Skip to main content
Glama

create_video

Generate a short AI video with synced sound from a text prompt using Epic Video. Videos are 5, 15, 30, 60 or 120 seconds long; anything over 15 seconds is stitched from chained 5-second clips for consistency. Videos cost tokens per second: 1 token/sec at 480p, 2 tokens/sec at 720p (e.g. a 15-second 480p video costs 15 tokens). Free plans get 15 tokens/week and can make videos up to 15 seconds; 60/120 require the Creator plan ($19.99/mo, 480 tokens/month released 120/week). $4.99/mo = 120 tokens/month released 30/week; $9.99/mo = 240 tokens/month released 60/week. Paid users can also spend top-up tokens bought on the website. Paid plans can attach a locked character (get its id from list_characters) so the same character appears in the video. Image-to-video: pass image_url (a public image URL) and the video will start from that image as its first frame and animate it — the prompt then describes the motion. Returns a job id — poll get_job_status until the status is 'done' to get the video URL. Check get_my_usage first to see the user's tokens left this week/month and top-up balance.

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": {
      "prompt": "<prompt>"
    },
    "name": "create_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
promptYesWhat the video should show, e.g. 'a red sports car on a coastal highway at golden hour, waves crashing'. With image_url, describe the motion instead, e.g. 'the car pulls away and speeds down the coast, camera tracking'.
qualityNoRequested quality. The actual quality is set by the user's plan (free and $4.99 plans render 480p; the $9.99 and Creator plans use the user's 720p/480p switch). The returned job shows the real quality used.
image_urlNoOptional public URL of an image (JPEG, PNG or WebP, up to 10 MB) to animate: the video starts from this image as its first frame (image-to-video). The server fetches and validates the image; private/loopback addresses are rejected.
duration_sNoLength in seconds: 5, 15, 30, 60 or 120. Free plans: up to 15. 60/120 require the Creator plan ($19.99/mo). Cost is duration x rate: 1 token/sec at 480p, 2 tokens/sec at 720p.
character_idNoOptional id of a locked character from list_characters, so that character appears in the video. Paid plans only.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and mostly does: it discloses that the call is asynchronous (returns a job id, must be polled), that long videos are stitched from chained 5-second clips, that quality requested may differ from quality rendered, and that tokens are consumed per second. It stops short of stating that the token charge is incurred up front and whether a failed job refunds tokens, which matters for a paid mutation.

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?

Purpose is front-loaded and the workflow guidance is valuable, but the middle is bloated with tier pricing minutiae ('$4.99/mo = 120 tokens/month released 30/week; $9.99/mo = 240 tokens/month...') that an agent cannot act on. The critical async instruction ('poll get_job_status') is buried at the very end rather than surfaced near the top.

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?

For a five-parameter generation tool with no annotations and no output schema, this covers the full lifecycle: cost model, plan-based limits, character and image inputs, quality resolution, and post-call polling to retrieve the video URL. Nothing an agent needs in order to invoke it correctly is missing.

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 coverage is 100%, so the baseline is 3; the description earns a bump by coupling duration to real cost ('15-second 480p video costs 15 tokens') and tying character_id to its source tool (list_characters) and quality to the user's plan. The image_url/prompt interplay is largely restated from the schema, so it is reinforcement rather than new meaning.

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?

Opens with a specific verb+resource combination ('Generate a short AI video with synced sound from a text prompt') and names the underlying model. It is immediately distinguishable from siblings like get_job_status, list_my_videos, and get_my_usage, which are only mentioned as follow-on steps rather than as competing capabilities.

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 routes the agent: check get_my_usage first, get character ids from list_characters, and poll get_job_status until status is 'done'. It also states concrete eligibility gates (free plans capped at 15s; 60/120s require the Creator plan; character locking is paid-plan only), so the agent knows when this tool will fail before calling it.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.