Google Merchant Center MCP Server
Connect Claude, ChatGPT, or any AI tool to your Google Merchant Center account. Diagnose product feeds, fix Shopping listing issues, and analyze price competitiveness — all in plain English, with no Merchant Center report-builder required.
What is the Google Merchant Center MCP?
The Pipeboard Google Merchant Center MCP (Model Context Protocol) Server connects AI assistants like Claude, ChatGPT, and custom agents to the Google Merchant Center API (the Merchant API and Merchant Reports API). Instead of clicking through the Merchant Center interface to find disapproved products or chase down feed errors, you ask questions in plain language and the assistant answers straight from your account.
It is built for ecommerce merchants, Shopping advertisers, and agencies who want fast answers about their Google Shopping presence — product approval status, item issues, price competitiveness, best sellers, and feed health — without learning the Merchant Center Query Language or the underlying API.
What you can do with it:
How Pipeboard uses your Google Merchant Center data
What we request, why, and what we never do with it
When you connect Google Merchant Center, Pipeboard requests access through Google’s official OAuth consent screen. We only request the Google scopes needed to run the analytics and feed tools described on this page, plus your basic account identity so we can show which Google account a Merchant Center account belongs to. We use this access solely to fulfil the requests you (or your AI assistant, on your behalf) make.
The access we request, and why:
contentReads your Merchant Center accounts, products, and diagnostics — approval status, item issues, price competitiveness, best sellers, and performance — and, only when you explicitly ask, updates product attributes such as destinations and custom labels. This is the access that powers every tool on this page.
userinfo.emailIdentifies the connected account so we can label which Google login a Merchant Center account belongs to. Important if you connect more than one Google account.
userinfo.profileDisplays the connected account name in your Pipeboard connections list so you can tell your connections apart.
Our commitments
- We never sell your Google Merchant Center data, and we never use it for advertising.
- Your data is used only to respond to the requests you or your AI assistant make — it is not used to train AI models.
- You can disconnect Google Merchant Center at any time from your connections page, which revokes Pipeboard’s access.
- Read-first by default: write tools (destinations, custom labels) only run when you explicitly ask, and bulk writes require confirmation.
- Pipeboard’s use of information received from Google APIs adheres to the Google API Services User Data Policy, including the Limited Use requirements.
See the shared Pipeboard for Google page for how every Google integration uses your data, plus full details in our Privacy Policy and Security pages.
Getting Started
Set up in under 2 minutes
1. Sign up for a Pipeboard account:
pipeboard.co/auth/signup →2. Connect your Google Merchant Center account (you’ll review and approve the access above on Google’s consent screen):
pipeboard.co/connections →3. Add the MCP server to Claude (or another MCP client):
https://google-merchant.mcp.pipeboard.co/Use this URL as a Streamable HTTP MCP server in your client. Authentication is handled automatically through your Pipeboard session.
Connect to Your AI Tool
The Google Merchant Center MCP works with any MCP-compatible client. Just add the server URL and start asking about your Shopping feeds in natural language.
Claude Pro / Max
Recommended- 1.Open claude.ai/customize/connectors
- 2.Click "Add custom connector"
- 3.URL:
https://google-merchant.mcp.pipeboard.co/
Claude Code
CLI / VS CodeRun this command in your terminal:
claude mcp add --transport http pipeboard-google-merchant https://google-merchant.mcp.pipeboard.co/Then type /mcp in Claude Code to authenticate with Pipeboard.
Alternative: use an API token for instant setup (no browser auth needed):
claude mcp add --transport http pipeboard-google-merchant https://google-merchant.mcp.pipeboard.co/?token=pk_...Get your token at pipeboard.co/api-tokens
Claude Desktop JSON configuration:
Add this to your Claude Desktop MCP settings (Settings → MCP Servers → Add):
{
"mcpServers": {
"google-merchant": {
"url": "https://google-merchant.mcp.pipeboard.co/"
}
}
}More integrations:
Try these prompts
Feed Health Check
"List my Google Merchant Center accounts and summarize how many products are disapproved and the top item issues"
Disapproval Triage
"Show me the approval status and item issues for product online~en~US~SKU123 and tell me how to fix them"
Price Competitiveness
"Compare my product prices against the market benchmark for the US and list where I am priced above the benchmark"
Performance + Labels
"Show my top products by clicks for the last 30 days, then tag my best sellers with a custom label for campaign segmentation"
What’s included
Products & diagnostics (read-only)
- List accounts and account info
- List products with aggregated approval status
- Per-product approval status and item issues
- Account-wide item issues summary
- Product status changes over time (daily snapshots)
- Per-product item quality score (click potential)
Performance & market analytics
- Product performance (clicks, impressions, CTR, conversions)
- Performance rolled up by destination country
- Price competitiveness vs. market benchmarks
- Price insights with predicted conversion uplift
- Best sellers by category and country
- Competitive visibility vs. competitor domains
Feeds & writes (opt-in)
- List product data sources (feeds)
- Create a primary API data source (feed)
- Update product destinations (Shopping Ads, Free Listings, …)
- Bulk-edit custom_label_0..4 for campaign segmentation
- Writes are explicit, support dry-run, and confirm bulk changes
Cross-store & raw queries
- Shopify × GMC coherence check (surfaces feed divergences)
- Run raw Merchant Center Query Language (MCQL) reports
- Filter, sort, and limit on every analytics tool
Best Practices
- List your Merchant Center accounts first, then pass the merchant ID on every request
- Start with the item issues summary to find systemic feed problems before drilling into single products
- Set explicit date ranges (e.g. last 30 days) on performance queries for consistent comparisons
- Preview writes with dry-run, then confirm bulk destination or custom-label changes before they apply
- Use custom labels (custom_label_0..4) to segment products for Google Ads Shopping campaigns
- Run the Shopify × GMC coherence check to catch divergences that cause disapprovals or wasted ad spend