How does MCP work?
Create with Higgsfield skills inClaude
Create a Mixed Media explainer showing how an airplane wing creates lift
Create a cinematic animated explainer showing how one decisive chess move changes the entire game
Create a short 2D animated explainer showing how early humans discovered and learned to use fire


Create a complete UGC flow for this tumbler using the attached creator, from concept and script to a finished 16:9 video
Create a fast-paced short-form product video with a strong opening hook
Create a polished social clip from the strongest moment in this YouTube video

Create a playful TV commercial for this snack brand with bold product shots and an energetic animated world

Create a sleek motion design video that presents this keyboard through rhythmic typography, graphic transitions, and detailed product shots
Create a colorful animated infographic that explains the key facts through bold numbers, icons, and easy-to-follow transitions


Create a short-form drama set in a quiet library, with a tense encounter, an emotional reveal, and a cinematic ending

Create a cinematic city sequence centered on a performance car, with atmospheric lighting, controlled camera movement, and an editorial film look


Localize this UGC video for English, Spanish, and French audiences while preserving the creator’s voice, timing, and visual performance
Every creative model, insideClaude
Give Claude access to the most powerful image and video models.

Nano Banana Pro
Google Omni Flash
Seedance 2.0

Seedream 5.0 Lite
Seedance 2.0 Fast & Mini
Kling 3

GPT Image 2

Soul 2.0
Got any questions left?
Higgsfield uses MCP (Model Context Protocol), an open standard that gives AI agents access to external tools. Once connected, your agent can generate images, create videos, train characters, and browse your creation history, all within a single session.
Higgsfield MCP works with Claude (web, Cowork, and Claude Code), OpenClaw, Hermes Agent, and NemoClaw. Any agent or client that supports MCP can connect to Higgsfield.
Higgsfield gives your agent access to 30+ models including Soul, Cinema Studio, Flux, Seedream, Kling, Minimax Hailuo, Veo, and more. Your agent automatically selects the best model for the task, or you can specify one yourself.
Images up to 4K resolution, videos up to 15 seconds across multiple cinematic styles, consistent characters using Soul training, and more. You can generate from text prompts, reference images, or a combination of both.
No. Add the Higgsfield MCP server URL in your agent's settings and authenticate through your Higgsfield account. No API keys to manage or configure.
Higgsfield tools use the same credit system as the Higgsfield platform. Each generation costs credits based on the model and resolution. Your existing Higgsfield plan credits work seamlessly through any connected agent.
Images typically complete in a few seconds. Videos take longer depending on duration and model. All generation runs asynchronously, so your agent polls for results and delivers them as soon as they're ready.
Yes. You can browse your full generation history, reference any past image or video, and use it as a starting point for new creations. This makes iterative workflows and multi-step production easy.
Yes. Any MCP-compatible client can connect. If you're running OpenClaw on a VPS, Hermes Agent on your local machine, or NemoClaw on NVIDIA hardware, just point it to the Higgsfield MCP server and you're ready to generate.






