MCP App Store
by KeenEthics
FeedShine Google Shopping Feed icon

FeedShine Google Shopping Feed MCP Server for Claude and ChatGPT

By Digital Darts

Overview

Grow sales on Google, Meta, Microsoft, TikTok, Pinterest, and more, right from Claude. FeedShine connects Claude to the product feed your Shopify store sends to every channel. Junk barcodes, missing identifiers and shipping gaps are caught before Google sees them, and Claude shows you why products are disapproved in Google Merchant Center, worst first. Claude helps you optimize any field, guided by the searches shoppers type and skills from 10 years growing client Shopping campaigns. You approve every change before it applies. Rewrite titles and every field the Google & YouTube channel locks away, for one product or up to 200 at once. Preview exactly what Google receives for any product. FeedShine changes your feed, never your Shopify products. Requires the FeedShine app on your Shopify store, with AI assistant access turned on.

How to connect

  1. Claude: Open the FeedShine Google Shopping Feed listing in the Claude connectors directory and choose Connect. Claude listing FeedShine Google Shopping Feed exposes 16 tools here.
  2. ChatGPT: Open the FeedShine Google Shopping Feed listing in the ChatGPT app directory and choose Connect. ChatGPT listing FeedShine Google Shopping Feed exposes 16 tools here.

Tools

get_feed

ChatGPT
Get one feed's full configuration: its saved settings, the rule behind every attribute, the file URL and the latest run. Settings are grouped in tabs (metadata, target, basic, media, identifiers, detail, label, shipping, others, custom, supplemental, inventory, reviews).

get_mapping_schema

ChatGPT
The rule vocabulary for feed attribute mappings: which attributes accept a mapping, the product fields a rule can read (including the store's master fields as master.<name>), the condition operators, the value sources (field, static, combine, lookup, extract, liquid), the limits, and a worked example. A mapping is how ONE update_feed_settings call fixes a field for the entire catalog, including filling values that are missing (condition is_empty plus a fallback value source). Read this before proposing any mappings.attributes change. No arguments.

get_optimization_guide

ChatGPT
The app's feed optimization playbook. Without section, lists every section with its summary and current affected count so you can pick where to start. With a section id (issues, titles, descriptions, images, identifiers, categories, price-availability, details, bundles, shipping, campaigns), the full guide: rules, checklist, examples, and which attributes to change. Read the relevant guide BEFORE proposing changes to any feed attribute it covers.

get_search_queries

ChatGPT
Lifetime Google Search Console query data for product pages, from the copy the app imports when the merchant syncs search data. With productId, the queries that product ranks for (clicks, impressions, position) so its title can be aligned to real demand. Without productId, the store's top title/query mismatch opportunities, highest impressions first. Fails with instructions when Search Console isn't connected or synced.

list_feeds

ChatGPT
List every product group and its feeds (type, format, enabled state, market binding) with each feed's latest generation run. Start here to find feed ids. Each feed carries its market name and locale, so feeds serving different languages are told apart before any text is written to them.

list_product_issues

ChatGPT
Google Merchant Center issues for this store, as of the app's last nightly sync: one row per issue code with severity, affected product counts, sample products and the destinations it applies to. Account-level issues are included. Covers the whole account (file feeds and the native channel too). Call this FIRST when the merchant asks why products are disapproved or wants to fix issues. Then inspect specific products with preview_product and fix via set_product_override or update_feed_settings.

list_products

ChatGPT
List products a feed covers, paginated, with per-product include/exclude state, attribute overrides (merged, plus storeOverrides and feedOverrides apart), stock, tags, the first variants' SKU, barcode, price and weight, and (API feeds) Google item status. filter: all | excluded | customized.

list_section_products

ChatGPT
A page of the products one optimization section flags (up to 50), each with the machine reason it was flagged. No per-product enrichment, so it is cheap to scan a whole field at once. Use this BEFORE optimize_next on any catalog big enough that fixing products one by one is not realistic: read a page, find the cause the products share, and fix the field once with update_feed_settings. On the issues section the rows are the sample products Google named, worst issue first. list_product_issues gives each code's full count and documentation. Paginate with nextCursor.

optimize_next

ChatGPT
The one-product-at-a-time optimization loop, for small catalogs and for the exceptions left after a field-wide fix. Returns the next product needing work in a section with everything required to propose a fix: why it's flagged, its current mapped feed output, its top search queries (null when Search Console isn't synced), and the section's rules. Propose a change, get the merchant's approval, apply with set_product_override (confirm: true), verify with preview_product, then call this again with the returned cursor. done: true means the section is finished. On a large catalog, prefer list_section_products plus one update_feed_settings change over hundreds of overrides.

preview_product

ChatGPT
Run the real feed mapping pipeline for ONE product and return the exact items Google would receive, including overrides and market prices. Use after edits to verify the output.

run_feed

ChatGPT
Queue a full regeneration of one feed now. Cheap and idempotent (no confirm needed) but unnecessary after update_feed_settings or override changes, which queue a run automatically.

set_product_override

ChatGPT
Set one product's attribute overrides and/or include state, for every feed (omit feedId) or for one feed. Overrides replace mapped attribute values on every item of the product, and a feed's own override wins over the store-wide one per attribute. An empty string sends nothing for that attribute, and omitting one the product already has returns it to its mapped value. The map you send REPLACES the product's whole override map, so send every attribute you want kept. The preview lists the ones it would drop under removes, and current shows what is stored today. This tool previews by default: called without confirm, it returns the proposed change and applies NOTHING. Show the merchant the proposal, then call again with confirm: true to apply.

set_product_overrides

ChatGPT
Set DIFFERENT attribute overrides on many products in one call (up to 200). This is the tool for a real title pass: get_search_queries gives each product its own top query and the words missing from its title, so every product needs a different string and no feed mapping can express that. Omit feedId to write once for every feed, which is the default for a title pass. Name a feed only when that feed needs its own values (another language, say). Each entry's overrides REPLACE that product's override map on the chosen layer, exactly like set_product_override, so send every attribute that should stay. The preview lists the ones each entry would drop under removes. An omitted included keeps that product's current include state. Unknown product ids are skipped and reported, not fatal. This tool previews by default: called without confirm, it returns the proposed change and applies NOTHING. Show the merchant the proposal, then call again with confirm: true to apply. One regeneration is queued for the whole batch.

set_products_included

ChatGPT
Bulk include or exclude products (max 1000 ids per call), from every feed (omit feedId) or from one feed. A store-wide exclusion holds in every feed until it is lifted store-wide. This tool previews by default: called without confirm, it returns the proposed change and applies NOTHING. Show the merchant the proposal, then call again with confirm: true to apply.

update_feed_settings

ChatGPT
Update a feed's attribute settings. Pass a PARTIAL settings object mirroring the tab shape from get_feed. Only the keys you send change. mappings.attributes merges per attribute, so you can fix one field per call without resending the others. Pass null for an attribute to drop its mapping and return it to the smart default. A mapping written here applies to this feed only and wins over the store's shared rule for that attribute. The merchant edits shared rules in the app. Call get_mapping_schema before writing a mapping. This tool previews by default: called without confirm, it returns the proposed change and applies NOTHING. Show the merchant the proposal, then call again with confirm: true to apply. Changes reach Google on the next generation run (queued automatically on save).

get_feed

Claude

get_mapping_schema

Claude

get_optimization_guide

Claude

get_search_queries

Claude

list_feeds

Claude

list_product_issues

Claude

list_products

Claude

list_section_products

Claude

optimize_next

Claude

preview_product

Claude

run_feed

Claude

set_product_override

Claude

set_product_overrides

Claude

set_products_included

Claude

update_feed_settings

Claude

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/feedshine"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/feedshine)