gemini-media-mcp

Overview Schema Source Related Servers Discussions Admin

Extend video

extend_video

Continue a completed video clip from its end by generating additional coherent footage from a prompt. Supports Gemini omni and Veo models with asynchronous job tracking.

Instructions

Continue a completed clip from its end: omni adds up to 10 s (40 s total, keeping characters and audio coherent); Veo fast/standard add about 7 s (720p, up to 148 s, within 2 days). Asynchronous like generate_video.

Input Schema

TableJSON Schema

Name	Required	Description
`seed`	No	Vertex AI only.
`jobId`	Yes	Job handle of a completed generate_video or extend_video call (operation names from older versions also work).
`prompt`	Yes	What happens next. Veo adds about 7 seconds (720p) from the last second; omni adds up to 10 seconds using the last 10 seconds as context.
`outputName`	No
`waitSeconds`	No	Block up to this many seconds for the result (default 0).
`negativePrompt`	No
`approvedCostUsd`	No	Only needed above the confirmation threshold.

Output Schema

TableJSON Schema

Name	Required	Description
`cost`	Yes
`next`	No	Suggested next step
`error`	No
`files`	No
`jobId`	Yes	Opaque handle; pass it to get_video, extend_video or edit_video
`model`	Yes
`state`	Yes	working, completed, failed or filtered
`warnings`	No
`elapsedSeconds`	Yes
`remoteExpiresAt`	No	When Google deletes the server-side copy; extend before this time

Schema Changelog

Changes observed during successful MCP inspections.

Changed21 schema fields changedv1.1.0Oct 14, 2026

addedInput schema / properties / approvedCostUsd

Added value: +{
+  "description": "Only needed above the confirmation threshold.",
+  "type": "number"
+}

addedInput schema / properties / jobId

Added value: +{
+  "description": "Job handle of a completed generate_video or extend_video call (operation names from older versions also work).",
+  "type": "string"
+}

removedInput schema / properties / model

Removed value: -{
-  "description": "Model tier (must match original). Standard and Fast only, Lite does not support extension",
-  "type": "string"
-}

addedInput schema / properties / negativePrompt
```
Added value: +{
+  "type": "string"
+}
```

removedInput schema / properties / operationId

Removed value: -{
-  "description": "Operation ID of the previous video generation",
-  "type": "string"
-}

addedInput schema / properties / outputName
```
Added value: +{
+  "type": "string"
+}
```

changedInput schema / properties / prompt / description

Previous value: -"Text description for the continuation"New value: +"What happens next. Veo adds about 7 seconds (720p) from the last second; omni adds up to 10 seconds using the last 10 seconds as context."

addedInput schema / properties / seed

Added value: +{
+  "description": "Vertex AI only.",
+  "type": [
+    "null",
+    "integer"
+  ]
+}

addedInput schema / properties / waitSeconds

Added value: +{
+  "description": "Block up to this many seconds for the result (default 0).",
+  "type": "integer"
+}

changedInput schema / required

Previous value: -[
-  "prompt",
-  "operationId"
-]New value: +[
+  "jobId",
+  "prompt"
+]

addedOutput schema / properties / cost

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "basis": {
+      "description": "How usd was derived: usage_metadata, unit_params, token_estimate or unpriced",
+      "type": "string"
+    },
+    "breakdown": {
+      "type": "string"
+    },
+    "estimatedUsd": {
+      "description": "Estimate computed before the call from the price table",
+      "type": "number"
+    },
+    "pending": {
+      "description": "True while a video job is still running (cost is reserved, not final)",
+      "type": "boolean"
+    },
+    "priceAsOf": {
+      "type": "string"
+    },
+    "usd": {
+      "description": "Best-known cost in USD; reconciled from token usage when the API reports it",
+      "type": "number"
+    }
+  },
+  "required": [
+    "estimatedUsd",
+    "usd",
+    "basis"
+  ],
+  "type": "object"
+}

addedOutput schema / properties / elapsedSeconds
```
Added value: +{
+  "type": "integer"
+}
```
addedOutput schema / properties / error
```
Added value: +{
+  "type": "string"
+}
```

addedOutput schema / properties / files

Added value: +{
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "bytes": {
+        "type": "integer"
+      },
+      "durationSeconds": {
+        "type": "number"
+      },
+      "height": {
+        "type": "integer"
+      },
+      "mimeType": {
+        "type": "string"
+      },
+      "name": {
+        "type": "string"
+      },
+      "path": {
+        "description": "Absolute path of the saved file on the server's filesystem",
+        "type": "string"
+      },
+      "uri": {
+        "description": "MCP resource URI; pass it back as an input to other tools or read it with resources/read",
+        "type": "string"
+      },
+      "width": {
+        "type": "integer"
+      }
+    },
+    "required": [
+      "path",
+      "uri",
+      "name",
+      "mimeType",
+      "bytes"
+    ],
+    "type": "object"
+  },
+  "type": [
+    "null",
+    "array"
+  ]
+}

addedOutput schema / properties / jobId

Added value: +{
+  "description": "Opaque handle; pass it to get_video, extend_video or edit_video",
+  "type": "string"
+}

addedOutput schema / properties / next

Added value: +{
+  "description": "Suggested next step",
+  "type": "string"
+}

removedOutput schema / properties / operationId
```
Removed value: -{
-  "type": "string"
-}
```

addedOutput schema / properties / remoteExpiresAt

Added value: +{
+  "description": "When Google deletes the server-side copy; extend before this time",
+  "type": [
+    "null",
+    "string"
+  ]
+}

addedOutput schema / properties / state

Added value: +{
+  "description": "working, completed, failed or filtered",
+  "type": "string"
+}

addedOutput schema / properties / warnings

Added value: +{
+  "items": {
+    "type": "string"
+  },
+  "type": [
+    "null",
+    "array"
+  ]
+}

changedOutput schema / required

Previous value: -[
-  "operationId",
-  "model"
-]New value: +[
+  "jobId",
+  "state",
+  "model",
+  "elapsedSeconds",
+  "cost"
+]

First observedApr 15, 2026

TDQS

A3.7/5.0

Behavior4/5

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

Annotations already declare the mutation profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false, openWorldHint=true). The description adds real value beyond them: per-model duration caps, 720p/coherence properties, and that the call is asynchronous like generate_video. It omits cost/threshold behavior, which limits it below 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-loaded with the core action, then dense but earned model-specific detail. The second sentence on async behavior is a compact, useful pointer to generate_video. No filler, though the parenthetical packing is heavy for a single sentence.

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

Completeness4/5

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 not be explained. Given the multi-model complexity, the description covers duration, coherence, resolution, and async behavior well, though it omits cost-confirmation context that the approvedCostUsd parameter hints at.

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 71%, so the schema documents most parameters (jobId, prompt, seed, waitSeconds, approvedCostUsd). The description's model context (10 s omni vs 7 s Veo, last-second vs last-10-seconds context) loosely informs how prompt is interpreted, but it does not clarify the two undocumented parameters (outputName, negativePrompt). Baseline 3 is appropriate.

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?

The description names a specific verb and resource ("Continue a completed clip from its end") and enumerates model-specific extension limits, so the purpose is immediately clear. However, it never explicitly distinguishes itself from the sibling edit_video, which is the operation an agent is most likely to confuse it with.

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?

Usage is implied by "completed clip," meaning the input must already exist, and the async note references generate_video as a parallel. But there is no explicit when-to-use vs edit_video/stitch guidance or any when-not condition, leaving routing to inference.

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

Deploy Server