Flux MCP connector for AI agents

Tools your creative agent reaches for on Flux, scoped per user.

CALL ANY TOOL

Image generation end to end: submit renders, batch variations, dress subjects in reference garments, and track per-user credits.

fluxmcp_get_result

Get result

DO NOT CALL FROM THE LLM. The image-viewer iframe handles all result polling automatically. Internal tool: the iframe invokes this per pending item via `app.callServerTool` after `generate_image` returns with items in `pending` status. Each call inline-polls BFL up to `INLINE_POLL_TIMEOUT_SECONDS`; if the request is still running when the budget expires, the response is `{status: "pending", request_id, ...}` and the iframe just calls again. Returns the same shape as a single-image `generate_image` result: `{data: {status, image_url, image_path, seed, cost, remaining_credits, ...}, message}` on ready, or `{error: {code, ...}, message}` on terminal failure.

Parameters

Name

Type

Required

Description

request_id

string

Required

The `request_id` returned by a previous `generate_image` call. The image-viewer iframe calls this tool per item to poll BFL until that item reaches a terminal state.

fluxmcp_vto

Vto

Virtual try-on: dress `person` in `garment`. Preserves the subject's face, hair, and pose; only the worn item changes. Use this tool : not `generate_image` : whenever the user wants to see a subject wearing a specific item from a reference image. Covers ALL wearable items: garments, hats, sunglasses, shoes, bags, jewelry, and accessories. Prompt formula: "The person of image 1, maintaining exactly their face and pose, wearing the {GARMENT DESCRIPTION} of image 2." Sourcing inputs (same {id}/{url} rules as generate_image): - Person: upload via request_upload_url and pass {id: data.media_id}. - Garment: if the user named a product without attaching an image, web-search for an official product image and pass its public URL as {url: }. Response shape matches generate_image: returns immediately with {data: {items: [{status: "pending", request_id, ...}]}, message}.

Parameters

Name

Type

Required

Description

garment

string

Required

The item to try on : garment, hat, sunglasses, shoes, bag, or other wearable. Same {id}/{url} shape as person. Image 2 in the prompt template. For multi-piece outfits, merge into a single canvas first.

person

string

Required

The subject to dress : usually a person, but a pet or mascot works too. Use {id: } for uploads via request_upload_url or prior generation request_ids. Use {url: } for public web images only. Keep at or below 1 MP for best results.

prompt

string

Required

Styling instruction using the BFL formula: "The person of image 1, maintaining exactly their face and pose, wearing the {GARMENT DESCRIPTION} of image 2." Describe only the garment (category, fit, color). Do NOT describe what to preserve from the person.

height

string

Optional

Output canvas height in pixels. Same caps as width. Omit to let BFL default.

seed

string

Optional

Optional seed for reproducibility. Same seed + same inputs → same result.

steps

string

Optional

Number of denoising steps, 1-4. BFL defaults to 4 (highest quality). Lower values trade quality for speed.

width

string

Optional

Output canvas width in pixels. Omit to let BFL default. width * height must stay under 2 MP.

fluxmcp_get_credits

Get credits

fluxmcp_enhance_video

Enhance video

fluxmcp_get_history

Get history

fluxmcp_generate_image

Generate image

fluxmcp_refresh_image_url

Refresh image url

fluxmcp_generate_video

Generate video

Generate videos with FLUX.3. Each `requests` entry picks an explicit `mode`: * `t2v` : text-to-video, prompt only. * `i2v` : image-to-video via `keyframes`: 1 keyframe animates a still (it becomes the opening frame); 2 keyframes transition/morph from the first to the second; 3-10 form a storyboard spread across the clip (needs explicit `duration`). Per-keyframe `timestamp` (seconds, all-or-none) pins exact positions. * `v2v` : video continuation via `start_video`: the output picks up from the source clip's final seconds (video AND audio). Chain results for longer sequences. When the user PROVIDES media, it MUST go into `keyframes` or `start_video` : never describe provided images/videos in prose and call with `t2v` (the output would look unrelated to the user's media). Media uses the same `{id}` / `{url}` shapes as `generate_image`; upload user-attached files via `request_upload_url` first (`kind: "video"` for MP4s). Reference-based conditioning (keep a subject's identity from reference images / borrow motion from a reference video) is NOT available on this endpoint yet : tell the user so instead of faking it with t2v. Clips are 5-20s at 24fps, `hd` or `fhd`, with synchronized audio by default. The harness reasons about the prompt before rendering and picks `duration` / `aspect_ratio` itself when they're `auto`. DRAFT WORKFLOW: pass `draft: true` for a fast, cheap preview of the exact planned generation. When the user likes a draft, call `enhance_video(request_id=)` to re-render the SAME clip (same composition, seed, and prompt plan) at full quality. Prefer drafts when the user is exploring ideas or wants variants : submit a batch of drafts, let them pick, enhance the winner. Drafts render at hd; `enhance_video` finishes the winner at `fhd` (default) or `hd`. VIDEO TAKES TIME: minutes for short clips, up to ~an hour for long ones. The response returns IMMEDIATELY with pending items. In hosts with the video-viewer widget the widget polls and renders automatically : do not poll yourself; tell the user the video is rendering. In text-only hosts, call `get_result(request_id=...)` per item to check progress (each call waits up to ~45s and returns `pending` again with a `progress` fraction until done). Results survive chat closes : the same `request_id` resumes from the server even days later.

Parameters

Name

Type

Required

Description

requests

array

Required

List of video generation requests. Pass a single-item list for one video; pass up to 4 to generate a batch in one call (each entry is submitted to BFL in parallel). Each entry carries its own mode / prompt / media, so a batch can mix variations of one idea or entirely different clips.

fluxmcp_request_upload_url

Request upload url

fluxmcp_generate_variations

Generate variations

Build your Agent

Same auth pattern across LangChain, OpenAI, Anthropic, and Google ADK.

import { ScalekitClient } from "@scalekit-sdk/node";
import { createReactAgent } from "@langchain/langgraph/prebuilt";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

// Flux tools scoped to this user
const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["fluxmcp"], toolNames: [
    "fluxmcp_generate_image",
    "fluxmcp_generate_variations",
    "fluxmcp_get_history"] },
  pageSize: 100,
});

const agent = createReactAgent({ llm, tools });
await agent.invoke({ messages: [{ role: "user", content: "Generate a hero image of a mountain cabin at dusk." }] });

import OpenAI from "openai";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const openai = new OpenAI();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["fluxmcp"] }, pageSize: 100,
});

const res = await openai.chat.completions.create({
  model: "gpt-5",
  messages: [{ role: "user", content: "Create 4 variations of my last generation." }],
  tools,
});

// Execute the tool call with the user's vaulted Flux credential
await sk.tools.executeTool(res.choices[0].message.tool_calls[0], "user_123");

import Anthropic from "@anthropic-ai/sdk";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);
const anthropic = new Anthropic();

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["fluxmcp"] }, pageSize: 100,
});

const msg = await anthropic.messages.create({
  model: "claude-sonnet-5",
  max_tokens: 1024,
  messages: [{ role: "user", content: "Show my recent Flux generations." }],
  tools,
});

// Tool call runs with the user's vaulted Flux credential
await sk.tools.executeTool(msg.content, "user_123");

import { Agent } from "@google/adk/agents";
import { ScalekitClient } from "@scalekit-sdk/node";

const sk = new ScalekitClient(env.SCALEKIT_ENV_URL, env.SCALEKIT_CLIENT_ID, env.SCALEKIT_CLIENT_SECRET);

const { tools } = await sk.tools.listScopedTools("user_123", {
  filter: { connectionNames: ["fluxmcp"] }, pageSize: 100,
});

const agent = new Agent({
  name: "flux_image_agent",
  model: "gemini-2.5-pro",
  instruction: "Generate and manage Flux images for the signed-in user.",
  tools,
});

await agent.run("Generate a product shot on a plain white background.");

Try these prompts

Copy any prompt into your agent. Each maps directly to a Flux tool. Click to copy, paste into your agent, done.

Generate images

Copy the prompt

Copied

Generate a hero image of a mountain cabin at dusk, 16:9.

Copy the prompt

Copied

Create 4 product shots of the ceramic mug on linen, rendered in parallel.

Copy the prompt

Copied

Dress the model in image 1 in the denim jacket from image 2.

Iterate and vary

Copy the prompt

Copied

Give me 4 variations of my last generation, same direction.

Copy the prompt

Copied

Use my uploaded sketch as a reference for the next render.

Copy the prompt

Copied

Rerun the rooftop scene as a batch of 3 alternatives.

Library and credits

Copy the prompt

Copied

Show my recent generations as a grid.

Copy the prompt

Copied

How many free generations do I have left?

Copy the prompt

Copied

Pull up the prompt and seed for yesterday's renders.

SEE HOW AUTH WORKS

Your users connect once. Their Flux credentials stay vaulted, every call is scope-checked, and every action is logged.

Authorize

Your user connects

Flux MCP

once. We tie it to their identity and the meetings they approved — no shared bot account, no org-wide access

Who:

user ‘A’

when:

Once per user

access:

Limited to user

Store

Their

Flux MCP

token lives in a vault scoped to them. User A's meetings are never reachable by an agent acting for user B, even on the same connection

vault:

encrypted

scope:

per-user

tokens:

auto-refreshed

Resolve

When your agent calls a

Flux MCP

tool, we fetch the right token server-side. It never touches your agent, never appears in the LLM context, never shows up in your logs

speed:

~40ms

check:

before every call

seen by:

nobody

Audit

Every

Flux MCP

tool call is logged — who triggered it, which meeting was fetched, what came back. 90 days of history, tied to the user who authorized it

history:

90 days

export:

SIEM-ready

logged:

every call

Test other agents

See the same per-user auth pattern across other AI connectors.

GTM and RevOps Teams

Competitive intelligence briefing agent

Scans Gong calls for competitor mentions, matches each one to its Notion battlecard, and DMs every affected rep a single Slack digest per cycle. Every call runs as the PMM who owns the briefing, never a shared bot.

GTM and RevOps Teams

Outbound prospecting agent

Searches Apollo for prospects matching your ICP, scores and ranks them, drafts personalized outreach in Gmail, and logs every send to Google Sheets. Mail goes out as the rep, not from a shared inbox.

GTM and RevOps Teams

CRM AI agent

Reads the Granola transcript after every call, extracts next steps and updates the HubSpot record, drafts the follow-up in Gmail, and confirms in Slack, all on the rep's own delegated OAuth.

Support and Ops Teams

Meeting prep

Pulls agenda, participant context, and open action items before every meeting.

Why Scalekit

Secure your agent's access. Connectors ship in minutes

01.

Shared tokens break per-user analytics

A shared Flux token looks fine in a demo. In production every render bills one account, credits drain with no attribution, and you cannot tell who generated what. Scalekit resolves the credential of the actual user who triggered the agent, never a shared bot.

// shared token
audit → bot_service_account

// scalekit
audit → user_abc ✓

02.

Authentication is not authorization

03.

Multi-tenancy is architectural

04.

Flux today. Others tomorrow.

“Our agents act across Salesforce, Gong, Google Drive, and more, on behalf of every customer. Scalekit behind the scenes meant we can keep adding tools without ever rebuilding how credentials or tool calling work.”

Venu Madhav Kattagoni

Head of Engineering / Von

FAQs

Frequently Asked Questions

Does the agent access Flux as the user or through a shared key?

As the user. Scalekit resolves the credential of the person who triggered the agent at request time, so every generation, variation, and upload in your audit trail is attributed to a real user, not a shared service account.

Where is the Flux token stored?

In an AES-256 encrypted vault with per-tenant namespacing. Tokens are resolved at request time, never enter LLM context, refresh automatically, and can be revoked from one dashboard.

Can I limit what the agent does in Flux?

Yes. Filter by tool name in listScopedTools to expose only what you want, for example generation and history without uploads or virtual try-on. Scalekit also enforces scope checks before every API call.

What happens when a user revokes access?

The credential is invalidated at the next tool call. The call fails closed, other users' connections are unaffected, and the revocation is logged in the audit chain.

Who pays when an agent generates images, and how are credits tracked?

The connected user. Every generation runs on that user's own BFL balance: free welcome generations are consumed first, then paid credits. Because Scalekit resolves per-user credentials, one user's batch never drains a teammate's pool, and get_credits reports each balance separately.

On this page

Tool and actions Framework Compatibility Starter Prompt Auth Lifecycle Try Other Agents Why Scalekit