CreativeClaw
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| how_to_connectB | Learn how to connect to the full Creative Claw MCP server with authentication. Creative Claw is an AI media generation platform supporting 1,000+ models (FLUX, Gemini, Veo, Sora, Kling, Seedance, HeyGen, ElevenLabs) for image, video, and speech generation. This tool explains setup for Claude Desktop, Cursor, ChatGPT, and other MCP clients, plus how to claim free credits. |
| generate_imageB | Generate high-quality images using AI models including FLUX, Gemini, GPT Image, Recraft, and more. Supports text-to-image, image-to-image editing, style transfer, background removal, and professional product photography. Handles transparency, aspect ratios, and multi-model comparison. Requires connection to the full Creative Claw MCP server. |
| generate_videoA | Generate cinematic video content using state-of-the-art models including Gemini Omni, Veo, Sora, Kling, Seedance, MiniMax, and Hailuo. Supports text-to-video, image-to-video animation, reference-based generation, native audio, and multi-shot film production. Handles durations from 2-30+ seconds depending on model. Requires connection to the full Creative Claw MCP server. |
| generate_speechA | Generate expressive, natural-sounding speech and voiceovers using ElevenLabs models. Supports multilingual narration, dialogue, emotional delivery, custom Character voices, and consent-based voice cloning. Ideal for video narration, audiobooks, podcasts, and UGC content. Requires connection to the full Creative Claw MCP server. |
| list_modelsA | Discover all available AI models for image, video, and speech generation across Creative Claw's catalog. Returns model IDs, capabilities, cost estimates, reference support, duration limits, and recommended use cases. Access 1,000+ production-ready models through a unified API. Requires connection to the full Creative Claw MCP server. |
| get_model_paramsA | Get detailed parameters, prompting guidelines, and technical specifications for a specific AI model. Returns supported dimensions, duration ranges, reference capabilities, cost structure, and expert prompting tips. Essential for optimizing generation quality and understanding model-specific features. Requires connection to the full Creative Claw MCP server. |
| check_jobA | Check the status and retrieve results of asynchronous generation jobs. Video and some image generations are queued; this tool monitors progress and returns completed media URLs. Returns job status (queued, in_progress, completed, failed), progress percentage, estimated completion time, and permanent media URLs. Requires connection to the full Creative Claw MCP server. |
| list_charactersA | List reusable Characters (persistent identities with visual appearance and optional voice) for consistent multi-shot video production, UGC ads, and branded content. Characters maintain identity across generations and can be combined with brand themes for on-brand storytelling. Supports ElevenLabs voice cloning with explicit consent. Requires connection to the full Creative Claw MCP server. |
| get_credits_balanceA | Check your current Creative Claw credits balance and usage history. Creative Claw uses usage-based pricing—pay only for what you generate, no subscriptions. New accounts include free trial credits. This tool returns your remaining balance, recent usage, and a link to purchase more credits. Requires connection to the full Creative Claw MCP server. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 9 tools
Most tools target clearly distinct actions: generation by modality, job checking, model discovery, character listing, and credits. The only real overlap is between list_models and get_model_params, which return similar capability/cost information at different levels of detail.
The naming pattern is mostly consistent verb_noun: generate_image, generate_video, generate_speech, list_models, list_characters, check_job, get_credits_balance. The outlier is how_to_connect, which breaks the verb_noun style but is still clear and understandable.
Nine tools is a well-scoped size for an AI media generation server. Each major capability has a corresponding tool, and the count is neither bloated nor too thin for the platform's purpose.
The server covers the core media generation lifecycle: model discovery, image/video/speech generation, async job status, credits, and persistent character lookup. Notable gaps include no character creation/update/delete and no job cancellation, but agents can still complete primary generation workflows.