Svelte Commerce
A standalone open-source storefront built with SvelteKit, headless across 26 commerce backends. MIT licensed.
翻译准备中
尚未收集仓库信息。
尚未检测到更新。GitHub 发布版本后会显示在这里。
Manage ChatGPT ads for your Shopify store from Claude Code, Codex or Cursor. MCP server + agent skills. Campaigns start paused.
翻译准备中
正在加载完整 README。
查看完整 README ↗Run your ChatGPT (OpenAI) ads from your own AI agent. An MCP server and agent skills for Shopify merchants: launch campaigns, read reports, guard the budget and fix the product feed from Claude Code, Codex, Cursor or any MCP client. Everything it creates starts paused, and the server will not start spending, raise a budget or bid, archive, re-point an ad or change a feed price until it gets your yes (asked by your client, or confirmed through a short-lived dry-run plan).
Not affiliated with OpenAI or Shopify. "ChatGPT", "OpenAI" and "Shopify" are trademarks of their owners and are used only to say what this works with.
Two parts, one agent:
| Manage ads | Measure results | |
|---|---|---|
| What | A local MCP server that calls OpenAI's Advertiser API | Orders attributed to ChatGPT ads, True ROAS, tracking health |
| Needs | Your own Advertiser API key (OPENAI_ADS_API_KEY) | Avada ChatGPT Ads, free, installed with its app embed on |
| Where the key lives | On your machine only | In the app; your agent gets a read-only key or OAuth approval |
| Tools | 33 ads tools (campaigns, ad groups, ads, previews, insights, feeds, pixels, locations, audit logs) | 13 measurement_* tools, plus Avada's hosted MCP server |
OpenAI's numbers say what OpenAI attributed to its ads. The store's numbers say what actually sold. You want both, side by side, in the same currency. Without the app, the measurement tools say exactly what is missing and how to set it up; they never make up a number.
You need Node.js 20 or later (tested on 22, 24 and 26) and an Advertiser API key: ads.openai.com > Settings > API keys. Put it in your environment, not in a chat:
export OPENAI_ADS_API_KEY=... # add it to your shell profile or a secret manager
Status: v0.2.1. It runs straight from this repository:
npx -y github:Avada-AI/shopify-chatgpt-ads(no npm package; do not install a package with a similar name from npm).
As a plugin (MCP server + all skills; it asks for the key and keeps it in your system keychain). The plugin runs the bundled dist/cli.js, so nothing is installed with npm:
/plugin marketplace add Avada-AI/shopify-chatgpt-ads
/plugin install shopify-chatgpt-ads@avada-ai
Or the MCP server alone, reading the key from your environment when it starts:
claude mcp add-json chatgpt-ads --scope user \
'{"command":"npx","args":["-y", "github:Avada-AI/shopify-chatgpt-ads"],"env":{"OPENAI_ADS_API_KEY":"${OPENAI_ADS_API_KEY}"}}'
Project config example: examples/claude-code.mcp.json.
Add to ~/.codex/config.toml (full example):
[mcp_servers.chatgpt-ads]
command = "npx"
args = ["-y", "github:Avada-AI/shopify-chatgpt-ads"]
env_vars = ["OPENAI_ADS_API_KEY", "AVADA_API_KEY"]
AGENTS.md tells Codex and other agents the safety rules. Skills: npx skills add Avada-AI/shopify-chatgpt-ads -a codex.
.cursor/mcp.json in your project, or ~/.cursor/mcp.json (example):
{
"mcpServers": {
"chatgpt-ads": {
"command": "npx",
"args": ["-y", "github:Avada-AI/shopify-chatgpt-ads"],
"env": {"OPENAI_ADS_API_KEY": "${env:OPENAI_ADS_API_KEY}"}
}
}
}
Run npx -y github:Avada-AI/shopify-chatgpt-ads over stdio with OPENAI_ADS_API_KEY in its environment (example).
The skills work with any agent that reads Agent Skills: npx skills add Avada-AI/shopify-chatgpt-ads (the open skills CLI, Node.js 22.20 or later), or copy a folder from skills/ into .claude/skills/ or .agents/skills/.
export AVADA_API_KEY=avk_live_... and restart your agent. The measurement_* tools start answering.https://avada-chatgpt.firebaseapp.com/mcp as a second MCP server and approve it in the app. The Claude Code plugin and the example configs already list it as avada-measurement.The measurement API (v1) is live. What it returns, its errors and its rate limits (30 calls a minute per key, 100 per store) are in docs/measurement-api.md.
What the server enforces, whatever the agent asks:
以上为 README 的开头部分。其余内容请阅读原文。 查看完整 README ↗