Back to Discover

creative-claw-marketplace

connector

CreativeClawCo

On-brand creative studio for AI agents: images, video, audio, and 3D.

View on GitHub
0 starsSynced Aug 2, 2026

Install to Claude Code

/plugin marketplace add CreativeClawCo/creative-claw-marketplace

README

Creative Claw

Generate on-brand media, inside Claude.

Creative Claw is an MCP plugin that brings a full AI media studio into Claude Code and Claude Desktop. Generate on-brand images, videos, speech, and HTML-rendered branded graphics — all from natural language, all through one account. Save your brand once and every future visual stays on-brand automatically. No API keys. No platform switching. Just describe what you need.

creativeclaw.co | Join the Beta


What You Get

MCP Server (auto-connected)

One connection to Creative Claw's MCP server gives you 30+ tools for media generation, editing, layout rendering, branding, and asset management:

CategoryTools
Imagegenerate_image (generate + edit), compare_models, load_image
Videogenerate_video, check_job
Speechgenerate_speech
HTML → mediarender_html_image, render_template
Media editingremove_background, upscale_media, trim_video, scale_video, add_subtitles, extract_frames, merge_media
Modelslist_models, get_model_params
Assetssearch_assets, update_asset, delete_asset, upload_asset, import_media, get_upload_url, confirm_upload
Brand themesget_theme, list_themes, update_theme, delete_theme
Templatescreate_template, update_template, list_templates, render_template
Creditsget_credits_balance, get_credits_link

Access 1,000+ production-ready AI models — FLUX, Gemini, Veo, Sora, Kling, Seedance, Hailuo, HeyGen, Recraft, ElevenLabs, and more — through a single unified account with usage-based pricing.

Skill (Creative Workflows)

The consolidated creativeclaw skill teaches an agent how to use the tools effectively: onboarding, model selection, prompt engineering, media import, brand themes, image/video/speech generation, templates, editing, characters, films, and asset management. It routes internally to focused reference files instead of assuming separate slash-command skills are installed.


Supported Models

Image Generation

ModelIDHighlights
GPT Image 1.5fal-ai/gpt-image-1.5Production-quality, strong prompt adherence, fine detail
Gemini 3 Profal-ai/nano-banana-proComplex reasoning, semantic understanding, text in images
Gemini 3.1 Flashfal-ai/nano-banana-2Fast, high-fidelity, excellent text rendering, multilingual
FLUX.2 Profal-ai/flux-2-proZero-config professional quality, HEX color precision
Recraft V3fal-ai/recraft/v3/text-to-image#1 on benchmarks, design and illustration
FLUX Schnellfal-ai/flux/schnellFastest (~0.5s), cheapest, great for drafts

Image Editing

ModelIDHighlights
GPT Image 1.5fal-ai/gpt-image-1.5/editStrong prompt adherence, identity preservation
Gemini 3 Profal-ai/nano-banana-pro/editSemantic edit instructions, 14 reference images
FLUX Kontext Maxfal-ai/flux-pro/kontext/maxTypography, consistency, precise edits
Gemini 3.1 Flashfal-ai/nano-banana-2/editFast, no masking required

Video Generation

ModelIDAudioImage Input
Veo 3.1fal-ai/veo3.1Native dialogue + SFXYes (/image-to-video)
Veo 3.1 Fastfal-ai/veo3.1/fastNative dialogue + SFXYes (/fast/image-to-video)
Sora 2 Profal-ai/sora-2/text-to-video/proNative audioYes (/image-to-video/pro)
Kling v3 Profal-ai/kling-video/v3/pro/text-to-videoNative audio + lip-syncYes (/image-to-video)
Seedance 2.0fal-ai/bytedance/seedance-2.0/text-to-videoNative audioYes (/image-to-video)
Seedance 2.0 Fastfal-ai/bytedance/seedance-2.0/fast/text-to-videoNative audioYes (/image-to-video)
Hailuo-02 Profal-ai/minimax/hailuo-02/pro/text-to-videoYesYes (/image-to-video)
Hailuo 2.3 Fastfal-ai/minimax/hailuo-2.3-fast/standard/image-to-videoNoYes (I2V only)

Talking Avatars

ModelIDHighlights
HeyGen Avatar 4fal-ai/heygen/avatar4/image-to-videoPhoto → talking avatar with lip-sync, 400+ poses, 100+ voices
HeyGen Video Agentfal-ai/heygen/v2/video-agentBudget talking avatar from text (~$2/min)

These are our top picks. Use list_models to browse 100+ more across all categories.


Install

Agent skills (npx skills)

The canonical cross-client skill remains in the standard repository layout, so skill-directory users can install it directly:

npx skills add CreativeClawCo/creative-claw-marketplace

The OpenAI Store installs the shared ChatGPT/Codex plugin and skill bundle separately; Store users do not need this command.

Claude Code

# 1. Add the marketplace
claude plugin marketplace add CreativeClawCo/creative-claw-marketplace

# 2. Install the plugin
claude plugin install creative-claw@creative-claw-marketplace

# 3. Authenticate — on first use, the MCP server will prompt you to sign in via Clerk OAuth

That's it. The plugin connects to Creative Claw's MCP server and installs the consolidated creativeclaw workflow skill.

Claude Desktop

Add to your MCP config (claude_desktop_config.json):

{
  "mcpServers": {
    "creative-claw": {
      "type": "http",
      "url": "https://app.creativeclaw.co/mcp"
    }
  }
}

No API keys needed — auth is handled via Clerk OAuth on first connection.


Quick Start

Just talk to Claude naturally:

"Generate a product photo of my headphones on a marble surface, golden hour lighting"
  -> creativeclaw routes to its image workflow, picks the model, and generates

"Make a 15-second cinematic video of coffee being poured in slow motion"
  -> creativeclaw routes to its video workflow, generates a reference image, then the video

"Edit this image — change the background to a beach sunset, keep the person unchanged"
  -> creativeclaw routes to an edit model, preserves identity, swaps background

"Make me a LinkedIn quote card with our brand colors"
  -> creativeclaw writes the HTML, pulls the saved theme, and renders via headless Chromium

"Set up our brand — here's our website"
  -> creativeclaw extracts colors/fonts/logos, uploads the assets, and saves a reusable theme

"I need a TikTok-style product video for this shoe" [attach image]
  -> creativeclaw imports the attachment, generates reference frames, picks an I2V model, and produces the clip

Architecture

You -> Claude + Skills (model selection, prompt engineering, creative direction, brand-aware rendering)
              |
         MCP Tools (generate_image, generate_video, render_html_image, update_theme, ...)
              |
       Creative Claw Server (fal.ai + headless Chromium + R2 storage + Clerk auth)
              |
       Permanent media URLs (never expire)

No API keys. No CLI wrappers. No expiring URLs. Just skills + MCP.


Project Structure

This repo is a marketplace — it contains one or more installable plugins.

.claude-plugin/
  marketplace.json         # Marketplace manifest (required for Claude Code marketplace sync)
  plugin.json              # Root plugin metadata
plugins/
  creative-claw/
    .claude-plugin/
      plugin.json          # Plugin manifest (MCP server config)
    openclaw.plugin.json   # OpenClaw compatibility
    skills/
      creativeclaw/
        SKILL.md           # canonical cross-client skill; discoverable by npx skills
        references/        # shared workflows and cross-client upload routing
skill-variants/
  chatgpt/
    platform-upload.md     # OpenAI Store routing for ChatGPT attachments and Codex local files
scripts/
  build-skill-zips.sh      # builds both upload-ready skill archives
creativeclaw-skill.zip             # cross-client archive
creativeclaw-chatgpt-skill.zip     # OpenAI Store archive for ChatGPT and Codex

Maintaining the two distributions

Edit the canonical skill once under plugins/creative-claw/skills/creativeclaw. Put only ChatGPT-specific routing differences in skill-variants/chatgpt/platform-upload.md, then run:

./scripts/build-skill-zips.sh

The OpenAI Store archive contains only SKILL.md, references/, and assets/, matching the Store upload shape for both ChatGPT and Codex. The general archive and repository skill retain the cross-client instructions used by npx skills, Claude Code, and other skill-directory clients.


Pricing

Usage-based — pay only for what you generate. No subscriptions, no commitments. Check creativeclaw.co for current rates.


Compatibility

  • Claude Code — via .claude-plugin/plugin.json
  • Claude Desktop — via MCP server config
  • Codex and other skill-directory clients — via the canonical creativeclaw skill
  • OpenAI Store (ChatGPT + Codex) — via creativeclaw-chatgpt-skill.zip
  • OpenClaw — via openclaw.plugin.json

All use the same skills and connect to the same MCP server.


License

Apache-2.0


Built by Creative Claw Co.

Rendered live from CreativeClawCo/creative-claw-marketplace's GitHub README — not stored, always reflects the source repo.

1 Install Method

NameDescriptionCategorySource
streamable-http remoteHosted streamable-http endpointmcp-serverhttps://app.creativeclaw.co/mcp

0 Comments

Login required
Log in to post a comment or update on this repo.

No comments yet — be the first to share an update.