Skip to main content
Glama
Sign In
Firefly MCP Server

Firefly MCP Server

by thenavidm
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Generate images with Image5

generate_image5

Generate images from text prompts with Adobe Firefly's Image 5, supporting reference-based edits and asynchronous job returns.

Instructions

Generate images with Image5. Image 5 supports natural-language edits through referenceBlobs. Consumes Firefly Services credits. Returns Adobe output URLs. Set wait=false to return an async job.

Input Schema

NameRequiredDescriptionDefault
nNoCompatibility alias for numVariations. Do not supply both.
waitNoWait for completion, default true. Set false to return the job immediately.
seedsNoThe seed value to vary the image generation. Only one seed per variation is allowed. If specified alongside with numVariations, the number of seeds must be equal to numVariations.
promptYesThe prompt used to generate the image. The longer the prompt, the better.
confirmNoSet true only when the user asked for exactly this action.
modelIdNoThe specific model to use for image generation. Available options: 'firefly_image' for Firefly Image model.
downloadNoDownload completed media to FIREFLY_OUTPUT_DIR, default false. Requires wait=true.
aspectRatioNoThe aspect ratio of the requested generations. This controls the size of the generated image. When referenceBlobs is included in the request, this property should be omitted or set to auto.
numVariationsNoThe number of image variations to generate. Greater than 1 is not supported. Only one image per variation is allowed. For multiple variations, send separate requests.
referenceBlobsNoList of reference blobs that will be used as additional input for the generation process. Only one reference image is supported. When this array is not empty, aspectRatio must be omitted or set to auto. [Pre-signed URLs can be used from supported domains](https://developer.adobe.com/firefly-services/docs/firefly-api/getting-started/usage-notes/#image-api-usage).
resolutionLevelNoThe resolution level.2.4MP
modelSpecificPayloadNoAdditional model-specific parameters for controlling the generation process.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field 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."
  2. First observedv2.0.0

TDQS

B3.4/5.0
Behavior4/5

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

Beyond the annotations (readOnly=false, destructive=false, openWorld=true, idempotent=false), the description discloses three genuinely useful traits: it consumes Firefly Services credits, it returns Adobe output URLs, and wait=false produces an async job. Cost consumption and async semantics are exactly the kind of context annotations cannot convey, though rate limits or failure behavior are not covered.

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?

Four short sentences with no filler, and the core purpose is front-loaded. It is efficient, though the trailing sentences read as a compressed feature list rather than a prioritized statement.

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

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 12-parameter tool with nested objects and no output schema, the description usefully notes that Adobe output URLs are returned and that async is available, partly compensating for the missing output schema. However, it is silent on most parameters (seeds, n, download, confirm, resolutionLevel, modelSpecificPayload) and on how the async job is later retrieved, leaving real gaps for a tool of this complexity.

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 12 parameters including referenceBlobs, wait, and prompt. The description only restates the referenceBlobs editing capability and the wait flag, adding no syntax, constraints, or defaults beyond the schema. 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 images with Image5') and adds a distinguishing capability note ('Image 5 supports natural-language edits through referenceBlobs'). It does not, however, differentiate itself from the sibling generate_image or generate_similar, so an agent must guess which generation tool to pick.

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

Usage Guidelines2/5

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

The description never states when to choose this tool over the ten sibling generation tools (generate_image, generate_similar, generative_fill, etc.). 'Set wait=false to return an async job' is an invocation detail, not a selection criterion, and no prerequisites or exclusions are given.

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