the model never had to touch the admin.
People, not just revenue. New accounts by group, how many customers ordered and how many came back, the guest share, and the top customers with their share of the period, next to the period before.
A shop with more plugins gets a bigger agent. The core tools are ready immediately. The extension lookup finishes in the background, four tools appear, the host is told to refresh its list, and a compliance question has an answer.
Reorder before it hurts. stock_forecast reads six months of line items
through one aggregation, joins them with the current stock, and says per
product how many days are left, when it hits zero, and how much to order. Nine
of these are already oversold; two are still fine today and will not be in
October.
The same audit, no host in sight. shopware-mcp audit prints the findings
as Markdown and exits non-zero when something is critical (or, with
--fail-on warning, when anything is off). Put it in cron and read the mail;
put it in CI and let the job fail. shopware-mcp report does the same for the
numbers.
A shop with an operations plugin gets an operations agent. FroshTools is the open-source toolbox many Shopware hosters install. When it is there, three more tools appear: the platform's health checks, the message queue with its worker, and the dependency advisories. The agent tells stale search results apart from a dead worker.
Fifty-six invoices, three at a time. order_documents_bulk_create finds the
paid orders that never got an invoice, oldest first, and shows the single request
that would create them before it does. Every order counts against the write
budget. Then scheduled_tasks_list explains how the backlog grew: 31 of 33
tasks overdue, none ever run, the scheduler is not running. tag_assign marks
the order for the team, creating the tag on the way.
Know before the agent finds out. shopware-mcp doctor probes what the integration may read, reads its role for the write privileges where it can, and names the missing one per tool. An administrator gets a wall of ticks; a support-desk role gets told exactly what to grant.



What's in the box
Twenty curated tools |
|
Shop settings |
|
Order history |
|
Checkout simulation |
|
Storefront search |
|
Shop pulse |
|
Campaign check |
|
Returns report |
|
Health audit |
|
Sales report |
|
Customer report |
|
Stock forecast |
|
Any entity |
|
Plugin-aware tools | The server detects installed, active extensions and adds tools for the ones it knows. Packs: FroshTools (platform health checks, message queue, dependency advisories) and Merqo. Off with |
Documents |
|
Guarded writes |
|
A command line too |
|
A GitHub Action |
|
Resources and prompts |
|
Shopware's vocabulary | Filters are Shopware Criteria filters ( |
Portable schemas | Every tool schema is checked to avoid constructs that some MCP clients misread, so the same server works in every host. |
A solid client | OAuth client credentials with early token refresh, one retry on 401 and on 429/5xx with |
Three ways to serve | stdio for desktop hosts, stateless Streamable HTTP with an optional bearer token, and a hosted mode for many shops behind OAuth 2.1 (PKCE, dynamic client registration, client ID metadata documents). |
Packaged four ways | npm with build provenance, a Docker image on GHCR for amd64 and arm64, a one-click |
Who it is for
You run a shop and want to ask it questions instead of clicking through the admin. Stuck orders, low stock, last month's numbers, one prompt each.
You run an agency and look after many shops. The core here covers one shop per server; the multi-shop, audited, hosted version is what the author builds for clients (see Open core).
You build Shopware plugins and want your custom entities reachable by an agent today, and your own tools registered tomorrow.
entity_searchdoes the first; one file undersrc/extensions/does the second.You build agents and want an MCP server that behaves: compact output, honest totals, dry runs, no surprises in the schema.
60 seconds
1. Let setup create the integration. It logs in as an admin once (the password is never stored), creates a read-only role with exactly the privileges the tools need and an integration using it, verifies both and prints or writes the host config:
npx shopware-mcp setup --url https://shop.example.com --user admin --for claude-desktop --writeAdd --allow-write for the write tools and --settings for shop_settings; --dry-run shows the role's privileges first. After an upgrade, run the same command again: it updates the role and keeps the keys. Rather click it yourself? Create an Integration under Settings → System → Integrations, give it a role (see permissions) and continue with step 2.
2. Or let the wizard test existing credentials and write the host config for you:
npx shopware-mcp init # asks for URL, key and secret, tests them, prints the config
npx shopware-mcp init --for claude-desktop --write # or merges it into the host's config file
npx shopware-mcp doctor # which tools can this integration use, and what is missing
npx shopware-mcp audit --fail-on warning # the shop audit as Markdown, exit 1 when something is off
npx shopware-mcp report --interval week # the sales report of the last 30 days as Markdown
npx shopware-mcp brief --html brief.html # pulse, audit and the last 7 days as one HTML pageOr run the server by hand:
export SHOPWARE_URL=https://shop.example.com
export SHOPWARE_CLIENT_ID=SWIA...
export SHOPWARE_CLIENT_SECRET=...
npx shopware-mcp # stdio (default)
npx shopware-mcp --http --port 3333 # Streamable HTTP on http://127.0.0.1:3333/mcp
npx shopware-mcp --allow-write # also register the guarded write tools3. Connect a host (or let init --write do it):
Download shopware-mcp.mcpb from the latest release and double-click it, or add this to claude_desktop_config.json:
{
"mcpServers": {
"shopware": {
"command": "npx",
"args": ["-y", "shopware-mcp"],
"env": {
"SHOPWARE_URL": "https://shop.example.com",
"SHOPWARE_CLIENT_ID": "SWIA...",
"SHOPWARE_CLIENT_SECRET": "..."
}
}
}
}claude mcp add shopware \
-e SHOPWARE_URL=https://shop.example.com \
-e SHOPWARE_CLIENT_ID=SWIA... \
-e SHOPWARE_CLIENT_SECRET=... \
-- npx -y shopware-mcpThey all take the same three fields. Cursor reads .cursor/mcp.json, VS Code .vscode/mcp.json (under servers instead of mcpServers), Windsurf ~/.codeium/windsurf/mcp_config.json, Gemini CLI ~/.gemini/settings.json, Codex CLI a [mcp_servers.shopware] table in ~/.codex/config.toml, Zed its context_servers block. init --for <host> --write writes each of them:
{
"mcpServers": {
"shopware": {
"command": "npx",
"args": ["-y", "shopware-mcp"],
"env": {
"SHOPWARE_URL": "https://shop.example.com",
"SHOPWARE_CLIENT_ID": "SWIA...",
"SHOPWARE_CLIENT_SECRET": "..."
}
}
}
}Hosts that read the official MCP registry find it as io.github.bnymnDev/shopware-mcp.
docker run --rm -p 3333:3333 \
-e SHOPWARE_URL=https://shop.example.com \
-e SHOPWARE_CLIENT_ID=SWIA... -e SHOPWARE_CLIENT_SECRET=... \
ghcr.io/bnymndev/shopware-mcpThe image serves Streamable HTTP on http://127.0.0.1:3333/mcp. Point any HTTP-capable host at that URL. Add -e SHOPWARE_MCP_HTTP_TOKEN=<random secret> and the endpoint requires Authorization: Bearer <secret>; without a token, keep it on localhost or behind a proxy that authenticates (self-hosting notes).
4. Ask. The first useful question is usually "Is everything okay with the shop?"
Ask it anything
You say | The agent calls |
"Is today normal?" |
|
"Why can't customer 10009 check out?" |
|
"Why does the code SUMMER26 not work?" |
|
"What does shipping to Switzerland cost?" |
|
"Why can nobody find the steel shirt?" |
|
"Is everything okay with the shop?" |
|
"How did we do in August?" |
|
"Which products are below 5 in stock?" |
|
"Summarise order 10042 for a support reply." |
|
"Which customers ordered more than ten times?" |
|
"Is the PayPal plugin up to date?" |
|
"Which manufacturers have no logo?" |
|
"Set the stock of SW10084 to 40." |
|
"Order 10042 shipped with DHL, tracking 00340434." |
|
"The bank transfer for 10038 arrived." |
|
"How was last week compared to the week before?" |
|
"Send me the invoice for 10042." |
|
"Note on 10042: customer called, ships Monday." |
|
"What happened to order 10042, and who did it?" |
|
"Who is customer 10042 and what did they order last?" |
|
"Who were our best customers this quarter?" |
|
"Which reviews are waiting for approval?" |
|
"Approve the review from Dominique and thank her." |
|
"Which payment methods does the storefront offer?" |
|
"Create a 10 % code AUTUMN10 for October." |
|
"Add the product Bench, SW10200, 119 euro, 3 in stock." |
|
"Two came back from the customer, add them to SW10084." |
|
"What do I need to reorder in the next two weeks?" |
|
"Orders per payment method last month, with revenue?" |
|
"Which paid orders have no invoice yet? Create them." |
|
"Are the cron jobs running at all?" |
|
"Mark this customer as VIP." |
|
"Is guest checkout on, and what is the default tax?" |
|
"Give SW10084 this picture: https://…/bench.jpg" |
|
"Thumbnails are missing, is the platform okay?" |
|
"Set it up with the least rights it needs." | not a tool: |
"Which of my tools will fail with this integration?" | not a tool: |
"Send me one page every morning." |
|
"Will our Black Friday codes work?" |
|
"Tell me if orders stop on Black Friday." |
|
"What do customers send back most?" |
|
"Orders stopped. Why?" |
|
"Can a Swiss guest still pay with PayPal?" |
|
"What would 20 % off over 50 euro have cost us last month?" |
|
"Do we sell anything below cost?" |
|
"Is the shop getting better or worse?" |
|
"How is the shop doing?" |
|
"Can ChatGPT and Gemini sell our products?" |
|
"Can we update to 6.8 yet?" |
|
"Are we ready for the GPSR?" |
|
"Mail me the audit every Monday." | not a tool either: |
Filters, in one screen
Every search tool takes the same filter array, and every entry is a Shopware Criteria filter:
{ "type": "equals", "field": "active", "value": true }
{ "type": "range", "field": "stock", "value": { "lt": 5 } }
{ "type": "range", "field": "orderDateTime", "value": { "gte": "2026-06-01" } }
{ "type": "equals", "field": "transactions.stateMachineState.technicalName", "value": "paid" }
{ "type": "contains", "field": "name", "value": "shirt" }
{ "type": "equalsAny", "field": "id", "value": ["…", "…"] }
{ "type": "equals", "field": "manufacturer.name", "value": "Acme" }Anything you can filter in the Admin API works here too, associations included.
Need a raw field that the compact output leaves out, such as customFields,
ean or weight? Pass fields: ["customFields", "ean"] and it is added to
every item. Reading a shop in another language? Set SHOPWARE_LANGUAGE_ID.
The full cheat sheet has more.
Tools
Tool | Access | Purpose |
read | Shop info | |
read | Shop settings | |
read | List sales channels | |
read | Search products | |
read | Get product | |
read | Search orders | |
read | Get order | |
read | Order history | |
read | List order documents | |
read | Download document PDF | |
read | Search customers | |
read | Get customer | |
read | List categories | |
read | List promotions | |
read | Check promotions before a campaign | |
read | What would a discount cost? | |
read | Margins: below cost and thin | |
read | Search product reviews | |
read | List payment methods | |
read | List shipping methods | |
read | List plugins and apps | |
read | Scheduled tasks | |
read | Get stock | |
read | Stock forecast | |
read | Search like a customer | |
read | Simulate a checkout | |
read | Run customer journeys | |
read | Ready for AI shopping agents? | |
read | Ready for the next Shopware update? | |
read | Why are orders not coming in? | |
read | Sales report | |
read | Customer report | |
read | Returns report | |
read | Shop pulse | |
read | Shop brief | |
read | Shop health audit | |
read | Entity schema | |
read | Search any entity | |
write (guarded) | Set stock (guarded) | |
write (guarded) | Update product (guarded) | |
write (guarded) | Create product (guarded) | |
write (guarded) | Set product cover image (guarded) | |
write (guarded) | Transition order state (guarded) | |
write (guarded) | Transition delivery state (guarded) | |
write (guarded) | Transition payment state (guarded) | |
write (guarded) | Add internal order note (guarded) | |
write (guarded) | Create order document (guarded) | |
write (guarded) | Create documents for many orders (guarded) | |
write (guarded) | Toggle promotion (guarded) | |
write (guarded) | Create promotion (guarded) | |
write (guarded) | Update customer (guarded) | |
write (guarded) | Moderate review (guarded) | |
write (guarded) | Assign tags (guarded) |
Every parameter of every tool: docs/tools.md. Searches return
{ total, page, limit, items } with exact totals, limit is capped at 50, and
errors come back as { error: { status, code, detail } } so the model can
react instead of guessing.
Resources: shopware://shop, shopware://sales-channels, shopware://order/{orderNumber},
shopware://product/{productNumber}. Prompts: order_summary, low_stock_report, weekly_review.
Plugin-aware tools
At startup the server asks the shop which extensions are installed and active,
in the background, and registers extra tools for the ones it knows. A shop that
does not answer simply keeps the core tools. --no-extensions turns the whole
mechanism off.
Two packs ship today. FroshTools,
the open-source operations plugin, adds frosh_health (platform health and
performance checks), frosh_queue (message queue transports, waiting messages,
worker) and frosh_composer_audit (dependency advisories); all read-only, the
plugin's own maintenance actions are never called. Merqo
adds merqo_health, merqo_einvoice_inbox, merqo_returns_search and
merqo_abandoned_carts. Shops without a plugin never see its tools, and nothing
in the core tools changes either way. Support for another vendor's extensions
is one file under src/extensions/, tested against the installed plugin; a
pack names the ACL privileges its plugin's routes need, and shopware-mcp setup
grants them when that plugin is installed. Pull requests are welcome.
Safety
Read-only by default. Without
--allow-write(orSHOPWARE_MCP_ALLOW_WRITE=true) the write tools are not registered. An agent cannot discover what it cannot call.Every write is a dry run first. All fifteen write tools, from
stock_settotag_assign, default todryRun: trueand return{ dryRun: true, wouldSend: { method, url, body } }, a list when one call needs several requests. A real write returns the re-fetched entity.A write budget.
SHOPWARE_MCP_MAX_WRITES=20refuses the twenty-first real write of a process withWRITE_BUDGET_EXHAUSTED; dry runs stay free. No prompt can lift it.Narrow writes.
product_updatetouches name, description, active and one currency's price;product_createmakes a simple product and nothing else;product_cover_setadds one picture (JPEG, PNG, WebP, GIF or AVIF, never SVG) that the shop itself downloads.promotion_createcreates one cart discount, inactive unless told otherwise.customer_updatetouches the active flag and the group. The transition tools only move state machines; nothing moves money. Documents come from Shopware's own generator and are never sent by this server;order_documents_bulk_createmakes at most fifty per call and charges the write budget once per order.tag_assignadds or removes tags by name and leaves the rest of the record alone. Nothing deletes. Nothing else is writable.A simulated cart is not an order.
checkout_simulateandstorefront_searchgo through Shopware's own admin proxy to the Store API with a random context token no visitor holds. The order route is never called and the cart is deleted afterwards; what remains is a context row Shopware expires by itself. Simulating as a customer does not touch that customer's own session or saved cart. Extensions that react to saved carts, such as abandoned-cart mailers, do see the simulated cart as that customer's, so simulate as a real customer only where that is fine.Least privilege by default.
shopware-mcp setupgrants each tool exactly the privileges it was measured to need against a role that had nothing else, and never administrator rights. Two privileges reach further than their tool and stay out unless you ask: reading the whole system config, SMTP passwords and payment keys included (--settings), and installing extensions (--plugin-updates). Setup only changes a role it created, names every privilege it adds or removes, and shows the new secret before anything else can fail. The admin password is used for one login over https, or plain http to this machine only, and never stored.Scrubbed reads.
entity_searchstrips passwords, keys, tokens and hashes from every payload and refuses entities that exist to hold credentials or system internals: users, integrations, ACL roles, apps, system config.No secrets anywhere. Credentials never appear in output, logs or error messages. Logs go to stderr only, at
errorlevel unless you ask for more.No telemetry. The server talks to your shop and to your host. Nothing else.
HTTP transport. Set
SHOPWARE_MCP_HTTP_TOKENand every call to/mcpneeds that bearer token, compared in constant time. Without it, bind to localhost (the default) or put it behind a reverse proxy that authenticates; the server warns when it is reachable further without a token.Requests time out. A shop that stops answering costs one request 30 seconds (
SHOPWARE_MCP_TIMEOUT_MS), not the whole session.
Found something? See SECURITY.md.
Configuration
Variable | Required | Notes |
| yes | Shop base URL, e.g. |
| yes | Integration access key ID |
| yes | Integration secret access key |
| no |
|
| no | Real writes one process may perform in total; |
| no | Default page size for search tools (default 20, max 50) |
| no |
|
| no | Language UUID for translated fields ( |
| no | Per-request timeout for the Admin API in milliseconds (default 30000, 1000 to 600000) |
| no | Bearer token the HTTP transport requires on |
| no |
|
| no | Time zone for "today" in |
| no | Rule packs and files for the audit, e.g. |
| no | JSON file with customer journeys for |
|
| The admin login |
CLI flags override the environment: --allow-write, --max-writes <n>, --no-extensions, --http, --port <n>, --host <addr>, --log-level <level>. Commands: setup, doctor, init, brief, audit and report; npx shopware-mcp --help lists their options.
The Integration needs read permissions on the entities the tools touch and
write permissions for the write tools. shopware-mcp setup grants exactly
those; Administrator is the quick path for a dev shop
(which permissions).
Design principles
Shopware's vocabulary, not ours. Filters, field paths, state names and entity names are Shopware's. A tool call reads like the Admin API request it becomes, and a Shopware developer needs no second dictionary.
Compact by default, complete on request. Items carry what a model needs to reason and page. Raw fields come with
fields, more rows withpage, and long text is truncated rather than dumped.Reading is free, writing is explicit. Write tools exist only when asked for, default to a dry run, and return the exact request. The model sees the consequence before the shop does.
Let the shop do the maths. Totals, timelines and top products are Shopware aggregations with exact counts, not client-side sums over pages.
Vendor-neutral core. Extension packs live in their own files, are registered only when the shop has the extension, and never change how the core tools behave. No telemetry, no phone-home.
The reasoning behind individual choices is in docs/decisions.md.
Documentation
Document | What is in it |
Integration, first run, host configs, example questions, the filters cheat sheet | |
Every tool with every parameter, generated from the code | |
Transports, Docker, reverse proxies, Shopware permissions, operations | |
Design decisions and the reasoning behind each | |
Setup, ground rules, end-to-end tests, releasing | |
What to report and where | |
What changed in each version |
Open core
Everything in this repository is MIT and stays that way. It covers one shop, one operator, interactive use.
The same author builds Merqo, a commercial suite of Shopware extensions for EU compliance and daily operations. This server detects them and adds matching tools, but it never requires them, and the core tools behave the same either way.
Agencies and merchants running this at scale usually need more, and that is what I build and operate for clients:
Multi-shop: one MCP endpoint that routes to dozens of shops with per-shop credentials and permissions
Hosted with audit trail: every tool call logged with who, what and when, role-based access, SLA
Bulk operations and migrations: mass price and stock updates, catalogue imports, safe rollbacks
Custom agents and Shopware plugins: workflows tailored to your ERP, PIM or support desk
Interested? Open an issue with the consulting label or reach out via github.com/bnymnDev. Using shopware-mcp in production and want it to stay maintained? Sponsoring helps.
Building from source
pnpm install
pnpm dev # stdio server via tsx
pnpm test # vitest + msw-mocked Admin API
pnpm build # tsup → dist/ (npm) and dist/bundle/ (self-contained)
pnpm pack:mcpb # Claude Desktop bundle → shopware-mcp.mcpb
pnpm inspect # MCP Inspector against dist/
pnpm docs:tools # regenerate docs/tools.md and the tool tables in both READMEs
pnpm docs:demos # re-render the recordings in docs/demo/ from their transcriptsEnd-to-end tests against a real Shopware (dockware/dev, or any shop you point them at) run with pnpm test:e2e; see CONTRIBUTING.md.
Status
v0.9. Everything on this page is implemented, covered by unit tests against mocked Admin API responses, and exercised nightly end-to-end against a real Shopware. The recordings above come from Shopware 6.7.13; 6.6 is supported too.
Not in it, on purpose: user management for the HTTP transport (one static token, or a proxy), multi-shop routing and audit trails (the commercial part), and write tools beyond the fifteen that a support desk and a shop manager need on a normal day.
Ideas that fit: more extension packs, more cart errors explained in plain words,
a products_search example gallery. The good first
issues
are a fine place to start.
License
Available Tools
38 toolsagent_readinessReady for AI shopping agents?ARead-onlyIdempotent
Can AI shopping agents (ChatGPT, Gemini, Perplexity, Copilot) find and sell this shop's products? Builds the product feed agents read (Agentic Commerce feed fields, as Google Merchant) from the storefront's visible products and checks each row: name, description, brand, image and price are required; GTIN with a valid check digit, manufacturer number and weight help agents match and ship. Also checks HTTPS and the privacy, terms and revocation pages an agent checkout links to. Read-only. Returns { score (0 to 100), products, gaps[] with share and samples, shop[], checkoutReady, feedSample[] }.
Inputs: maxItems, salesChannelId.
categories_listList categoriesARead-onlyIdempotent
List categories as a flat list with parentId and level so you can rebuild the tree. Each item includes productCount (directly assigned products). Filter by parentId to get one level, or by level=1 for the roots. Returns { total, page, limit, items[] }.
Inputs: page, sort, term, limit, +2 more.
checkout_simulateSimulate a checkoutARead-only
See the checkout the way a customer does: puts products (and promotion codes) into a throwaway cart of a sales channel through Shopware's own Store API, as a guest shipping to a country or as a given customer with their group, prices and rules, and returns what Shopware calculates: prices per item next to the listing price, discounts, shipping, taxes, total, which payment and shipping methods the customer is offered, which are hidden and by which rule, and every cart error with a plain explanation (country not assigned, code expired, product not visible, stock). Nothing is ordered and the cart is deleted afterwards; as a customer, extensions that react to saved carts (abandoned-cart mailers) see it like any other cart of that customer. Use it for 'why can't this customer order?', 'why does this code not work?' or 'what does shipping to Switzerland cost?'. Returns { salesChannel, as, canOrder, items[], promotions[], shipping, totals, problems[], paymentMethods, shippingMethods }.
Inputs: items (required), country, salesChannel, paymentMethod, +3 more.
customer_reportCustomer reportARead-onlyIdempotent
Customer figures for a period straight from Shopware: new accounts (registered vs guest, by customer group), how many distinct customers ordered, the repeat share (two or more orders in the period), the guest order share and the top customers by gross revenue with their share of the total. compareWithPrevious adds the period of equal length before from and the change. Defaults to the last 30 days, cancelled orders excluded. Returns one object.
Inputs: to, from, topCustomers, salesChannelId, +2 more.
customers_getGet customerARead-onlyIdempotent
Get one customer by ID, customer number or email, including all addresses (with default billing/shipping flags), customer group, default and last used payment method. Returns one object.
Inputs: email, fields, customerId, customerNumber.
customers_searchSearch customersARead-onlyIdempotent
Search customers by term (name, email, customer number) and/or Criteria filters such as email, active, guest, group.name or lastOrderDate ranges. Returns compact summaries with group, order count and last order date. Use customers_get for addresses and payment method. Returns { total, page, limit, items[] }.
Inputs: page, sort, term, limit, +2 more.
document_downloadDownload document PDFARead-onlyIdempotent
Fetch one order document (invoice, delivery note, credit note, cancellation invoice) as a PDF. The file is returned to the host as an embedded resource next to the document's metadata; the model sees the metadata only. Get the documentId from order_documents_list. Read-only, nothing is marked as sent. Returns { id, type, documentNumber, orderNumber, mimeType, bytes, attachments[] }.
Inputs: documentId (required).
entity_schemaEntity schemaARead-onlyIdempotent
Describe a Shopware entity: its fields (name, type, flags such as required/translatable) and associations (name, relation, target entity), taken from the shop's own entity schema. Call it without entity to list all entity names. Use it to build precise filters for entity_search or the fields parameter of other tools. Returns one object.
Inputs: entity.
entity_searchSearch any entityARead-onlyIdempotent
Escape hatch for everything without a dedicated tool: search ANY Shopware entity (e.g. product_manufacturer, property_group, shipping_method, tax, country, newsletter_recipient, product_review, seo_url, cms_page, media) with the same Criteria filters, sort and paging. Use entity_schema first to see the available fields and associations. Credentials and internal fields are always stripped, long values such as stored files are truncated, and entities holding secrets (users, integrations, system config) are blocked. Prefer the dedicated tools when one exists. aggregations asks Shopware to count, sum or average over the whole match (terms, sum, avg, min, max, count, stats, histogram, one nested metric per bucket), e.g. orders per payment method or revenue per month for any entity; set limit: 1 when only the aggregations matter. Returns { entity, total, page, limit, items[], aggregations? } with raw (scrubbed) data.
Inputs: entity (required), page, sort, term, +5 more.
journeys_runRun customer journeysARead-only
Synthetic customers: run fixed buying paths through the shop's real cart, e.g. 'Swiss guest with code SUMMER26', 'regular customer pays by invoice', and say which one broke and why. Each journey takes the inputs of checkout_simulate plus expectations: the cart can be ordered, given payment or shipping methods are offered, codes apply, the total stays in a range. Without journeys it runs the ones in SHOPWARE_MCP_JOURNEYS (a JSON file). Nothing is ordered; carts are deleted. Returns { ok, passed, failed, results[] }.
Inputs: journeys.
margin_checkMargins: below cost and thinARead-onlyIdempotent
Find active products whose net price is below their purchase price, products with a thin margin, and products that an automatic discount running right now pushes below cost: the '60 % instead of 6 %' mistake on the price side. Uses Shopware's purchase price; products without one are counted, not guessed. Read-only. Returns { checked, withoutPurchasePrice, automaticDiscount, summary, belowCost[], thin[], lossWithDiscount[] }.
Inputs: maxItems, minMargin.
order_documents_listList order documentsARead-onlyIdempotent
List the documents generated for one order: invoices, delivery notes, credit notes and cancellation invoices, with document number, type, creation date and whether they were sent. Use document_download to fetch one as PDF. Returns { orderId, orderNumber, total, items[] }.
Inputs: orderId, orderNumber.
order_historyOrder historyARead-onlyIdempotent
The state history of one order: every order, payment and delivery transition in chronological order with the previous and new state, the action name and who triggered it (admin user, API integration or the system). Use it for 'what happened to this order and when?'. Orders imported without transitions have an empty history. When there are more transitions than limit, the newest ones are kept. Returns { orderId, orderNumber, orderDate, total, entries[], note? }.
Inputs: limit, orderId, orderNumber.
orders_getGet orderARead-onlyIdempotent
Get one order by ID or order number with line items, billing/shipping addresses, transactions (payment method and state) and deliveries (shipping method, tracking codes). Use it to answer detailed questions about a single order. Returns one object.
Inputs: fields, orderId, orderNumber.
orders_searchSearch ordersARead-onlyIdempotent
Search orders by term (order number, customer name/email) and/or Criteria filters such as stateMachineState.technicalName (open, in_progress, completed, cancelled), transactions.stateMachineState.technicalName (paid, open, ...), orderDateTime ranges or orderCustomer.email. Newest first by default. Returns compact summaries with totals, order/payment/delivery state and customer. Use orders_get for line items and addresses. Returns { total, page, limit, items[] }.
Inputs: page, sort, term, limit, +2 more.
payment_methods_listList payment methodsARead-onlyIdempotent
List payment methods with active flag, handler (plugin), availability rule and the sales channels they are assigned to. Filter e.g. active=true or salesChannels.id. Use it for 'which payment methods do we offer?' and to explain why one is missing at checkout. Returns { total, page, limit, items[] }.
Inputs: page, sort, term, limit, +2 more.
plugins_listList plugins and appsARead-onlyIdempotent
List installed plugins and apps with version, active/installed state and the available upgrade version (when the shop can reach the Shopware store). Use it to check whether an extension is installed or outdated. Returns { total, items[] }.
Inputs: type, activeOnly.
products_getGet productARead-onlyIdempotent
Get one product by ID with everything an agent usually needs: description, price, stock, tax, manufacturer, categories, properties, media and all variants with their options, stock and price. Use products_search or stock_get to find the ID first. Returns one object.
Inputs: productId (required), fields.
products_searchSearch productsARead-onlyIdempotent
Search products by free-text term and/or Criteria filters (e.g. active, stock, manufacturer.name, categories.id, productNumber). Returns compact product summaries with price, stock, availability, manufacturer, category names and cover image URL. By default only main products are returned; set includeVariants=true to also get variants. Use products_get for the full record of one product. Returns { total, page, limit, items[] }.
Inputs: page, sort, term, limit, +3 more.
promotion_impactWhat would a discount cost?ARead-onlyIdempotent
Before switching a promotion on: replay its cart discount (or one you describe) on the orders of the last days and say what it would have cost: if every eligible order had used it, and at the share of orders that used a promotion so far. Respects a percentage cap and a minimum cart value; rules that limit who gets it are not evaluated, so the result is an upper bound. Read-only. Returns { orders, revenue, eligibleOrders, scenarios, averagePerOrder, capReached, note }.
Inputs: days, discount, promotionId, minCartValue, +1 more.
promotions_checkCheck promotions before a campaignARead-onlyIdempotent
Before Black Friday or any sale: check every promotion that runs or starts before a date, active or not, the way Shopware decides whether it applies. Flags a promotion that starts but is still inactive, has no discount, no sales channel or only channels in maintenance, needs a code but has none, has no unused individual codes left, is close to its redemption limit, gives 50 % or more, ends before it starts, or applies automatically together with another one so the discounts add up. Read-only. Returns { window, checked, summary, promotions[] } with findings per promotion, worst first.
Inputs: until.
promotions_listList promotionsARead-onlyIdempotent
List promotions (discount campaigns) with code settings, validity window, redemption limits and a summary of their discounts (scope, type, value). Filter by active or code. Returns { total, page, limit, items[] }.
Inputs: page, sort, term, limit, +2 more.
returns_reportReturns reportARead-onlyIdempotent
How many orders came back and which products come back most, from Shopware's own delivery states (returned, returned partially), no plugin needed. Gives the return rate of the period next to the period before, the revenue of returned orders, and products ranked by the share of their orders that came back. Use it for 'what do customers send back?' or before reordering stock. Read-only. Returns { period, totals, previous, change, products[], note }.
Inputs: to, from, minOrders, topProducts, +1 more.
reviews_searchSearch product reviewsARead-onlyIdempotent
Search product reviews with their rating (1-5 points), text, reviewer, product and moderation state. Filter on status (false = awaiting approval), points, productId, product.productNumber or createdAt ranges. Newest first. Adds averagePoints over the whole match. Use review_moderate to approve or hide one. Returns { total, page, limit, averagePoints, items[] }.
Inputs: page, sort, term, limit, +2 more.
sales_channels_listList sales channelsARead-onlyIdempotent
List sales channels (storefronts, headless APIs, marketplaces) with their type, domains and active flag. Use it to find the sales channel or domain an order or product belongs to. Returns { total, page, limit, items[] }.
Inputs: page, sort, term, limit, +2 more.
sales_reportSales reportARead-onlyIdempotent
Aggregate sales figures for a period straight from Shopware: order count, gross/net revenue, average order value, breakdowns by order/payment/delivery state, payment method, currency and sales channel, a revenue timeline (day/week/month) and the top-selling products. Use it for 'how did we do last month?' questions instead of paging through orders. compareWithPrevious adds the period of equal length before from and the change in orders and revenue. Defaults to the last 30 days, cancelled orders excluded. Returns one object.
Inputs: to, from, interval, timeZone, +4 more.
scheduled_tasks_listScheduled tasksARead-onlyIdempotent
Shopware's scheduled tasks (indexing, cleanups, cache invalidation, plugin jobs) with status, interval, last and next run, and per task whether it is overdue past a grace period, failed, or stuck running for over a day. Many overdue tasks with no recent last run mean the scheduler or message worker is not running, which shows up as stale search results, missing thumbnails and unsent mails. Read-only. Returns { total, summary: { byStatus, overdue, failed, stuck, longestOverdueMinutes, lastRun }, tasks[], problems[], truncated }.
Inputs: graceMinutes, onlyProblems.
shipping_methods_listList shipping methodsARead-onlyIdempotent
List shipping methods with active flag, delivery time, tracking URL pattern, availability rule and the sales channels they are assigned to. Filter e.g. active=true or salesChannels.id. Returns { total, page, limit, items[] }.
Inputs: page, sort, term, limit, +2 more.
shop_auditShop health auditARead-onlyIdempotent
Run a one-shot health check across the shop and return prioritised findings: paid orders not shipped, old unpaid orders, shipped orders never completed, out-of-stock and low-stock products, products without cover image, delivery time or sales channel visibility, expired promotions still active, promotions in the next 14 days that will not work, sales channels in maintenance mode, storefronts missing legal pages (imprint, terms, privacy, revocation, shipping), reviews awaiting moderation, scheduled tasks overdue or failed, and extensions with pending updates. Each finding has a severity, total count, sample items and a hint. Also reports which EU duties (e-invoicing, accessibility, packaging reporting, AI labelling) appear to be covered by an installed extension, guessed from extension names, and whether Shopware itself is set up for ZUGFeRD e-invoices. The shop's own rules (Shopware filters, e.g. 'active products without a manufacturer') run too: pass them as rules, or point SHOPWARE_MCP_RULES at a JSON file. Ready-made packs check product data for the GPSR, the accessibility act and shopping feeds (rulePacks). Start here when asked 'is everything okay with the shop?'. Read-only. Returns one object.
Inputs: rules, maxItems, timeZone, rulePacks, +4 more.
shop_briefShop briefARead-onlyIdempotent
One look at the whole shop, as a manager wants it in the morning: orders and payments right now against a usual day, the audit's findings, and the last seven days' revenue. Hosts that show MCP Apps get it as an interactive page with charts. Read-only. Returns { headline, today, audit, last7Days } in short; use shop_pulse, shop_audit or sales_report for the details of one part.
Inputs: timeZone.
shop_diagnoseWhy are orders not coming in?ARead-only
Look at the usual suspects in one call when orders stop or customers complain: storefronts in maintenance or inactive, a test purchase of the best seller of the last two weeks with the payment methods really offered, extensions installed or updated in the last 24 hours, errors in Shopware's log in the last 6 hours (failed mails included), and scheduled tasks that stopped. Nothing is ordered. Returns { causes[], fine[] }: likely causes first, and what was checked and found fine.
Inputs: no named parameters.
shop_infoShop infoARead-onlyIdempotent
Get basic facts about the connected Shopware shop: version, edition (Community/Commercial), default currency and default language, plus whether write tools are enabled on this server. Use it first to orient yourself or to confirm the connection works. Returns one object.
Inputs: no named parameters.
shop_pulseShop pulseARead-onlyIdempotent
How is the shop doing right now? Orders and revenue since local midnight next to the same hours of the same weekday in previous weeks, the last order, and how unusual the current quiet spell is: the orders the same stretch brought in earlier weeks and the chance of seeing none by accident (a Poisson estimate). 'unusual' means the checkout, payment or storefront may be broken; follow up with checkout_simulate. Also compares today's failed or cancelled payments with their usual share. On a campaign day compare with last year (baseline 'last-year') or raise the expectation (expectFactor 3 on Black Friday), so a quiet spell is judged against what the day should bring. Public holidays in the compared weeks are left out (DE, AT, CH). Read-only. Returns { today, typical, change, lastOrder, silence, payments, history[] }.
Inputs: weeks, baseline, holidays, timeZone, +2 more.
shop_settingsShop settingsARead-onlyIdempotent
Read the shop's trading settings from Shopware's system configuration, for the whole shop or one sales channel with inheritance: basic information (shop name, contact, legal pages), login and registration (guest checkout, double opt-in, password rules), cart, listing (products per page, sorting, reviews), tax, newsletter, addresses and documents. Only these domains are readable; mail servers, licences and plugin secrets are not, and credential-like keys are dropped. Use it for 'is guest checkout on?' or 'what is the default tax?'. Returns { salesChannelId, inherited, settings: { : { key: value } } }.
Inputs: domains, salesChannelId.
stock_forecastStock forecastARead-onlyIdempotent
Which products run out soon, from real sales: units sold per product in the last days (cancelled orders excluded), the current available stock, the days of cover at that pace, the date the stock reaches zero and a reorder quantity that keeps it in stock through the horizon plus restockDays more days (a negative stock is a backlog and is covered too). Lists the active products whose cover is below horizon days, soonest first. Products without sales in the window are never listed. Use it for 'what do I need to reorder?'. Returns { window, horizon, restockDays, total, items[], notes? }.
Inputs: days, limit, horizon, restockDays, +1 more.
stock_getGet stockARead-onlyIdempotent
Get stock and available stock for one product by ID or product number, including every variant. Use it for 'how many X are left?' questions. Returns one object with a variants[] list (empty for simple products).
Inputs: productId, productNumber.
storefront_searchSearch like a customerDRead-onlyIdempotent
Run a search in a sales channel exactly as a customer would, through Shopware's Store API: same visibility, stock and closeout rules, same ranking and prices. Optionally explain one product: its position in the results, or why it does not show up (inactive, not visible in the channel, link-only visibility, closeout without stock, not in the search index, no search keyword matching the term). Read-only. Returns { salesChannel, term, total, items[], explain? }.
Inputs: term (required), limit, explain, salesChannel.
update_checkReady for the next Shopware update?ARead-onlyIdempotent
Before a Shopware update, a major one like 6.8 included: the version available next and the security issues it fixes, Shopware's own requirement checks, and for every extension whether it works with that version (compatible, update the extension first, a compatible version announced, not compatible, or not in the store so test it yourself), straight from Shopware's update service. Read-only: it never starts an update. Needs the privilege system:core:update (and system_config:read for the extensions), which setup grants with --plugin-updates. Returns { currentVersion, update, upToDate, requirements[], extensions[], summary, blockers[], notes[] }.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 38 tools
Most tools have clearly distinct resource/action targets, and descriptions explicitly differentiate close pairs like products_search vs storefront_search, orders_search vs orders_get, and the various diagnostic tools. There is some overlap among shop_brief, shop_pulse, shop_audit, shop_diagnose, and entity_search vs dedicated tools, but the boundaries are usually explained well enough.
All names use snake_case, but the convention is mixed: many follow resource_action (orders_search, customers_get), while others are noun_noun or verb-first (order_history, checkout_simulate, update_check, sales_report). Singular/plural is inconsistent too (orders_* vs order_history, order_documents_list), though names remain readable.
38 tools is heavy for a single server and well above the typical coherent range. The broad Shopware admin domain justifies many operations, but the surface still feels sprawling and would benefit from consolidation, especially around diagnostics, reporting, and entity escape hatches.
Read/analysis coverage is strong across products, orders, customers, promotions, stock, checkout, reporting, and diagnostics, but the lifecycle is almost entirely read-only. There are no create/update/delete operations for products, orders, customers, promotions, or settings, which is a notable gap for a general shop-management server.
Maintenance
Related MCP Connectors
Unofficial Shopify MCP Pack — wraps the Shopify Admin REST API (2024-01)
Manage a Hyprcart store: catalog, prices, stock, orders and content, with the merchant's consent.
Connect AI assistants to your Webanto workspace to review products and copy proposals, explore SEO and imported Search Console opportunities, and search organization knowledge. Inspect workspace capabilities, connection health, usage, and supported operations. Access requires OAuth or a scoped Webanto API key and follows the authorized organization, permissions, and scopes. With separate consent for the applicable paid AI operation, create a product copy proposal and track its job for review; this workflow does not publish changes to your store. A Webanto account and the relevant connected services or uploaded knowledge are required. Paid AI operations require the applicable subscription and available credits. Authentication is required for MCP discovery; an anonymous HTTP 401 is an access challenge, not evidence of a service outage. Official connector repository: https://github.com/empline/webanto-mcp. Support: support@webanto.com.
Governed MCP gateway for business apps: roles, previews, approvals and one audit log.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients to work with one or many Horoshop stores through the public API, control panel and storefront cart — reading and updating the catalog, processing orders, managing SEO, redirects, marketplace feeds, design and settings. Write operations preview changes by default, require confirmations for bulk or irreversible actions, and verify results by reading them back.1MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI assistants to manage Magento 2 / Adobe Commerce products, stock, orders, and customers through 12 read/write MCP tools with secure, audited access.AGPL 3.0
- AlicenseNot gradedqualityCmaintenanceConnects MCP-compatible clients to a Shopify store's Admin GraphQL API, exposing products, orders, customers, inventory, and sales data as callable tools. It enables natural-language store queries, low-stock and sales summaries, customer support answers, and creation of draft products for review.MIT
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients to run one or more WooCommerce stores through the REST API: browsing the catalog, working through orders, issuing refunds, adjusting prices and stock in bulk, and reading sales analytics. Every write is previewed before it is applied and can be recorded to an audit log.136 npm1MIT