# Higgsfield MCP

Vendor: Higgsfield  
Category: other  
Auth: API_KEY  
Composio slug: `higgsfield`

Higgsfield AI provides asynchronous image and video generation APIs powered by multiple creative AI models.

## Verdict

Higgsfield brings AI image and video generation into your workspace. @mention it to create visuals from text prompts, train custom character references your team can reuse, or turn static images into short video clips. The MCP exposes twelve tools covering text-to-image (Soul Standard and V2), image-reference workflows (Popcorn), and text-to-video (Seedance 2.0). Designers and content teams get the most value — you can iterate on concepts, test visual directions, or produce social assets without leaving a Project. All requests are asynchronous: you submit a prompt, poll for status, then retrieve the final URL. You'll need an API key and credits in your Higgsfield account; generation costs vary by model and resolution.

## Tools

- **Cancel Request** — Cancel a Higgsfield generation request while it is still queued; requests already processing or finished cannot be canceled.
- **Create Character Reference** — Start training a reusable Higgsfield Soul ID character reference from one or more public images. Poll GET_CHARACTER_REFERENCE with the returned ID.
- **Estimate Soul V2 Cost** — Estimate the authenticated account's credit and USD cost for a fixed Higgsfield Soul V2 Standard image request without starting generation.
- **Generate Content (Deprecated)** — Deprecated fallback for model routes without typed tools; returns a request ID for status polling. Prefer typed generation actions.
- **Generate Image** — Submit a text-to-image request to Higgsfield Soul Standard and return the request ID used to track the asynchronous result.
- **Generate Image With References** — Submit a Higgsfield Popcorn request that uses one or more reference images and return the request ID used to track the asynchronous result.
- **Generate Seedance 2 Text Video** — Submit a ByteDance Seedance 2.0 text-to-video request through Higgsfield and return the request handle used to track the asynchronous result.
- **Generate Soul V2 Image** — Submit a text-to-image request to Higgsfield Soul V2 and return the request ID used to track the asynchronous result.
- **Generate Video From Image** — Generate a video from a publicly accessible starting image with Higgsfield DOP Lite and return the request ID used to track the asynchronous result.
- **Get Character Reference** — Get a Higgsfield Soul ID character reference and its current training status by ID.
- **Get Request Status** — Get the current state of a Higgsfield generation request and return generated image, video, or audio URLs when complete.
- **List SOUL V2 Styles** — List the SOUL V2 image styles available to the authenticated Higgsfield account, including the style IDs accepted by SOUL V2 generation requests.

## Setup

1. Create or open a Switchy Project.
2. Open Integrations and connect Higgsfield.
3. Authorise through api_key.
4. Teammates can now @-mention Higgsfield tools in chat.

---
Last verified: 2026-10-17T02:00:10.360Z  
Canonical URL: https://switchy.build/directory/mcps/higgsfield