higgsfield-mcp-unified
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| HIGGSFIELD_JWT | No | __session cookie (expires in ~1 minute); for one-shot tests only. Alternative to HIGGSFIELD_CLERK_CLIENT for authenticating the web backend. | |
| HIGGSFIELD_SECRET | Yes | Secret from the platform.higgsfield.ai dashboard. Required for the official REST API backend. | |
| HIGGSFIELD_API_KEY | Yes | API key from the platform.higgsfield.ai dashboard. Required for the official REST API backend. | |
| HIGGSFIELD_CLERK_CLIENT | No | __client cookie from cloud.higgsfield.ai (lasts ~7 days). Required for the web backend unless HIGGSFIELD_JWT is provided instead. | |
| HIGGSFIELD_ENABLE_WEB_BACKEND | No | Set to 1 to opt in to the experimental cloud web backend (unlocks cloud-only models such as Sora 2, Veo 3.x, Kling 3.0). Off by default. |
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
} |
| logging | {} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
| extensions | {
"io.modelcontextprotocol/ui": {}
} |
| experimental | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| list_models_toolC | List every supported Higgsfield model. |
| generate_image_toolC | Submit an image-generation request. Returns a job_handle to poll. |
| generate_video_toolC | Submit a video-generation request. Returns a job_handle to poll. |
| get_status_toolC | Check job state and return output URLs when ready. |
| cancel_job_toolC | Cancel a queued or in-progress job. |
| upload_image_toolC | Upload a local image and get a hosted URL to use as image_url. |
| subscribe_toolB | Long-poll until the job reaches a terminal state (completed/failed/etc). |
| preflight_check_toolA | Check auth + config for both backends before submitting a generation. |
| recommend_model_toolB | Suggest models for a described goal. Ranks by keyword overlap; verified-only by default. |
| validate_params_toolB | Pre-flight check params against a model's supported set (no generation). |
| create_character_toolC | Train a reusable Soul character from reference images. Results best-effort until verified. |
| get_character_toolC | Check a Soul character's training status. |
| list_characters_toolC | List trained Soul characters. |
| delete_character_toolC | Delete a trained Soul character. |
| get_balance_toolA | Get available credits + plan (best-effort; official API key required). |
| list_jobs_toolC | List recent generations (history) from the official backend. |
| list_soul_styles_toolA | List Soul image style presets to pick by name. |
| list_motions_toolA | List DOP motion presets for image-to-video. |
| generate_speech_video_toolC | Talking-head video from a face image + WAV audio (official backend). |
| generate_batch_toolB | Submit multiple generations at once. Each request: {kind, model_id, prompt, ...params}. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| cinematic_shot | A cinematic still/video prompt for a subject with a given mood and lens. |
| product_360 | A turntable product-showcase prompt. |
| animate_portrait | An image-to-video prompt to gently animate a portrait. |
| action_sequence | A dynamic action video prompt. |
| b_roll | An atmospheric b-roll video prompt. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| all_models | The full Higgsfield model catalog, including inferred (unverified) models. |
TDQS
Scored across 20 tools
Most tools target distinct resource+action pairs (image vs video vs speech-video generation, character CRUD, model/job listing). The only mild overlap is get_status_tool vs subscribe_tool (both inspect job state) and the three pre-flight helpers (preflight_check, validate_params, get_balance), but descriptions make their separate targets clear.
Every tool follows the same verb_noun_tool convention (generate_image_tool, list_characters_tool, get_status_tool, cancel_job_tool), giving a fully predictable, uniform naming pattern with no deviations.
20 tools is on the heavier side but each covers a plausibly needed capability across generation, character lifecycle, presets, job control, and utilities. It leans verbose (several discovery/validation helpers) but nothing is clearly redundant.
Strong coverage: generation (image/video/speech/batch), full character CRUD, job status/cancel/subscribe, upload, model/style/motion discovery, balance, and pre-flight validation. Minor gaps like job history deletion or character update are absent but not blocking for the core workflow.