Higgsfield MCP for AI agents

Agents read Higgsfield MCP at once. Changes and sends are held for a person's approval by default.

Book a discovery call Browse all connectors

About Higgsfield MCP

Higgsfield MCP lets agents generate authorized images, videos, characters, and audio, reuse prior creations, and inspect credit balances through Higgsfield's creative platform.

What an agent can do in Higgsfield MCP

Every Higgsfield MCP action is classed by the platform as a read, a change or a send. Reads run at once. Changes and sends are held for a person by default.

Runs at once (reads)

Looks things up in Higgsfield MCP without asking first. 48 actions.

Animation actionsRead-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
Apps describeGet an app's action contract: with `action`, the full input/output schema + execution mode for that one action; without it, a summary of every action. Also returns `manifest_revision`, which apps_invo
Apps searchSearch Higgsfield Marketplace apps callable through MCP. Returns each app's id, name, and the actions it exposes. Flow: apps_search to find an app → apps_describe(app_id, action) to get an action's ar
BalanceGet the user's available credits and current subscription plan. For transaction history, call `transactions` instead.
Get explainer presetsShow the explainer video style presets (CMS-managed catalog). Returns preset ids, names, and preview media. When the user picks one, resolve it with resolve_explainer_preset to get the style reference
Get workflow bundle fileRead a safe text file or directory from a workflow's resource folder. Use this after get_workflow_instructions when the SKILL.md requires a template, reference, or script file.
Get workflow instructionsAd Multiplier — load workflow 'ad-multiplier' when the user asks to 'multiply my video', 'multiply my ad', create multiple independently edited versions of one supplied 4-30 second video, or regenerat
Job displayShow one specific previous generation in the single-result UI widget by job ID. Use when the user wants to inspect or re-display that individual result, including workflows that require separate appro
Job statusCheck the status and results of an async job. Returns instantly. For non-terminal jobs the response includes poll_after_seconds — wait that many seconds before calling again. Typical total times: imag
Jobs waitLong-poll 1-12 generation jobs together without opening a widget. Waits up to timeout_seconds (default 15, max 15) for every job to reach a terminal state, then returns compact indexed statuses and re
List voicesList available voices for speech and voice tools. Returns built-in preset voices plus the user's own custom voices. Each voice has a voice_id and a voice_type ('preset' or 'element'); pass that exact
List website categoriesList the content categories a website can be filed under — each with a slug, label, description, and display position. create_website REQUIRES a `category`; call this first to get the valid slugs, the

Show all 48

List websitesList the websites you own — each with its id, name, slug, and live URL. Use this to find the id of a website you created earlier so you can edit, deploy, or check its status.
List workspacesList every workspace the user can access (their private workspace plus any shared/team workspaces). The `is_selected` field marks which workspace MCP operations currently target. Use when the user ask
Marketing studio v2 avatarsWidget-internal: list the user's Marketing Studio avatars (preset and custom) for the avatar picker.
Marketing studio v2 costsWidget-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 presetsWidget-internal: load a page of the Marketing Studio v2 preset feed for a category.
Marketing studio v2 statusWidget-internal: poll status and results of submitted Marketing Studio v2 jobs.
Models exploreFind 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
Personal clipper jobsShow recent clipping jobs.
Personal clipper statusCheck clip creation progress.
Presets showShow available Higgsfield presets for image-to-video generation. Returns preset ids, names, previews, and descriptions.
Scene builder 3d get artifactResolve a short-lived download for an image or video that a successful Python operation published through `artifacts`. Use the artifact ID and operation ID or revision returned by that operation; do n
Scene builder 3d get blendResolve a short-lived download for the current committed editable Blender file, or a specified historical revision. This retrieves the existing scene; it does not create a revision or render a preview
Scene builder 3d get glbFor an interactive scene preview use `scene_builder_3d_show_scene`. Resolve a short-lived download for the current committed GLB, or a specified historical revision. This retrieves an existing export;
Scene builder 3d get operationRead or wait for a submitted Python operation in this project. Only `succeeded`, `failed`, `timed_out`, and `expired` are terminal; all other statuses require another poll using the same project and o
Scene builder 3d get projectRead a 3D Jutsu project's current revision, scene sequence, active operation, and committed artifacts. Obtain `projectId` from `scene_builder_3d_list_projects`, `scene_builder_3d_create_project`, or a
Scene builder 3d list projectsDiscover the authenticated user's 3D Jutsu projects before choosing a scene to read or edit. Follow `nextCursor` to see more results. Use the selected project's `id` as `projectId` in every project-sc
Scene builder 3d query pythonInspect the latest settled Blender scene without committing changes. `bpy` and the `artifacts` registry are available; assign concise JSON-serializable findings to `result`. Query exact names, metre-s
Scene builder 3d search assetsSearch the curated GLB model catalog available to 3D Jutsu. This read is authorized against `projectId`; the catalog itself is shared. Pass a returned `assetId` to `scene_builder_3d_import_asset` for
Scene builder 3d show sceneShow a minimal interactive 3D Jutsu scene preview with orbit, pan, zoom, a basic animation timeline with play/pause and seeking, and a link to the website. Choose projectId with scene_builder_3d_list_
Shorts studio list presetsBrowse Shorts Studio style presets — the visual STYLE a short is restyled toward. Use this when the user wants to make a short and needs to choose a look: they can pick one of these or create their ow
Shorts studio list sessionsList the caller's past Shorts Studio sessions (newest first) to find a session_id to poll with shorts_studio_status.
Shorts studio statusPoll one Shorts Studio session. Returns {id, status, job_ids}. status='completed' means every clip job is terminal (not necessarily successful). Poll each job_id via job_status for its clip video url
Show generation by idsRender exactly 1-60 requested generation jobs in the full-profile gallery widget, ordered by index and paginated locally in groups of 12. Use once every jobs_wait group is terminal for generate_image_
Show generationsBrowse completed non-Marketing Studio generation history and render one paginated page in the gallery widget. Returns generations with {id, type, status, model, params, results}. Use only when the use
Show marketing studio generationsBrowse past completed Marketing Studio generations only. Returns Marketing Studio video and ad/image generations with {id, type, status, model, params, results}. Use show_generations for non-Marketing
Show marketing studio v2Open 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 the
Show mediasList your uploaded media files by type. Returns media IDs, URLs, and creation timestamps. Call once with the single type the user asked for (default image); do not enumerate the other types unless the
Tiktok accountsList the user's connected TikTok accounts. Returns each account's connector_id (needed by other tiktok_* tools) and status. `active` accounts are ready; `error` accounts need tiktok_reconnect; no acco
Tiktok music trendingList trending commercially licensed tracks from TikTok's Commercial Music Library for the connected account. Show the user a few tracks with their listen links and let them pick; then pass the chosen
Tiktok music tuneOpen the tuning editor for one Commercial Music Library track the user already picked (via tiktok_music_trending): trim start/end and set track/original volumes. Pass the same genre/country_code/date_
Tiktok publish statusStep 3 of publishing. Fetch processing status for a publish_id returned by tiktok_publish. TikTok may take a few minutes to process before the post is live. Read-only.
TransactionsList the user's credit transactions (spend/refund/grant/deduct), newest first. Paginated: if next_cursor is not null, pass it as cursor to get the next page.
Video analysis jobsList the user's video analyses in the current workspace, newest first. Paginate by passing the previous response's cursor.
Video analysis statusGet the status and result of a video analysis. Poll this after video_analysis_create until status='completed' (scenes populated) or 'failed' (fail_reason populated). Analyses typically finish in 3-5 m
Website dbInspect the website's database (D1 / SQLite), READ-ONLY. The website has ONE database — the live site's real data. Pick an operation: 'tables' (list tables); 'schema' (a table's columns — needs table)
Website statusGet the website's deploy status — the live URL and the status of the last deploy. Use to check a deploy that returned 'pending', or to fetch the live URL.

Held for approval by default (changes and sends)

Held for a person's approval by default. The approval is recorded and the action is sent once, never twice, with 10 seconds to undo. 52 actions.

Apps invokeRun one described action on a Marketplace app AS the current user. First call apps_describe(app_id, action) to get the exact `arguments` schema and the `manifest_revision`, then pass them here. Long-r
Cancel trial auto renewalCancel the auto-renewal of the Higgsfield MCP free trial. Call this when the user asks to cancel the trial, cancel auto-renewal, stop the upcoming charge, or asks how to cancel. IMPORTANT SEMANTICS: c
Confirm billing purchaseINTERNAL — invoked ONLY by the plans widget on an explicit user Confirm click. Do NOT call this tool yourself; it charges the user's real saved payment method off-session. To help a user upgrade, top
Confirm trial cancelINTERNAL — invoked ONLY by the cancel-trial confirmation widget on an explicit user click of 'Cancel auto-renewal'. Do NOT call this tool yourself; to cancel the trial's auto-renewal use `cancel_trial
Create voiceOpen the Create Voice Apps UI. Call this immediately when the user asks to create a voice, call the Create Voice tool, or needs a local browser record/upload surface and no confirmed audio_media_id is
Create voice from confirmed audioBackend-only creation of a cloned voice from an already confirmed audio upload. Do not call this tool until audio_media_id and name are already known. For direct creation, first upload speech audio wi
Create websiteStart a new full-stack website. Creates the website and a git repo: a React 19 + TanStack Start app, server-rendered, in ONE Cloudflare Worker, with D1 / R2 / KV / Durable Objects / Containers availab
Deploy websiteBuild and deploy the website via CI, then return its live URL. Every deploy ships the live site at the website's public URL (there is no separate preview stage). IMPORTANT: commit and git push ALL you
DubbingDub a video into another language: translate the spoken audio, synthesize it in the target language, and lip-sync the result back onto the video. Use this when the user asks to dub, translate the spee
Generate audioGenerate 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 to
Generate audio batchSubmit 1-12 independent audio generations in parallel without opening a widget. Each requests[] item accepts the same params as generate_audio, creates exactly one job, and keeps its caller-provided i
Generate imageGenerate 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 differe

Show all 52

Generate image batchSubmit 1-12 independent image generations in parallel without opening a widget. Each requests[] item accepts the same params as generate_image, creates exactly one job, and keeps its caller-provided i
Generate videoGenerate 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 independe
Generate video batchSubmit 1-12 independent video generations in parallel without opening a widget. Each requests[] item accepts the same params as generate_video, creates exactly one job, and keeps its caller-provided i
Marketing studio v2 createWidget-internal: recreate a Marketing Studio v2 preset — validates inputs against the preset's recreate contract and submits one generation.
Media confirmConfirm file uploads after using media_upload's upload_url method. Call this only after every curl PUT returned HTTP 200. Supports confirming multiple uploads at once via media_ids.
Media import urlImport an HTTPS image, video, or audio URL into Higgsfield storage and return a confirmed media_id. Use this before generate_image/generate_video when the user provides a web media URL; generation med
Media uploadUpload media for use in generation, or general files (documents, archives, code) for sharing. Returns presigned URLs for clients that can upload bytes themselves; run the generated curl commands or PU
Media upload widgetRequired local-media intake for Higgsfield in Apps UI-capable clients. Call this immediately as the only tool in the turn when the user refers to an attached/local photo, image, video, or audio but th
Motion controlAnimate an existing character image with the motion and camera movement from a reference video using Kling 3.0 Motion Control. Use this when the user asks to recast, puppeteer, transfer motion, or mak
Outpaint imageExpand or uncrop an existing image by outpainting beyond the original frame while preserving the source content. Use this when the user asks to extend the background, make an image wider or taller, ch
Participate in contestEnter the website in the current Higgsfield app contest, together with the social-media links promoting it. A website not yet PUBLISHED to the community feed is published automatically by the entry —
Personal clipper createTurn YouTube videos into ready-to-share clips. This is a long-running job and can take up to 30+ minutes. Before starting, ask the user how many clips they want, which clip aspect ratio to use, and wh
Publish websitePublish the website: lists the website's CURRENT LIVE production deploy on the Higgsfield community feed ('show in feed'), where other users can discover it. This does NOT deploy — deploy_website (whi
ReframeExpand or reframe an existing video to a new aspect ratio while preserving the source content. Use this when the user asks to make a video vertical, horizontal, square, wider, taller, or fill new edge
Remove backgroundRemove or cut out the background from an existing image or video. Use this when the user asks for background removal, a transparent background, an isolated subject, a clean cutout, or a subject-only a
Rename websiteRename the website's SUBDOMAIN (the slug in its public URL). The site is re-deployed under the new subdomain and the OLD subdomain STOPS WORKING — anyone holding the old URL must be given the new one.
Resolve explainer presetResolve a explainer video style preset (from get_explainer_presets) into a style reference media_id: the backend imports the preset's style image into the user's media storage. Pass the returned media
Reveal generationConfirm the user has rights to the content of an `ip_detected` generation and flip its status to `completed`. Backend accepts only seedance-family jobs (cs_3_0, seedance_2_0, ms_video, etc) and only w
Sandbox execExecute a shell command in a remote Higgsfield cloud Linux sandbox — NOT your local machine or the client's own shell. Whenever a task needs shell tooling (ffmpeg, image/file conversion, scripting), u
Scene builder 3d create projectCreate a new private 3D Jutsu project for the authenticated user. Supply a descriptive name; the service assigns ownership and the project ID. Use this when the user requests a new project or a new st
Scene builder 3d import assetImport a confirmed catalog GLB from `scene_builder_3d_search_assets` into the selected project as a collaborative scene entity. Supply the catalog's asset ID, not a URL. The tool runtime resolves and
Scene builder 3d run pythonCommit one coherent Blender scene edit against the exact revision and scene sequence you inspected with `scene_builder_3d_get_project` or `scene_builder_3d_query_python`. `bpy` and `artifacts` are ava
Select workspaceSet or clear the active workspace — the one all subsequent MCP operations bill against and read from (generations, balance, transactions, uploads, custom references). How to work with workspaces: (1)
Shorts studio createStart a Shorts Studio short: restyle one uploaded source video (4s–120s) into a set of AI-generated short-form clips using a style preset. PAID — reserves credits. Prerequisites, gathered in whatever
Shorts studio create presetCreate a user-owned Shorts Studio style preset from reference media (videos + images). This just stores a STYLE — no generation, no credits. Reference media must be public https URLs (use an uploaded
Show charactersSoul Characters widget — reusable trained identity models. Actions: `list` (browse), `train` (needs `name` + 5-20 ref images, ~10 min, non-blocking — widget polls), `status` (inspect by `soul_id`). Pr
Show plans and creditsOpen the single combined pricing widget for everything billing-related. The widget has two tabs the user can switch between: **Upgrade Plan** (Plus + Ultra, monthly + annual subscription cards) and **
Show reference elementsElements widget — reusable characters / environments / props per workspace. Actions: - `list` (default; paginated by `created_at` DESC, use `cursor` from prev `next_cursor`). - `get` (default when `el
Sync agentsSync Agents — imports the user's user-authored Skills and a personality dump from the current host LLM into Higgsfield. One trigger, one upload, one final confirmation. Calling modes: 1. `message: "/s
Tiktok connectStart connecting the user's TikTok account. Returns an authorize_url — show it to the user as a link; they open it in a browser, approve access on TikTok, and land on a confirmation page. Afterwards c
Tiktok prepare publishStep 1 of publishing to TikTok. Validates the media and TikTok account, creates a publish session, and returns what the user must review and choose (preview, privacy options, required declarations, co
Tiktok publishStep 2 of publishing. Call only after tiktok_prepare_publish and after collecting the user's explicit choices and confirmations. Pass the publish_session_id from prepare (the media is locked to it — d
Tiktok reconnectRe-run the TikTok OAuth for an existing connector in `error` status (expired/revoked access). Returns a fresh authorize_url — show it to the user as a link, then verify with tiktok_accounts.
Upscale imageUpscale and enhance an existing image. Use this when the user asks to upscale, enhance, or increase the resolution of an image to 2K/4K. This tool does not use prompt or count. Provider selects the up
Upscale videoUpscale and enhance an existing video. Use this when the user asks to upscale, enhance, sharpen, denoise, restore, or convert a video to higher resolution. This tool does not use prompt or count, and
Video analysis createStart a scene-by-scene analysis of a video. Provide EXACTLY ONE of: (a) video_input_id — UUID of a video the user has uploaded via media_upload/media_confirm, or (b) youtube_url — a YouTube link (yout
Virality predictorVirality Predictor predicts a video's virality potential, engagement, attention, audience response, retention risk, hook strength, and creative performance with an interactive dashboard. Use when the
Voice changeReplace the spoken voice in a video with a different voice while keeping the original timing and visuals, then re-merge the new audio onto the video. Use this when the user asks to change, swap, or re
Website repo accessGet direct git access to a website's repo to edit it — THE way to get the website's code. Returns the repo URL, branch, slug, and a scoped token; clone it with the terminal tool, edit files, commit +
Website secretsManage a website's SECRETS (environment variables: API keys, tokens). Set them HERE instead of hardcoding them in source. One tool, three operations: 'set' (store/replace — needs name + value); 'delet

Changes wait in Needs you

Changes and sends in Higgsfield MCP are held for a person's approval by default. The approval is recorded, and the action is sent once, never twice, with 10 seconds to undo.

How approvals work

Higgsfield MCP questions

Can an agent change data in Higgsfield MCP on its own?

Not by default. Changes and sends in Higgsfield MCP are held for a person's approval. The approval is recorded, and the action is sent once, never twice, with 10 seconds to undo.

What can an agent read in Higgsfield MCP?

This connector lists 48 read actions. Reads run at once, without waiting for approval.

How does Higgsfield MCP connect?

It connects with dcr oauth. Connectors are built and maintained by third-party developers; availability is confirmed during scoping.

Bring Higgsfield MCP to your agents.

Book a discovery call