Skip to main content
Glama
Sign In
Firefly MCP Server

Firefly MCP Server

by thenavidm
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Generate video

generate_video

Generate a video from a text prompt, optionally using keyframe images to guide the output. Returns Adobe output URLs.

Instructions

Generate video. Consumes Firefly Services credits. Returns Adobe output URLs. Set wait=false to return an async job.

Input Schema

NameRequiredDescriptionDefault
waitNoWait for completion, default true. Set false to return the job immediately.
imageNoThe details of the image used as a keyframe for the generated video. Provided images are used as a first frame or final frame to guide the video generation.
seedsNoThe seed reference value. Currently only 1 seed is supported.
sizesNoThe dimensions of the generated video. Consult the [supported aspect ratios in the usage notes](https://developer.adobe.com/firefly-services/docs/firefly-api/getting-started/usage-notes/#supported-aspect-ratios) for allowed values.
promptNoThe prompt used to generate the video. The longer the prompt, the better.
confirmNoSet true only when the user asked for exactly this action.
downloadNoDownload completed media to FIREFLY_OUTPUT_DIR, default false. Requires wait=true.
bitRateFactorNoThe constant rate factor for encoding video. 0 indicates a lossless generation, with the highest quality and largest file size. 63 indicates the worst quality generation with the smallest file size. The suggested value range is 17-23.
videoSettingsNoThe camera and shot control settings.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv3.0.0
    • changedInput schema / properties / confirm / description
      Previous value: -"Must be true to spend Firefly Services credits for the operation the user requested."New value: +"Set true only when the user asked for exactly this action."
    • changedInput schema / properties / image / properties / conditions / items / properties / source / properties / uploadId / format
      Previous value: -"uuid4"New value: +"uuid"
  2. First observedv2.0.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare the mutation/open-world profile (readOnlyHint=false, openWorldHint=true, idempotentHint=false). The description adds genuinely useful behavior the annotations don't carry: the credit cost, that output is returned as Adobe URLs, and the async return behavior. It does not describe failure modes, credit quantities, or how the returned URLs expire.

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?

Four short sentences, zero filler, front-loaded with the core action and followed by cost, return format, and the key async flag. Every sentence earns its place.

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?

With no output schema, the description usefully discloses that Adobe output URLs are returned and that the call can be async. Given nine parameters, nested objects, and a credit-consuming mutation, it is close to complete, though it omits credit cost magnitude and any precondition on the confirm flag.

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 nine parameters in detail (including wait, download, sizes, and videoSettings). The description only restates the wait=false semantic that is already in the schema, adding no meaning beyond it; 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?

States a specific verb and resource ('Generate video'), which distinguishes it from the image-generation siblings in the list. However, it does not name or contrast with the closest alternatives (e.g., generate_similar, generate_image), so the differentiation comes only from the resource noun.

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?

The description gives one concrete usage instruction — 'Set wait=false to return an async job' — which tells the agent how to switch between synchronous and async modes. It offers no guidance on when to prefer this tool over the sibling generation tools or when video generation is appropriate.

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

Deploy Server

Other Tools