Pixly

Photo to Video

photo_to_video

Turn a start photo — and optionally an end photo — into a video. With an end photo the camera travels from the first photo and lands exactly on the second (e.g. two views of the same kitchen → an orbit around the island). Pick a ready-made camera move or write your own prompt; choose the model, length and sound. Costs credits from the user's Pixly balance.

Input Schema

Name	Required	Description	Default
`model`	No	kling-v3: 3/5/8/10/15 s, optional sound, lands most precisely on the end frame. kling-2.6: 5/10 s, silent, cheaper.	kling-v3
`sound`	No	Add ambient sound (kling-v3 only; kling-2.6 is always silent).
`format`	No	Video shape. original (default) keeps the start photo's own shape; 16:9, 9:16 or 1:1 crop the photos, centred, to that shape before they are animated.	original
`prompt`	No	Your own description of the video, in any language. Replaces cameraMove when set.
`r2Path`	No	Storage path of a photo already in the user's Pixly library (from list_library, or returned by an upload ticket) — the alternative to imageUrl.
`imageUrl`	No	Start frame — where the video begins. Public https URL or data: URI; either imageUrl or r2Path is required.
`endR2Path`	No	R2 path of the end frame — the alternative to endImageUrl.
`listingId`	No	A property folder (from list_listings or create_listing) to put the result in. Results of a photo that is already in a folder go there by themselves.
`cameraMove`	No	Ready-made camera move used when no prompt is given.	smooth
`endImageUrl`	No	Optional end frame — the camera travels from the start photo and lands exactly on this one. Best when both photos show the same space from different spots.
`durationSeconds`	No	Clip length. kling-v3 takes 3, 5, 8, 10 or 15; kling-2.6 takes 5 or 10.

Output Schema

Name	Required	Description
`jobs`	No	Several jobs at once (get_job with jobIds, or a plan's steps): each one's jobId, status and results
`note`	No
`type`	No
`error`	No
`jobId`	Yes	Pass to get_job to poll
`quote`	No	Present when status is "awaiting_confirmation": nothing ran and nothing was charged yet — the price and settings the user is asked to confirm
`status`	Yes	pending \| processing \| completed \| failed — anything not completed/failed is still running
`createdAt`	No
`resultUrls`	No	Present when completed; valid 7 days
`completedAt`	No
`resultPaths`	No	Storage path of each result — pass one as r2Path (or beforeR2Path, a photos[] item) to run another tool on this result
`creditsCharged`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedOct 11, 2026

addedInput schema / properties / listingId

Added value: +{
+  "description": "A property folder (from list_listings or create_listing) to put the result in. Results of a photo that is already in a folder go there by themselves.",
+  "type": "string"
+}

addedOutput schema / properties / jobs

Added value: +{
+  "description": "Several jobs at once (get_job with jobIds, or a plan's steps): each one's jobId, status and results",
+  "items": {
+    "type": "object"
+  },
+  "type": "array"
+}

Changed3 schema fields changedOct 7, 2026

changedInput schema / properties / format / default
```
Previous value: -"16:9"New value: +"original"
```

changedInput schema / properties / format / description

Previous value: -"Label for the clip's shape; the video follows the start photo's own shape."New value: +"Video shape. original (default) keeps the start photo's own shape; 16:9, 9:16 or 1:1 crop the photos, centred, to that shape before they are animated."

changedInput schema / properties / format / enum

Previous value: -[
-  "16:9",
-  "9:16",
-  "1:1"
-]New value: +[
+  "original",
+  "16:9",
+  "9:16",
+  "1:1"
+]

Changed1 schema field changedOct 6, 2026

addedOutput schema / properties / quote

Added value: +{
+  "description": "Present when status is \"awaiting_confirmation\": nothing ran and nothing was charged yet — the price and settings the user is asked to confirm",
+  "type": "object"
+}

Changed1 schema field changedOct 2, 2026

addedOutput schema / properties / resultPaths

Added value: +{
+  "description": "Storage path of each result — pass one as r2Path (or beforeR2Path, a photos[] item) to run another tool on this result",
+  "items": {
+    "type": "string"
+  },
+  "type": "array"
+}

Changed1 schema field changedSep 23, 2026

changedInput schema / properties / r2Path / description

Previous value: -"R2 object path from an upload ticket (the create_upload_ticket tool, or POST /api/v1/uploads over REST) — the alternative to imageUrl when the photo is a local file."New value: +"Storage path of a photo already in the user's Pixly library (from list_library, or returned by an upload ticket) — the alternative to imageUrl."

Changed1 schema field changedSep 21, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "completedAt": {
+      "type": "string"
+    },
+    "createdAt": {
+      "type": "string"
+    },
+    "creditsCharged": {
+      "type": [
+        "number",
+        "null"
+      ]
+    },
+    "error": {
+      "type": "string"
+    },
+    "jobId": {
+      "description": "Pass to get_job to poll",
+      "type": "string"
+    },
+    "note": {
+      "type": "string"
+    },
+    "resultUrls": {
+      "description": "Present when completed; valid 7 days",
+      "items": {
+        "type": "string"
+      },
+      "type": "array"
+    },
+    "status": {
+      "description": "pending | processing | completed | failed — anything not completed/failed is still running",
+      "type": "string"
+    },
+    "type": {
+      "type": "string"
+    }
+  },
+  "required": [
+    "jobId",
+    "status"
+  ],
+  "type": "object"
+}

Changed1 schema field changedSep 20, 2026

changedInput schema / properties / r2Path / description

Previous value: -"R2 object path from an upload ticket (POST /api/v1/uploads) — the alternative to imageUrl when the photo is a local file."New value: +"R2 object path from an upload ticket (the create_upload_ticket tool, or POST /api/v1/uploads over REST) — the alternative to imageUrl when the photo is a local file."

AddedSep 19, 2026

TDQS

A3.8/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare it's a non-idempotent, open-world, non-destructive write. The description adds genuinely new context beyond annotations: it consumes credits from the user's Pixly balance, and explains the end-frame landing behavior. It omits any async/job semantics (the get_job sibling suggests polling), which would have earned a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the core action ('Turn a start photo ... into a video') and stays reasonably tight. The kitchen orbit example is illustrative but slightly expendable; overall efficient with no wasted preamble.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need no explanation, and all 11 params are fully documented in the schema. The description supplies the remaining gaps an agent needs: credit cost, the optional end-frame behavior, and the cameraMove-vs-prompt choice.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all 11 parameters including enum trade-offs (model time/sound differences, cameraMove, format). The description only paraphrases ('choose the model, length and sound') without adding format or syntax detail, so baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource: turn a start photo (and optionally an end photo) into a video. The end-frame mechanism description (camera lands exactly on the second image) is distinctive and clarifying. However, it never names the related siblings (cinematic_motion, flythrough_video, before_after_reel) to differentiate scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives implied usage: with an end photo you get a landing shot, otherwise pick a cameraMove or prompt. But there is no explicit 'when to use this vs cinematic_motion / flythrough_video' guidance, leaving the agent to infer routing among several video-generation siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Pixly tools Inspect

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

Need Help?