Skip to content
Scalekit Docs
Talk to an Engineer Dashboard

Connect AI agents to the Higgsfield MCP server

Vendor MCP
Open markdown

The Higgsfield MCP connector routes your AI agent's tool calls to Higgsfield's own MCP server through Scalekit. Each user signs in to Higgsfield once, and Scalekit stores and refreshes their tokens, so your agent never handles credentials. It comes with 192 tools.

Tools
192
What they doRead · write · destructive
50 · 134 · 850 read134 write8 destructive
Users sign in with
OAuth app
Scalekit's or your own

What you can do

  • Generate media: create images, videos, speech audio, and 3D models from prompts, one at a time or in batches
  • Edit images and videos: upscale, remove backgrounds, outpaint, reframe, dub, change voices, and transfer motion to characters
  • Make short-form clips: turn YouTube videos into clips or restyle a source video into shorts with style presets
  • Analyze videos: break a video down scene by scene and predict its virality, hook strength, and retention risk
  • Build and deploy websites: create full-stack sites, deploy them live, manage secrets, and publish to the community feed
  • Publish to TikTok: connect accounts, pick licensed trending music, and post videos with the required confirmations

Setup

  1. Install the SDK

    Terminal window
    npm install @scalekit-sdk/node dotenv

  2. Set your credentials

    Add your Scalekit credentials to your .env file. Find values in app.scalekit.com > Developers > API Credentials.

    .env
    SCALEKIT_ENVIRONMENT_URL=<your-environment-url>
    SCALEKIT_CLIENT_ID=<your-client-id>
    SCALEKIT_CLIENT_SECRET=<your-client-secret>

  3. Create the Higgsfield MCP connection

    In AgentKit > Connections, create a Higgsfield MCP connection. The name you give it is the connection_name your code passes. See Configure connections.

    Scalekit credentials are available for Higgsfield MCP server, so you don't need to register an OAuth app.

  4. Authorize a user and make your first call

    quickstart.mts
    import { ScalekitClient } from '@scalekit-sdk/node'
    import 'dotenv/config'
    import { createInterface } from 'node:readline/promises'
    

    const scalekit = new ScalekitClient(
      process.env.SCALEKIT_ENVIRONMENT_URL,
      process.env.SCALEKIT_CLIENT_ID,
      process.env.SCALEKIT_CLIENT_SECRET,
    )
    const actions = scalekit.actions
    

    const connector = 'higgsfieldmcp'
    const identifier = 'user_123'
    

    // Generate an authorization link for the user
    const { link } = await actions.getAuthorizationLink({ connectionName: connector, identifier })
    console.log('Authorize Higgsfield MCP:', link)
    const rl = createInterface({ input: process.stdin, output: process.stdout })
    await rl.question('Press Enter after authorizing...')
    rl.close()
    

    // Make your first call
    const result = await actions.executeTool({
      connector,
      identifier,
      toolName: 'higgsfieldmcp_animation_actions',
      toolInput: {},
    })
    console.log(result)
    Terminal window
    npx tsx quickstart.mts

    Each user signs in once. See Authorize a user for the full flow and statuses.

Tools

Pass the exact name to execute_tool
Try in PlaygroundRequest a tool
  • higgsfieldmcp_animation_actionsRead-only catalog of the 3D rig animation library (678 actions: locomotion, gestures, dancing, combat, daily actions).Read-only

    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.

    Inputs

    afterstring
    Pagination cursor (next_page_token from a previous result).
    categorystring
    Filter by category, e.g. Walking, Running, Jumping, Idle, Dancing, Punching (see `categories` in the result).
    groupstring
    Filter by top-level group: WalkAndRun, BodyMovements, DailyActions, Dancing, Fighting.
    limitinteger
    Max results, default 20.
    querystring
    Search term matched against action name and category, e.g. 'walk', 'backflip', 'sword attack'. Omit to browse.
  • higgsfieldmcp_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.Read-only

    Describe App Action

    Get 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_invoke requires. Read-only.

    Inputs

    app_idstringrequired
    App UUID from apps_search.
    actionstring
    Action name. Omit to list all actions in summary.
  • higgsfieldmcp_balanceGet the user's available credits and current subscription plan.Read-only

    Check Balance

    Get the user's available credits and current subscription plan. For transaction history, call `transactions` instead.

    Inputs

    This tool takes no inputs.

  • higgsfieldmcp_get_account_overviewRetrieve the authenticated user's available free-trial offer and account URL for display in the app.Read-only

    Get Account Overview

    Retrieve the authenticated user's available free-trial offer and account URL for display in the app. Fetching the offer may create a checkout session, but does not start a trial or charge a payment method. Invoked only by the app.

    Inputs

    infostringrequired
    Account information requested by the app.
  • higgsfieldmcp_get_explainer_presetsShow the explainer video style presets (CMS-managed catalog).Read-only

    Explainer Presets

    Show 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 media_id for generations.

    Inputs

    This tool takes no inputs.

  • higgsfieldmcp_get_folderRead exactly one existing folder_id inside project_id.Read-only

    Get Folder

    Read exactly one existing folder_id inside project_id. Does not list children or create a folder.

    Inputs

    folder_idstringrequired
    No description.
    project_idstringrequired
    No description.
    workspace_idstringrequired
    Workspace context used for this request. This never changes the account's selected workspace.
  • higgsfieldmcp_get_katana_configCreate a run session for a specific published Katana preset.Read-only

    Get 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. Bare /katana must first resolve to a specific preset. Reuse the same idempotency_key on retries; never create a session just to reread instructions. Forward the returned preset_session_id in every generation, cost estimate and batch item in this run. Add use_free_gens: true only when the user explicitly requests free generations; a session alone does not select free billing.

    Inputs

    free_generationbooleanrequired
    False tracks a paid run without spending a Katana free run. True spends a Katana free run at session start; use only after an explicit request for free generations. Keep this choice unchanged on retries.
    idempotency_keystringrequired
    A unique key per intended run; reuse unchanged after uncertain responses or retries.
    presetstringrequired
    Exact published /katana/slug selected through get_preset_instructions; not a general command or continuation path.
All 153 in AI