For AI agents — MCPBundles Directory API
For MCP client apps (human connect):
MCP connect URL: https://mcp.higgsfield.ai/mcp
Skill page: https://www.mcpbundles.com/skills/higgsfield-mcp
Publisher MCP server
Tools: 158
Live probe refreshed Nov 21, 2026 · Endpoint host mcp.higgsfield.ai
AI Skill
SKILL.md
Domain knowledge for Higgsfield MCP — workflow patterns, data models, and gotchas for your AI agent.
Higgsfield is an AI media generation platform for creating short videos, images, and motion effects from text and reference assets. Use this skill for any request that asks to produce, animate, restyle, or stage media via Higgsfield's models (DoP camera-aware video, Soul photoreal image, Speak lip-sync, plus motion/effects models surfaced through Marketing Studio).
Capabilities
Generate images from a text prompt with an optional aspect ratio, style/model choice, and one or more reference images for likeness, composition, or style transfer.
Generate videos from a text prompt and/or a starting image. Camera-aware video supports specific shot intents (push-in, orbit, dolly, etc.); motion-effect generation drives stylized animation from a still.
Apply a named Marketing Studio preset (look, motion effect, or template) to a prompt or reference image to match a current trend or campaign style without hand-tuning parameters.
Maintain persistent characters: list saved characters and reuse a character reference across generations so the same face/identity appears in new scenes.
Predict the virality of a generated piece of media before publishing, to choose between candidates.
Asset and job lifecycle
Upload a reference image or audio asset, then confirm it so it becomes addressable by id in subsequent generation calls. Generations accept these media ids in their reference slots; never paste a public URL into a prompt when the asset is uploadable.
Generations are asynchronous. After a generate call, poll job status until completion, then fetch the job display to read the final media ids and rendered URLs. A pending status is normal for video; do not retry the generate call while a job is still running.
List past generations to recover work the user mentions ("the cinematic kitchen video from earlier") without asking for ids. List media to retrieve raw uploads or render outputs by recency or type.
Model and template selection
Explore the model catalog to discover which models are currently available and what each is tuned for (photoreal stills, camera-aware video, lip-sync, effect transfer). Pick the model that matches the user's described output, not the most expensive option.
Marketing Studio presets bundle a model + parameters + style guidance into a single named template. Prefer a preset when the user names a trend or a look ("Y2K music video", "product hero shot"); fall back to raw model parameters when they describe a custom intent.
Workspace and account scoping
All generations, characters, and media belong to a workspace. List workspaces and select the right one before generating when the user mentions a specific brand, client, or project; otherwise the current workspace persists across calls.
Credit balance, plan tier, and transaction history are available for "do I have enough credits?" or "what did I spend?" questions. Read balance for the instantaneous number, plans-and-credits for the entitlement view, and transactions for spend history. Generations consume credits; refuse to fire a long video render if the balance check shows it will fail.
Output handling
Generated media is returned as URLs plus internal media ids. Surface the rendered URL to the user and keep the media id internally so follow-up calls (restyle, re-cut, virality scoring, reuse as reference) work without re-uploading.
When the user says "make another like that" or "use the same character", resolve the prior generation or character by listing recent work first; do not re-prompt them for an id they never saw.
Setup Instructions
Connect Higgsfield MCP to any MCP client in minutes
This server may ask you to sign in when your AI client connects.
Maintain this listing
Operate Higgsfield? You can take over the listing's metadata.
Operate Higgsfield MCP?
Take over this listing's metadata — name, description, category, logo, website, contact email, and skill content. Verification is a 6-digit code we email to one of the maintainer addresses your server already publishes in /.well-known/security.txt or /.well-known/mcpbundles.json. Free, takes about a minute.
MCPBundles publishes this directory for MCP discovery. Except where we host or operate an offering, third-party services run under their own terms. Product and company names on this page are used in a descriptive, identifying way (including under nominative fair use where applicable); they remain the property of their owners. Nothing here grants you rights in those marks, and nothing here is an offer to sell a third party's services. Terms
OAuth sign-in
Higgsfield
Connect your account, then chat with AI to run tools.
Generate AI videos, images, and motion effects with Higgsfield's models (DoP, Soul, Speak, and related) from chat.
This listing identifies a third-party MCP server. MCPBundles is not affiliated with, sponsored by, or endorsed by the service or its operator unless stated on this page.
Opens MCPBundles Studio with this server selected. After sign-in, chat and run tools from the same thread (tool names load once your session connects).
Showing 25 of 158 tools from the public preview. Connect the server to inspect the full live tool list.
Generate7
Marketing6
Get4
Show2
Other capabilities6
Higgsfield app services
write
use_higgsfield
Interact with Higgsfield through a single interface for app services and UI actions. Use action to select the operation and page to identify the current app page. If action is omitted, the app is initialized; if page is omitted, home is used. Returns structured data for the requested operation.
Higgsfield app services — Interact with Higgsfield through a single interface for app services and UI actions. Use action to select the operation and page to identify the current app page. If action is omitted, the app is initialized; if page is omitted, home is used. Returns structured data for the requested operation.
Higgsfield Preset Instructions — Resolve a named Higgsfield preset or command and read its instructions without executing it. For every Katana preset run, read all instruction parts and collect required inputs, then call get_katana_config to register the session, whether the run is paid or free. Set free_generation: false for a paid run, or true only when the user explicitly requests a free run. Forward its preset_session_id in every generation, cost estimate and batch item. Add use_free_gens: true only when the user explicitly
Higgsfield Katana Config — Create a run session for a specific published Katana preset. This tool writes session state. Call for every Katana preset run, whether paid or free, after reading all get_preset_instructions parts and collecting required inputs. Reading instructions, browsing presets or asking about free balance alone does not start a run. Set free_generation to false for a paid tracking session, or true only when the user explicitly requests a free run; true spends the backend Katana free run when starting. Bar
Explore Models — Find generation models. Use recommend with goal + input context; use get for model constraints. Items carry supports_unlim when the model accepts free-trial unlimited generations; the top-level unlim block says whether the caller can spend them right now, and the trailing 'Unlim configs' text lists the configurations their allowance actually covers.
Generate Image — Generate one image request and render its result(s) in the generation widget. Use count 2-4 only for variants of the same prompt, inputs, and settings; for 2-12 independent image requests with different prompts or inputs, use the headless generate_image_batch tool instead. Attached/local media: if your code environment can read the file, upload it yourself (`media_upload`, curl PUT, `media_confirm`); otherwise call `media_upload_widget`. Do not ask for Claude chat attachments because remote tool
Frequently Asked Questions
What is the Higgsfield MCP server?
Generate AI videos, images, and motion effects with Higgsfield's models (DoP, Soul, Speak, and related) from chat. It provides MCP tools that your client discovers when it connects (this page may not list every tool name) that AI agents can use through the Model Context Protocol (MCP).
How do I connect Higgsfield MCP directly?
Add this server URL to your MCP client configuration (Claude Desktop, Cursor, VS Code, etc.). The URL is: https://mcp.higgsfield.ai/mcp. Sign in with your account on that server.
Remote MCP directoryUnlimited tool calls through MCPBundlesThe operator of this MCP may charge for API usage, seats, or OAuth access. Check their site before heavy use.
Generate Video — Generate one direct video request and render it in the generation widget. Use count 2-4 only for variants of the same prompt, inputs, and settings; use headless generate_video_batch for 2-12 independent requests. GENJUTSU TRIGGERS: route `Higgsfield Genjutsu` by intent. Copy, repeat, reproduce, mimic, or transfer motion, movement, actions, gestures, dance, or camera motion from one driving video to reference-image subjects -> `hf_mult_motion_control`. Replace, change, or swap an object, product,
Generate Audio — Generate one speech/voice request (text-to-speech) and render it in the generation widget. This tool accepts one prompt; for 2-12 independent lines or prompts, use the headless generate_audio_batch tool instead. DEFAULT model: seed_audio (Seed Audio 1.0 by ByteDance) — use it unless the user explicitly asks for a different engine. seed_audio takes a preset or reference-element voice (voice_type 'preset'|'element' + voice_id) plus optional tuning params (format, sample_rate, speech_rate, loudness
Generate Image Batch — Submit 1-12 independent image generations in parallel without opening a widget. Each requests[] item accepts generation params with count fixed to 1 and no get_cost, creates one job on successful submission, and keeps its caller-provided index in the response. Use for multiple distinct prompts or inputs; use generate_image for one user-facing generation. Poll returned job IDs with jobs_wait in agent-chosen groups of at most 12. For larger sets, collect indexed jobs across submission batches. Aft
Generate Video Batch — Submit 1-12 independent video generations in parallel without opening a widget. Each requests[] item accepts generation params with count fixed to 1 and no get_cost, creates one job on successful submission, and keeps its caller-provided index in the response. Use for multiple distinct prompts or inputs; use generate_video for one user-facing generation. Poll returned job IDs with jobs_wait in agent-chosen groups of at most 12. For larger sets, collect indexed jobs across submission batches. Aft
Generate Audio Batch — Submit 1-12 independent audio generations in parallel without opening a widget. Requests can send text and reference inputs to external audio model providers through Higgsfield and consume credits. Each requests[] item accepts generation params with count fixed to 1 and no get_cost, creates one job on successful submission, and keeps its caller-provided index in the response. Use for multiple distinct prompts or inputs; use generate_audio for one user-facing generation. Poll returned job IDs wit
Generate 3D — Generate a 3D GLB mesh. Use `models_explore(type:'3d')` to pick a model and see its `medias[].roles` and `parameters`. Attached/local file: upload it yourself if readable (`media_upload`, curl PUT, `media_confirm`), else call `media_upload_widget`; remote tools cannot read Claude chat attachments. Web media URL: call `media_import_url`, pass returned `media_id`; `medias[].value` must be media_id/job_id, not URL. Defaults: `image_to_3d` for general image-to-3D with optional texturing, PBR, and ri
Animation Actions — Read-only catalog of the 3D rig animation library (678 actions: locomotion, gestures, dancing, combat, daily actions). Search by name or browse by group/category to find the animation_action_id for 3D generation with enable_animation=true. Each result has a preview_url GIF — when several candidates fit (e.g. many Idle or Walk variants), show the user the previews as markdown images and let them pick instead of choosing blindly. Does not create jobs.
Save Katana result to history — Save one verified final video from a named Katana preset as a completed job in the selected workspace. Pass preset_id and the confirmed final video media_id, the run preset_session_id from get_katana_config, and optionally folder_id. The final job set is added to that session, including when the session is already closed. This links the existing video without copying files, generating, charging generation credits or publishing to the community. Keep media_upload → PUT → media_confirm for local/s
Publish Katana Preset — Submit an uploaded video as a Katana community preset for the authenticated user in their selected workspace, optionally including the original prompt and up to ten uploaded image or video references. Returns a submission receipt; acceptance does not mean the preset is publicly available. Invoked only by the app. Identical submissions reuse their receipt; changed details for an already submitted video are rejected.
Get Katana Preset Submission — Check whether the authenticated user has submitted an uploaded video as a Katana community preset in their selected workspace. Returns the saved receipt, prompt and reference IDs, or submitted=false when no submission exists. Submission does not imply delivery, approval or public availability. Invoked only by the app.
Browse Media Presets — Search and browse reusable image and video generation presets from Higgsfield's Viral, Marketing Studio, Genjutsu and Katana galleries, or retrieve a preset's inputs and preview without starting a generation. For sources other than Katana: A bare preset slash command or a request to open, preview, or browse a preset only opens its widget. For supplied attachments, use input_schema from get_preset_instructions to map and upload the relevant files before opening any widget. Call get_presets exactl
Execute Preset — Request execution of one published preset from the Viral, Marketing Studio or Genjutsu gallery, including a Genjutsu Style (genjutsu-style: preset_id) that restyles the user's own video. A bare preset slash command or a request to open, preview, or browse a preset only opens its widget. For supplied attachments, use input_schema from get_preset_instructions to map and upload the relevant files before opening any widget. Call get_presets exactly once with source, preset_id and initial_inputs in t
List Marketing Avatars — Read-only list of user and preset Marketing Studio avatars. Does not create or modify avatars.
Show Marketing Studio v2 — Open Marketing Studio — a template gallery widget with category tabs (UGC ads, product shots, motion graphics, posters, ads, marketplace) and a preset grid the user browses and recreates from with their own product image. Use this whenever the user asks for Marketing Studio or wants marketing assets in UGC, ads, posters or marketplace categories. For product-shot or motion catalog browsing, and /marketing-studio, use get_presets instead. The widget handles preset selection, inputs, generation, a
Marketing Studio v2 Presets Page — Widget-internal: load a page of the Marketing Studio v2 preset feed for a category.
Marketing Studio v2 Avatars — Widget-internal: list the user's Marketing Studio avatars (preset and custom) for the avatar picker.
Marketing Studio v2 Costs — Widget-internal: the Marketing Studio v2 pricing document. credits = cost_units / cost_units_per_credit; video flows cost fixed_cost_units + cost_units_per_second × duration.
Marketing Studio v2 Create — Widget-internal: recreate a Marketing Studio v2 preset — validates inputs against the preset's recreate contract and submits one generation.
Marketing Studio v2 Job Status — Widget-internal: poll status and results of submitted Marketing Studio v2 jobs.
Show Generations — Browse completed non-Marketing Studio generation history by default, or include all job states for a live feed with only_completed=false. Renders one paginated page in the gallery widget. Returns generations with {id, type, status, model, params, results}. Use only when the user explicitly asks to browse regular generation history. Do not use this history tool after generate_*_batch or jobs_wait; show an exact completed batch with one show_generation_by_ids call instead. Use show_marketing_studi
Showing the first 25 tools — full list and schemas: Directory API.
How do I connect Higgsfield MCP through the MCPBundles gateway?
Add the MCPBundles server URL to your MCP client configuration (Claude Desktop, Cursor, VS Code, etc.). The URL format is: https://mcp.mcpbundles.com/bundle/higgsfield-mcp. Authentication is handled automatically.
How many tools does Higgsfield MCP provide?
Higgsfield MCP is a remote MCP server. The live tool list is supplied by the server when your MCP client connects, so the count is not fixed on this public page. After you connect in MCPBundles Studio or your client, you will see the tools your session can call. A SKILL.md is still included to guide your agent on capabilities and workflows.
What authentication does Higgsfield MCP require?
Higgsfield MCP uses One-click sign in. Higgsfield MCP requires credentials. Connect via MCPBundles and authentication is handled automatically.
MCPBundles is an independent platform built on the open Model Context Protocol standard. MCPBundles is not affiliated with, sponsored by, or endorsed by Anthropic PBC.
More in media
Other MCP servers in this category from the directory index