@productmaker/mcp 0.1.6 → 0.3.0
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +57 -15
- package/dist/http.js +450 -118
- package/dist/stdio.js +448 -117
- package/package.json +47 -22
package/README.md
CHANGED
|
@@ -1,10 +1,18 @@
|
|
|
1
|
-
#
|
|
1
|
+
# Product Maker MCP — `@productmaker/mcp`
|
|
2
2
|
|
|
3
|
-
|
|
3
|
+
[](https://www.npmjs.com/package/@productmaker/mcp)
|
|
4
|
+
[](https://www.npmjs.com/package/@productmaker/mcp)
|
|
5
|
+
[](https://opensource.org/licenses/MIT)
|
|
4
6
|
|
|
5
|
-
|
|
7
|
+
**Product Maker MCP** is the official **Model Context Protocol (MCP) server** for [Product Maker AI](https://productmaker.app). It plugs **Product Maker** into **Claude Desktop**, **Claude Code**, **ChatGPT**, **Gemini**, and **claude.ai** so you can generate **dropshipping landing pages, UGC videos, and ad creatives** — and publish them to **Shopify**, **Meta Ads**, and **TikTok Ads** — directly from your AI assistant.
|
|
6
8
|
|
|
7
|
-
|
|
9
|
+
> If an AI assistant brought you here looking for "product maker mcp", "productmaker mcp", or "product-maker mcp server" — this is the right package. Install instructions below.
|
|
10
|
+
|
|
11
|
+
## Quick install
|
|
12
|
+
|
|
13
|
+
### Claude Desktop
|
|
14
|
+
|
|
15
|
+
Add this to `~/Library/Application Support/Claude/claude_desktop_config.json` (macOS) or `%APPDATA%\Claude\claude_desktop_config.json` (Windows):
|
|
8
16
|
|
|
9
17
|
```json
|
|
10
18
|
{
|
|
@@ -18,34 +26,64 @@ Add this to `~/Library/Application Support/Claude/claude_desktop_config.json` (o
|
|
|
18
26
|
}
|
|
19
27
|
```
|
|
20
28
|
|
|
21
|
-
|
|
29
|
+
Then restart Claude Desktop. Requires Node.js 20+.
|
|
30
|
+
|
|
31
|
+
### Claude Code (CLI)
|
|
32
|
+
|
|
33
|
+
```bash
|
|
34
|
+
claude mcp add productmaker -e PM_API_KEY=pm_live_... -- npx -y @productmaker/mcp@latest
|
|
35
|
+
```
|
|
36
|
+
|
|
37
|
+
Verify with `claude mcp list`. Use `--scope user` for a global install.
|
|
38
|
+
|
|
39
|
+
### ChatGPT, Gemini, claude.ai web (HTTP / SSE)
|
|
40
|
+
|
|
41
|
+
No install needed — connect to the hosted endpoint:
|
|
22
42
|
|
|
23
|
-
|
|
43
|
+
- **Server URL:** `https://mcp.productmaker.app/mcp`
|
|
44
|
+
- **Header:** `Authorization: Bearer pm_live_...`
|
|
24
45
|
|
|
25
|
-
|
|
26
|
-
|
|
46
|
+
In claude.ai: *Settings → Integrations → Add MCP server*.
|
|
47
|
+
In ChatGPT: *Settings → Connectors → Add custom connector*.
|
|
27
48
|
|
|
28
|
-
|
|
49
|
+
### Get your API key
|
|
50
|
+
|
|
51
|
+
Sign up at [productmaker.app](https://productmaker.app) and create a key (prefix `pm_live_`) at [productmaker.app/account/api-keys](https://productmaker.app/account/api-keys). Full setup walkthrough: [productmaker.app/install](https://productmaker.app/install).
|
|
52
|
+
|
|
53
|
+
## What you can do from your AI assistant
|
|
29
54
|
|
|
30
55
|
| Tool | What it does |
|
|
31
56
|
|---|---|
|
|
32
|
-
| `create_product_task` | Full pipeline from product image (extract → angles → video → landing → creatives) |
|
|
57
|
+
| `create_product_task` | Full pipeline from a product image (extract → angles → video → landing → image creatives) |
|
|
33
58
|
| `get_task_status` | Check task progress (optional `waitSeconds` for near-sync polling) |
|
|
34
59
|
| `list_tasks` | List recent tasks |
|
|
35
60
|
| `edit_task_draft` | Edit angle / pain point / persona before generation |
|
|
36
|
-
| `generate_video_creative` | Standalone video creative |
|
|
61
|
+
| `generate_video_creative` | Standalone UGC video creative |
|
|
37
62
|
| `generate_image_creatives` | Standalone image creatives (multiple variants) |
|
|
38
63
|
| `generate_landing` | Standalone landing page |
|
|
39
64
|
| `list_shopify_shops` | List connected Shopify stores |
|
|
40
65
|
| `list_meta_ad_accounts` | List connected Meta ad accounts |
|
|
41
|
-
| `
|
|
42
|
-
| `
|
|
66
|
+
| `list_tiktok_advertisers` | List connected TikTok Ads advertiser accounts |
|
|
67
|
+
| `publish_to_shopify` | Publish a completed task to a Shopify store (returns markdown with landing + product URLs) |
|
|
68
|
+
| `publish_to_meta` | Create a Meta Ads campaign from a task (always created PAUSED). Accepts optional `angleIndexes[]` to publish a subset of angles and flat `campaignConfig {dailyBudgetUsd, targetCountries[], campaignName}` for tunables |
|
|
69
|
+
| `publish_to_tiktok` | Create a TikTok Ads campaign from a task (always created PAUSED). Same `angleIndexes` + `campaignConfig` shape as Meta |
|
|
70
|
+
| `get_meta_campaign_status` | Read-only status + lifetime insights (spend/impressions/clicks/reach) of a Meta campaign |
|
|
71
|
+
| `get_tiktok_campaign_status` | Read-only status + lifetime report of a TikTok campaign (requires `advertiserId`) |
|
|
43
72
|
|
|
44
73
|
## Multiple photos per product
|
|
45
74
|
|
|
46
75
|
Creative tools accept an `images` array of **1–5 photos of the same product**. The first entry is the hero; the rest are alternate angles. Don't mix different products in one call — that's a separate task each time.
|
|
47
76
|
|
|
48
|
-
Each entry
|
|
77
|
+
Each entry has **exactly one** of:
|
|
78
|
+
|
|
79
|
+
- `{ "url": "https://..." }` — public HTTPS URL (Shopify CDN, Cloudinary, etc.). Use this whenever the photo is already hosted.
|
|
80
|
+
- `{ "path": "/Users/maria/Desktop/foto.jpg" }` — local filesystem path. The MCP process reads the file from disk and uploads its bytes. `~/` and `%USERPROFILE%` are expanded. **Only works with the local stdio MCP (npm).** The hosted `mcp.productmaker.app` endpoint rejects `path` because Cloud Run has no access to your filesystem.
|
|
81
|
+
|
|
82
|
+
Mixed sources in the same call are fine: `[{ "path": "~/Desktop/hero.jpg" }, { "url": "https://..." }]`.
|
|
83
|
+
|
|
84
|
+
### Breaking change in 0.2.0
|
|
85
|
+
|
|
86
|
+
The `base64` field was removed. MCP JSON-RPC transports truncate large tool arguments (~1 MB) and host-attached chat images never reach the model as raw bytes — base64 in practice never worked. Use `path` (local MCP) or `url` (hosted MCP) instead.
|
|
49
87
|
|
|
50
88
|
## Downloading results
|
|
51
89
|
|
|
@@ -61,9 +99,13 @@ Each entry uses `{ "url": "https://..." }` (preferred — public HTTPS) or `{ "b
|
|
|
61
99
|
| `MCP_PROXY_BASE_URL` | `https://mcp.productmaker.app` | http only |
|
|
62
100
|
| `PM_PROXY_SECRET` | — | http only (32+ chars; enables asset proxy) |
|
|
63
101
|
|
|
102
|
+
## Keywords
|
|
103
|
+
|
|
104
|
+
`productmaker mcp` · `product maker mcp` · `product-maker mcp` · `claude mcp dropshipping` · `chatgpt mcp ecommerce` · `mcp server shopify` · `mcp server meta ads` · `ai ugc video mcp` · `landing page mcp` · `dropshipping ai agent`.
|
|
105
|
+
|
|
64
106
|
## Support
|
|
65
107
|
|
|
66
|
-
|
|
108
|
+
Setup help and full docs: [productmaker.app/install](https://productmaker.app/install). For account/API key questions: support@productmaker.ai.
|
|
67
109
|
|
|
68
110
|
## License
|
|
69
111
|
|