Fotor

Submit Multimodal Video Task

submit_multimodal_video_task

Destructive

Starts one Fotor video generation task using image, video or audio references. May consume existing Fotor credits. Returns a task ID without waiting for completion; use get_task to check its status once. This tool does not poll for completion. Repeating the request may create another task and consume additional credits. Do not automatically retry when the submission outcome is uncertain. This tool does not purchase credits or initiate a checkout flow.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "model_id": "<model_id>",
      "prompt": "<prompt>"
    },
    "name": "submit_multimodal_video_task"
  }
}

Input Schema

Name	Required	Description	Default
`prompt`	Yes	Describe the video. <<<image_n>>>, <<<video_n>>> and <<<audio_n>>> reference each URL list; numbering starts at 1.
`duration`	No	Video duration in seconds from list_models; 0 uses default_duration.
`model_id`	Yes	Model ID from list_models; inspect its supported mode and parameters first.
`audio_urls`	No	Ordered HTTPS audio references; check reference_types and max_audio_references in list_models. When audio_requires_visual_reference is true, include an image or video. Encode literal URL commas as %2C.
`image_urls`	No	Ordered HTTPS image references; check reference_types in list_models. Supply at least one image, video or audio reference.
`resolution`	No	Native output resolution from list_models; auto uses the model default.	auto
`video_urls`	No	Ordered HTTPS video references; check reference_types in list_models. Encode literal URL commas as %2C.
`aspect_ratio`	No	Output aspect ratio from list_models. With images and no video, supply an explicit ratio; otherwise auto uses the model default.	auto
`audio_enable`	No	Generate native video audio; requires native_audio support. Independent of reference audio.

Output Schema

Name	Required	Description	Default
`status`	No	Submission accepted; generation is not yet confirmed complete.	submitted
`task_id`	Yes	Fotor task ID for get_task.
`model_id`	Yes	Model ID used for this task.
`media_type`	Yes	Generated media category.
`credits_increment`	No	Reported task credit cost; not an additional charge on each query. Null if unavailable.

Schema Changelog

Changes observed during successful MCP inspections.

Changed14 schema fields changedOct 29, 2026

addedInput schema / properties / aspect_ratio / description

Added value: +"Output aspect ratio from list_models. With images and no video, supply an explicit ratio; otherwise auto uses the model default."

addedInput schema / properties / audio_enable / description

Added value: +"Generate native video audio; requires native_audio support. Independent of reference audio."

addedInput schema / properties / audio_urls / description

Added value: +"Ordered HTTPS audio references; check reference_types and max_audio_references in list_models. When audio_requires_visual_reference is true, include an image or video. Encode literal URL commas as %2C."

addedInput schema / properties / duration / description

Added value: +"Video duration in seconds from list_models; 0 uses default_duration."

addedInput schema / properties / image_urls / description

Added value: +"Ordered HTTPS image references; check reference_types in list_models. Supply at least one image, video or audio reference."

addedInput schema / properties / model_id / description

Added value: +"Model ID from list_models; inspect its supported mode and parameters first."

addedInput schema / properties / prompt / description

Added value: +"Describe the video. <<<image_n>>>, <<<video_n>>> and <<<audio_n>>> reference each URL list; numbering starts at 1."

addedInput schema / properties / resolution / description

Added value: +"Native output resolution from list_models; auto uses the model default."

addedInput schema / properties / video_urls / description

Added value: +"Ordered HTTPS video references; check reference_types in list_models. Encode literal URL commas as %2C."

addedOutput schema / properties / credits_increment / description

Added value: +"Reported task credit cost; not an additional charge on each query. Null if unavailable."

addedOutput schema / properties / media_type / description
```
Added value: +"Generated media category."
```
addedOutput schema / properties / model_id / description
```
Added value: +"Model ID used for this task."
```

addedOutput schema / properties / status / description

Added value: +"Submission accepted; generation is not yet confirmed complete."

addedOutput schema / properties / task_id / description
```
Added value: +"Fotor task ID for get_task."
```

First observedOct 28, 2026

TDQS

A4.2/5.0

Behavior4/5

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

Adds substantial context beyond annotations: credit consumption, asynchronous return of a task ID without waiting, and that repeated calls create new tasks and burn more credits. This complements the non-idempotent and destructive hints rather than merely restating them; only the exact side effects of a failed/partial submission remain unstated.

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

Conciseness3/5

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

Front-loaded and mostly earning its place, but the second and third sentences repeat the same idea ('Returns a task ID without waiting for completion' / 'does not poll for completion'), and the closing credits/checkout sentence overlaps with the earlier credit warning.

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?

Given rich annotations, a full output schema, and 100% parameter coverage, the description supplies exactly the missing operational context: cost implications, async lifecycle, retry policy, and the get_task handoff. Nothing an agent needs before calling is absent.

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

Parameters4/5

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

Schema description coverage is 100%, so per-parameter meaning is already carried by the schema. The description adds a coarse cue ('using image, video or audio references') that frames the reference-URL families, but adds no syntax or constraint detail beyond the schema.

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 and resource ('Starts one Fotor video generation task') plus the discriminating qualifier 'using image, video or audio references', which separates it from the text-to-video and first-frame siblings. It stops short of naming those siblings explicitly, so it is clear but not maximally differentiated.

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

Usage Guidelines5/5

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

Explicitly scopes when/when-not: do not poll, use get_task once instead, do not auto-retry on uncertain outcomes, and this tool does not purchase credits or start checkout. Alternatives are named and failure modes are called out, leaving little to inference.

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

All Fotor 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?