@productmaker/mcp 6.3.1 → 6.7.3

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.
Files changed (4) hide show
  1. package/README.md +11 -1
  2. package/dist/http.js +6867 -3585
  3. package/dist/stdio.js +7112 -4196
  4. package/package.json +1 -3
package/README.md CHANGED
@@ -1,5 +1,15 @@
1
1
  # Product Maker MCP — `@productmaker/mcp`
2
2
 
3
+ ## Market-led video planning
4
+
5
+ For `generate_video_creative` and video outputs of `create_product_task`, an
6
+ explicit `competitorScanEnabled: true` requests the commercial video study.
7
+ Do not ask for a narrative in that case: the adapter submits `auto` and retains
8
+ the canonical study-driven planner. Preserve `replicateWinnerWhenFound: false`
9
+ when the user wants the study without copying a winner. This optional preference
10
+ does not add a mandatory question. Existing per-angle edits and reviews remain.
11
+ MCP 6.7.0 also carries optional per-angle and script-regeneration `narrativeSelection` (`market` or `guided`); publishing still requires the normal release.
12
+
3
13
  [![npm version](https://img.shields.io/npm/v/@productmaker/mcp.svg)](https://www.npmjs.com/package/@productmaker/mcp)
4
14
  [![npm downloads](https://img.shields.io/npm/dm/@productmaker/mcp.svg)](https://www.npmjs.com/package/@productmaker/mcp)
5
15
  [![license: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](https://opensource.org/licenses/MIT)
@@ -89,7 +99,7 @@ continues through the corresponding tool without creating a project. The guided
89
99
  flow uses the project's persisted phase and `guide_dropshipping_launch`'s
90
100
  `nextAction` instead of maintaining a second checklist in the chat.
91
101
 
92
- The launch flow asks for explicit confirmation before the 2,000-credit product
102
+ The launch flow asks for explicit confirmation before the 1,000-credit product
93
103
  research run and before other paid or external mutations, uses the real supplier
94
104
  cost for costing, pauses at user-review gates, and leaves Meta campaigns PAUSED.
95
105
  It does not promise persistent memory, automatic next-day monitoring, traffic-light