Skip to main content
Layers exposes two Model Context Protocol (MCP) servers that let AI assistants interact directly with your stores. Use them to manage merchandising, search tuning, catalog operations, and storefront queries through any MCP-compatible client.
ServerEndpointAuthPurpose
Layers MCP serverhttps://app.uselayers.com/mcp/v1OAuth (mcp:use scope)Full store management — catalog, merchandising, search tuning, metrics, and more
Storefront MCP serverhttps://app.uselayers.com/mcp/storefront/v1Storefront API tokenRead-only storefront operations — search, browse, recommendations

Layers MCP server

The main MCP server exposes tools for managing your Layers stores. It uses OAuth authentication and requires the mcp:use scope.

Connecting

Configure your MCP client with the following endpoint:
https://app.uselayers.com/mcp/v1
When you connect for the first time, you’ll be redirected to the Layers dashboard to authorize the connection. After authorization, your MCP client stores the OAuth tokens and reconnects automatically.

Available tools

ToolDescription
store-listList all stores you have access to
store-detailsGet detailed configuration for a store
store-configurationGet or update core store configuration (search instructions, autocomplete prompt, sync preferences, search tuning, storefront options)
store-accessList and manage store members, pending invites, and shareable invite links
store-integrationsList the integration catalog, enable or disable integrations, and queue Global-E rate resyncs
catalog-searchSearch products in the catalog
catalog-product-getGet full details for a specific product
collections-listList collections with filtering
collections-getGet details for a specific collection
ToolDescription
store-operational-statusGet permission failures, sync blockers, recent tasks, and protected collection deletion events for a store
store-clear-permission-failureClear one recorded Shopify permission failure, or clear all when clear_all is true
store-clear-operational-blockClear a specific operational block (for example OAuth access blocked or analytics catalog unavailable)
store-dispatch-sync-operationDispatch a Shopify sync operation (collections, metafield definitions, resource limits, locations, market pricing)
store-list-collection-deletion-eventsList pending and recently resolved protected collection deletion events
store-resolve-collection-deletion-eventApprove or deny a pending protected collection deletion event
ToolDescription
attributes-listList all product attributes
attributes-valuesGet values for a specific attribute
attributes-manageCreate, update, or delete attributes, and update or clear calculated-attribute drafts (draft_update, draft_clear)
attributes-calculated-recipesList pre-built computed attribute templates
attributes-generate-facet-sortGenerate AI-powered facet value ordering
ToolDescription
search-rules-listList search rules
search-rules-manageCreate, update, or delete search rules
semantic-redirects-listList semantic redirects
semantic-redirects-manageCreate, update, or delete semantic redirects
ranking-rules-listList ranking rules
ranking-rules-manageCreate, update, or delete ranking rules
query-expansion-examples-listList query expansion examples
query-expansion-examples-manageCreate, update, or delete query expansion examples
ToolDescription
merchandise-rules-listList merchandising rules
merchandise-rules-manageCreate, update, or delete merchandising rules with pins, expressions, and scheduling. Also supports bulk_enable, bulk_disable, and bulk_delete
blocks-listList recommendation blocks
blocks-manageCreate, update, or delete blocks with strategies, safeguards, and fallback chains. Also supports bulk_publish, bulk_unpublish, bulk_duplicate, and bulk_delete
block-strategies-listList block data strategies and their computation status
ToolDescription
sort-orders-listList available sort orders
sort-orders-previewPreview product ranking for a sort order
ToolDescription
product-familiesList, inspect, create, update, publish/unpublish, or delete manual product families
product-sequencesList, inspect, create, update, publish/unpublish, or delete ordered product sequence groups
variant-breakoutsList, inspect, create, update, enable, disable, or delete option-based variant breakout rules
ToolDescription
metrics-listList custom metrics
metrics-manageCreate, update, or delete metrics
metrics-resultsGet computed results for a metric
metrics-validate-queryValidate a LayersQL expression
analytics-dashboardsList, inspect, create, update, or delete analytics dashboards, and discover visualizable metric blocks
ToolDescription
docs-searchSearch the Layers documentation

Usage pattern

1

List your stores

Call store-list to see all stores you have access to. Note the store slug for each store you want to work with.
2

Pass the store slug

Include the store slug in all subsequent tool calls. For example, if your store is my-store.myshopify.com, the slug is my-store.
3

Use manage tools to make changes

Tools ending in -manage accept an action parameter — typically create, update, or delete, plus tool-specific actions such as bulk variants. All other tools are read-only and safe to call freely.

Example: create a merchandising rule

Ask your AI assistant:
“Pin the product ‘Classic White Tee’ to position 1 in the Summer Sale collection, and boost all products where brand is ‘Nike’ using a soft boost expression.”
The assistant calls merchandise-rules-manage with action: "create" and the appropriate parameters — handling pin positions, collection targeting, and expression configuration automatically.

Bulk actions

Several -manage tools accept bulk variants so an assistant can apply the same change to many records in one call:
  • blocks-managebulk_publish, bulk_unpublish, bulk_duplicate, bulk_delete (pass block_ids)
  • merchandise-rules-managebulk_enable, bulk_disable, bulk_delete (pass rule_ids)
Use bulk actions to act on many records at once — for example, unpublishing all draft blocks after a seasonal campaign, or disabling a batch of merchandising rules outside their window.
{
  "store": "my-store",
  "action": "bulk_unpublish",
  "block_ids": ["blk_123", "blk_456", "blk_789"]
}
The response includes an affected_count so the assistant can confirm how many records changed.

MCP audit log

Every write action your assistant performs through the Layers MCP server is recorded in an audit log. Each entry captures the tool, action, user, store, timestamp, and a JSON context payload. Review activity in the dashboard:
  • Store activityConfigure → Access → MCP Audit Log shows every MCP action recorded for a single store.
  • Your activityProfile → MCP Audit Log shows every MCP action recorded for your account across all stores.
Filter by event, action, or free-text search, and open any entry to inspect its full context.

Storefront MCP server

The Storefront MCP server exposes read-only storefront operations as MCP tools. It uses the same access token as the Storefront REST API, so you can integrate AI assistants into customer-facing experiences.

Connecting

Configure your MCP client with the storefront endpoint and your API token:
https://app.uselayers.com/mcp/storefront/v1
Authentication uses the same storefront access token you use for the REST API. Pass it as a bearer token in the authorization header.

Available tools

ToolDescription
search-textSemantic text search with query understanding and typo tolerance
browse-collectionBrowse a collection with sort orders, merchandising, and faceted filtering
search-similarFind visually and semantically similar products
search-autocompleteGet predictive search query suggestions
facets-getRetrieve available filter facets for a collection
sort-orders-listList available sort orders
blocks-recommendationsGet product recommendations from a configured block
search-contentSearch non-product content (pages, articles, blogs)

Common parameters

Most search and browse tools accept these optional parameters:
ParameterDescription
filter_groupNested filter conditions (AND/OR with operators like eq, in, gt, lt, between, and the geo operators geoRadius, geoPolygon, geoBoundingBox — see Geospatial filtering)
facetsArray of attribute codes to retrieve facet values for
pagination{ page, limit } for paginated results
sort_order_codeSort order to apply (use sort-orders-list to see available codes)
attributesArray of attribute codes to include in the response
contextContextual data for personalization (geo, customer, cart, marketing channel)
identitySession, customer, and device identifiers for behavioral tracking

When to use each server

  • Use the Layers MCP server when you want an AI assistant to help manage your store — creating merchandising rules, tuning search behavior, building sort orders, or analyzing metrics.
  • Use the Storefront MCP server when you want to integrate AI-powered product discovery into a customer-facing experience. It’s also useful when building AI agents that need to search and browse your catalog.

Next steps