convez.ai
MCP ServerIntegração & APIsIntermediário
Focus-GTS

Firefly Services MCP Server

Focus-GTS/firefly-services-mcp

Integre Adobe Firefly, Photoshop e Lightroom APIs ao seu fluxo de IA com MCP

Ver no GitHub
InicialPluginScore · de 0 a 100

Servidor MCP que expõe as APIs do Adobe Firefly, Photoshop e Lightroom como ferramentas nativas do Claude Code e Cursor. Permite gerar, expandir e manipular imagens, além de processar arquivos PSD e fazer batch de imagens diretamente de sessões de IA, sem deixar o editor.

Instalação

$npx convez-ai Focus-GTS/firefly-services-mcp

1 comando no terminal: detecta o formato do repositório (marketplace ou plugin avulso) e instala via Claude Code. Requer Node 18+ e o Claude Code instalado.

Métricas

Estrelas
1
Forks
0
Acompanhando
0
Saúde
75%
Último commit
há 3 meses
Versão
v0.2.0
Issues abertas
4
Contribuidores
1

Casos de uso

  • Gerar imagens a partir de prompts em sessões de Claude Code
  • Expandir e preencher áreas de imagens existentes automaticamente
  • Processar templates PSD e executar operações Photoshop via IA
  • Fazer batch processing de imagens através da API Lightroom
  • Compor objetos em cenas geradas de forma programática

Veredito

MCP server maduro e bem validado (v0.1.2, 18 ferramentas, 168+ testes) que bridgeeia as APIs oficiais do Adobe sem reinventar a roda. Firefly está 100% validado em produção; Photoshop e Lightroom prontos mas aguardando validação com S3/Azure/GCS. Ideal para fluxos de design e processamento de imagem dentro de ambientes MCP.

README

A tradução para o português deste README ainda está na fila.

Firefly Services MCP Server

License: Apache 2.0 CI Status Tools

Model Context Protocol server for Adobe Firefly Services — exposes Firefly, Photoshop API, and Lightroom API endpoints as MCP tools that Claude Code, Cursor, and other MCP-compatible AI clients can call directly.

Built by FocusGTS. Not affiliated with or endorsed by Adobe Inc. or Anthropic, PBC.


See it in action

These are real images generated through this MCP server, live against the Adobe Firefly Services API — not mockups or stock art.

firefly_generate_imagefirefly_expand_imagefirefly_generate_object_composite
Text-to-image generated by firefly_generate_imageCanvas extended by firefly_expand_imageObject placed into a scene by firefly_generate_object_composite
Text-to-image with Firefly V3Canvas extended 1024 → 1408 pxProduct composited into a generated scene

Generated in seconds from a Claude Code session, each by a single MCP tool call.


Status

v0.1.2 — 18 tools, fully implemented. The MCP server boots over stdio, implements the MCP protocol, and registers all 18 tools across Firefly (8), Photoshop API (6), and Lightroom API (4). Test coverage: 142 unit tests + 26 mocked integration tests passing.

Live validation status (against the Adobe Firefly Services sandbox):

SurfaceToolsStatus
Firefly8✅ Live-validated — all 8 exercised end-to-end against the real API (auth, generate, generate-similar, expand, fill, object-composite, upload, video)
Photoshop API6SDK- + mock-validated. Live validation pending — these endpoints write results to a caller-supplied pre-signed output_url (your own S3/Azure/GCS bucket), so live runs require storage configuration
Lightroom API4SDK- + mock-validated. Live validation pending for the same reason

The Photoshop and Lightroom APIs, by Adobe's design, do not host outputs — the caller provides a writable destination. Live validation of those 10 tools is gated on bucket configuration, not on the server. See docs/PRD.md for the release plan.


What this is

For developers using Claude Code (or any MCP-compatible client) who want to call Adobe Firefly Services directly from their AI workflow — generate images from prompts, expand and fill existing images, run Photoshop API operations on PSD templates, batch-process images through Lightroom — without leaving the editor.

This is not an Adobe SDK and not a replacement for one. It is a thin MCP adapter on top of Adobe's official SDKs (@adobe/firefly-apis, @adobe/photoshop-apis, @adobe/lightroom-apis, @adobe/firefly-services-common-apis). The SDKs do the real work; this server translates between MCP tool calls and SDK method calls. See ADR-001 for the rationale.


Install

Option 1 — From source (for development)

git clone https://github.com/Focus-GTS/firefly-services-mcp.git
cd firefly-services-mcp
npm install   # builds dist/ automatically via the prepare script

# Add to Claude Code
claude mcp add firefly-services -- node "$(pwd)/dist/server.js"

For the development loop without a build step:

claude mcp add firefly-services -- npx tsx "$(pwd)/src/server.ts"

Option 2 — From npm (recommended)

The package is published to npm, so install is one line:

claude mcp add firefly-services -- npx @focusgts/firefly-services-mcp

Published at npmjs.com/package/@focusgts/firefly-services-mcp.

Required environment variables

export FIREFLY_SERVICES_CLIENT_ID=<your client id from Adobe Developer Console>
export FIREFLY_SERVICES_CLIENT_SECRET=<your client secret>

The credentials must be an OAuth Server-to-Server credential pair issued via the Adobe Developer Console with Firefly Services API access provisioned on the workspace. See examples/install-claude-code.md for the full credential-acquisition walkthrough or the firefly-services-bootstrap skill for the FDE-grade detail.


Tools (v0.1 surface — 18 tools)

Firefly (8)

  • firefly_generate_image
  • firefly_generate_similar
  • firefly_expand_image
  • firefly_fill_image
  • firefly_generate_object_composite
  • firefly_generate_video
  • firefly_upload_image
  • firefly_check_auth

Photoshop API (6)

  • photoshop_smart_object_replace
  • photoshop_document_manifest
  • photoshop_apply_actions
  • photoshop_edit_text
  • photoshop_apply_edits
  • photoshop_remove_background

Lightroom API (4)

  • lightroom_apply_preset
  • lightroom_auto_tone
  • lightroom_auto_straighten
  • lightroom_apply_edits

Naming follows ADR-005: <product>_<action>_<object> in snake_case.


Architecture

Claude Code / Cursor
    ↓ MCP protocol (stdio)
@focusgts/firefly-services-mcp
    ↓
@adobe/firefly-apis | @adobe/photoshop-apis | @adobe/lightroom-apis
    ↓ HTTPS
firefly-api.adobe.io | image.adobe.io | ims-na1.adobelogin.com

Key architectural decisions:

ADRDecision
001Wrap Adobe SDKs; do not reimplement the API surface
002Node.js + TypeScript + stdio transport
003Single-credential-per-server-instance for v0.1
004Storage references: triple-mode input (uploadId | url | path), dual-mode output (URL only or inlined bytes)
005Tool naming: <product>_<action>_<object> snake_case

Full PRD: docs/PRD.md.


Development

git clone https://github.com/Focus-GTS/firefly-services-mcp.git
cd firefly-services-mcp
npm install

# Type-check
npm run lint

# Run the server in dev mode (uses tsx, no build step)
FIREFLY_SERVICES_CLIENT_ID=<id> FIREFLY_SERVICES_CLIENT_SECRET=<secret> npm run dev

# Unit tests (mocked SDKs)
npm test

# Mocked integration tests (HTTP-layer mocks via msw)
npm run test:integration:mocked

# Live integration tests (real Adobe API — needs valid credentials)
npm run test:integration:live

# Build for production
npm run build

Smoke-test the protocol

The fastest way to verify the server is working end-to-end:

INIT='{"jsonrpc":"2.0","id":1,"method":"initialize","params":{"protocolVersion":"2024-11-05","capabilities":{},"clientInfo":{"name":"smoke-test","version":"0"}}}'
LIST='{"jsonrpc":"2.0","id":2,"method":"tools/list"}'

( printf '%s\n%s\n%s\n' "$INIT" '{"jsonrpc":"2.0","method":"notifications/initialized"}' "$LIST"; sleep 1 ) \
  | FIREFLY_SERVICES_CLIENT_ID=dummy FIREFLY_SERVICES_CLIENT_SECRET=dummy npm run dev

You should see two JSON-RPC responses on stdout — the second one lists all registered tools.


Trademarks and independence

This repository is independently developed and maintained by FocusGTS.

  • "Adobe", "Adobe Firefly", "Adobe Firefly Services", "Photoshop", "Lightroom", "InDesign", "Creative Cloud", "Adobe Express", "Adobe Sensei", "GenStudio", and "Adobe Stock" are trademarks or registered trademarks of Adobe Inc. in the United States and/or other countries.
  • "Claude", "Claude Code", and "Model Context Protocol" are trademarks or service marks of Anthropic, PBC.
  • These trademarks are used under nominative fair use solely to identify the products this MCP server interoperates with.
  • This repository is not sponsored, endorsed, affiliated with, or supported by Adobe Inc. or Anthropic, PBC.

See NOTICE for the full trademark, attribution, and no-warranty statement.


License

Apache License 2.0. See LICENSE and NOTICE.

Distributed on an "AS IS" basis, without warranties or conditions of any kind. Endpoint paths, parameter shapes, and rate limits may change as Adobe evolves its APIs; verify against current official Adobe documentation before relying on any specific behavior.

Copyright © 2026 FocusGTS.


Related projects

Ver o original no GitHub

Bom para

Relacionados