In simple English
Managing product listings and shopping ads inside Google Merchant Center takes too many manual clicks and complex tables. This program lets you talk to an AI assistant to check inventory, update prices, and fix disapproved items. It runs on your own computer and connects directly to your Google account. You do not need to pay for commercial reporting software to query your catalog data. It saves time for store owners who want to automate routine updates without writing code.
What it is
A self-hosted Model Context Protocol (an open standard that lets AI assistants talk to local tools and data sources) server for Google Merchant Center. It provides 126 tools covering products, inventory, reports, and account settings.
What it is good for
Solo ecommerce founders who want to manage their Google Shopping feeds and check product performance using natural language instructions inside Claude.
- Exposes 126 different tools covering almost every part of the Merchant API.
- Includes safety features like an append-only audit log and a one-click rollback tool.
- Comes with a dry-run mode so you can test changes before sending them to Google.
- Requires setting up a Google Cloud project and generating service account credentials.
- Needs a local Python environment and command-line configuration to get started.
- Requires careful permission management so the AI does not make unwanted changes to your catalog.
Paid SaaS reporting tools like Windsor.ai, Catchr, and Adzviser, or manual work in the Google Merchant Center web interface
Claude Desktop or Claude Code
- archpeng/GMC-mcp-server
Another self-hosted Google Merchant Center assistant tool, but built on the older API version instead of the modern one.
- deepset-ai/haystack27k stars
A Python framework for joining language models, document search and tools into one working pipeline.
- Giskard-AI/giskard-oss5.9k stars
A Python library that writes tests for language-model programs and tries to break them on purpose.
- ggml-org/llama.cpp132k stars
A C and C++ library and command-line tool for running language models locally.
pip install gmc-mcp