StockCake

Create Video

create_video

Generate a short video from a prompt and/or a start image with one of StockCake's video models (list_models). Priced per second of output; charges credits. Video usually takes longer than the 20 s inline wait: expect a pending result and poll get_job. Re-sending identical arguments within 2 hours returns the same job (reused: true) instead of charging again. Requires a free StockCake account (the host will prompt to sign in).

Input Schema

Name	Required	Description
`tier`	No	Tier key from list_models (e.g. 720p, 1080p, 768p)
`model`	No	Video model id from list_models (default: H3 Max)
`prompt`	No	Required unless start_image is given
`context`	Yes	In one sentence, what is the user trying to make or find?
`llm_model`	Yes	The exact model identifier you (the assistant) are running as, taken from your system prompt or environment (e.g. "claude-opus-4-8", "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" — never guess.
`start_image`	No	Animate from this image (stock id or your edited image id)
`aspect_ratio`	No	Text-to-video only; a start image sets the ratio
`conversation_id`	No	Pass the exact conversation_id from the server's previous response, unchanged. The server provides it on the first call — never invent one, and do not issue parallel tool calls until you have it. Keep passing the same conversation_id for the rest of the conversation, including after later user messages or on a different task; do not reset it when the user starts a new request.
`negative_prompt`	No
`duration_seconds`	No	Clip length; must be one of the model's durations

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 2, 2026

changedOutput schema / anyOf

Previous value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "credits_charged": {
-        "type": "number"
-      },
-      "job_id": {
-        "type": "string"
-      },
-      "status": {
-        "const": "completed",
-        "type": "string"
-      },
-      "video": {
-        "additionalProperties": false,
-        "properties": {
-          "duration_seconds": {
-            "type": [
-              "number",
-              "null"
-            ]
-          },
-          "url": {
-            "type": "string"
-          }
-        },
-        "required": [
-          "url",
-          "duration_seconds"
-        ],
-        "type": "object"
-      }
-    },
-    "required": [
-      "job_id",
-      "status",
-      "video",
-      "credits_charged"
-    ],
-    "type": "object"
-  },
-  {
-    "additionalProperties": false,
-    "properties": {
-      "credits_charged": {
-        "type": "number"
-      },
-      "job_id": {
-        "type": "string"
-      },
-      "message": {
-        "type": "string"
-      },
-      "status": {
-        "const": "pending",
-        "type": "string"
-      }
-    },
-    "required": [
-      "job_id",
-      "status",
-      "credits_charged",
-      "message"
-    ],
-    "type": "object"
-  },
-  {
-    "additionalProperties": {},
-    "properties": {
-      "code": {
-        "type": "string"
-      },
-      "message": {
-        "type": "string"
-      }
-    },
-    "required": [
-      "code",
-      "message"
-    ],
-    "type": "object"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "credits_charged": {
+        "type": "number"
+      },
+      "job_id": {
+        "type": "string"
+      },
+      "message": {
+        "type": "string"
+      },
+      "reused": {
+        "const": true,
+        "type": "boolean"
+      },
+      "status": {
+        "const": "completed",
+        "type": "string"
+      },
+      "video": {
+        "additionalProperties": false,
+        "properties": {
+          "duration_seconds": {
+            "type": [
+              "number",
+              "null"
+            ]
+          },
+          "url": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "url",
+          "duration_seconds"
+        ],
+        "type": "object"
+      }
+    },
+    "required": [
+      "job_id",
+      "status",
+      "video",
+      "credits_charged"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": false,
+    "properties": {
+      "credits_charged": {
+        "type": "number"
+      },
+      "job_id": {
+        "type": "string"
+      },
+      "message": {
+        "type": "string"
+      },
+      "reused": {
+        "const": true,
+        "type": "boolean"
+      },
+      "status": {
+        "const": "pending",
+        "type": "string"
+      }
+    },
+    "required": [
+      "job_id",
+      "status",
+      "credits_charged",
+      "message"
+    ],
+    "type": "object"
+  },
+  {
+    "additionalProperties": {},
+    "properties": {
+      "code": {
+        "type": "string"
+      },
+      "message": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "code",
+      "message"
+    ],
+    "type": "object"
+  }
+]

Changed1 schema field changedOct 24, 2026

changedInput schema / properties / tier / description

Previous value: -"Tier key from list_models (e.g. 720p, 1080p, 720p-audio)"New value: +"Tier key from list_models (e.g. 720p, 1080p, 768p)"

Changed1 schema field changedOct 22, 2026

changedInput schema / properties / model / description

Previous value: -"Video model id from list_models (default: MiniMax H3)"New value: +"Video model id from list_models (default: H3 Max)"

Changed1 schema field changedOct 2, 2026

changedInput schema / properties / model / description

Previous value: -"Video model id from list_models (default: Veo 3.1 Fast)"New value: +"Video model id from list_models (default: MiniMax H3)"

First observedSep 28, 2026

TDQS

A4.5/5.0

Behavior5/5

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

Goes well beyond the annotations: per-second credit pricing, the fact that generation exceeds the 20 s inline wait and will return pending, and a 2-hour dedup window that returns the same job with reused: true. The idempotentHint=false annotation is qualified rather than contradicted – the dedup is time-bounded, so outside 2 hours a new job is created.

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

Conciseness5/5

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

Five dense sentences, front-loaded with what the tool does before cost, async behavior, dedup, and auth. No filler and no repetition of the schema.

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; the description covers the parts that matter for a costly, long-running, open-world generation call: billing, async polling, idempotency, and auth. An agent has everything needed to invoke it correctly.

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 coverage is 90%, so the schema already documents nearly every parameter including tier, model, aspect_ratio's text-to-video restriction, and duration_seconds. The description adds only that output is priced per second (implying cost scales with duration_seconds), which is marginal value over the schema.

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

Purpose5/5

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

States a specific verb and resource ('Generate a short video from a prompt and/or a start image') plus the model source (StockCake's video models via list_models). An agent can immediately distinguish this from the sibling generate_image tool without opening the schema.

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

Usage Guidelines4/5

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

Routes the agent to two siblings with explicit conditions: list_models for model/tier ids and get_job for polling once the result is pending. It also declares the auth prerequisite (free StockCake account, host sign-in prompt). It never explicitly says when to prefer generate_image over video, which keeps it short of a 5.

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

All StockCake 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?