Skip to main content
Glama

switch

by ai.switchapp
OverviewDiscussionsAdmin

Video To Prompt

video_to_prompt
Read-only

Turn one of your finished Video Analysis reports into ONE reusable generation prompt that recreates the source video's look, energy, pacing and mood, with a {your photo} placeholder where your own subject goes. Pass report_id (from analyze_video_report or list_vision_reports) or video_url (the exact source URL you already analyzed). Free: it rewrites the analysis you already paid for and never charges. If the video has not been analyzed yet, run analyze_video_report first. Optional focus: pass mode to control what the prompt describes, and engine to pick the model format — also free.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNoWhat the prompt focuses on. action = motion/gestures only, no appearance or scene. scene = setting/camera/lighting only, no subject. action_scene = both, no appearance. description_scene (default) = full prompt including the subject's appearance.
engineNoWhich model format to return: seedance (default, control-format), kling (cinematic prose), or gemini (plain paragraph for Omni).
report_idNoA finished report id from analyze_video_report or list_vision_reports.
video_urlNoAlternative: the exact public https URL you already analyzed.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • addedInput schema / properties / engine
      Added value: +{
+  "description": "Which model format to return: seedance (default, control-format), kling (cinematic prose), or gemini (plain paragraph for Omni).",
+  "enum": [
+    "seedance",
+    "kling",
+    "gemini"
+  ],
+  "type": "string"
+}
    • addedInput schema / properties / mode
      Added value: +{
+  "description": "What the prompt focuses on. action = motion/gestures only, no appearance or scene. scene = setting/camera/lighting only, no subject. action_scene = both, no appearance. description_scene (default) = full prompt including the subject's appearance.",
+  "enum": [
+    "action",
+    "scene",
+    "action_scene",
+    "description_scene"
+  ],
+  "type": "string"
+}
  2. Added

TDQS

Score is being calculated.

All switch toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources