FLUX

by black-forest-labs

Not rated
GitHub

About

Official FLUX MCP server from Black Forest Labs. Generate, edit, vary, and browse FLUX.2 images directly in any MCP-compatible client

Details

Author
black-forest-labs
Categories
Design, Other, AI

Setup

Install FLUX in your MCP client (Claude Desktop, Cursor, Windsurf, and others).

Repository: https://github.com/black-forest-labs/flux-mcp

Follow the installation instructions in the repository README, then restart your MCP client.

Bring FLUX into the tools you already use.
Generate, edit, vary, and browse FLUX and videos from any MCP-compatible client.

Install·Showcase·Tools·Examples·Troubleshooting

TheFLUX MCP serverexposes the full FLUX toolkit — text-to-image, image editing, multi-reference composition, virtual try-on, FLUX 3 video, variations, and history — to any client that speaks theModel Context Protocol. Generate options in parallel, edit attached images through prompts, try garments on a photo, animate stills into clips with audio, and branch into variations from any result you like. No API code, no keys pasted into the conversation.

claude mcp add --transport http FLUX https://mcp.bfl.ai

A browser opens on first use for OAuth. Tokens refresh automatically.

One-click:Add to Cursor— opens Cursor with the FLUX server pre-filled.

{ "mcpServers": { "FLUX": { "url": "https://mcp.bfl.ai" } } }
codex mcp add flux --url https://mcp.bfl.ai codex mcp login flux
[mcp_servers.flux] url = "https://mcp.bfl.ai"

Edit~/.codeium/windsurf/mcp_config.json(note Windsurf usesserverUrl, noturl):

{ "mcpServers": { "FLUX": { "serverUrl": "https://mcp.bfl.ai" } } }

Reload plugins from the Cascade panel. The first FLUX call opens a browser for sign-in.

For clients that support stdio MCP but don't handle the OAuth flow themselves — for exampleHermes(Nous Research) and similar tools that only accept static bearer tokens:

{ "mcpServers": { "FLUX": { "command": "npx", "args": ["-y", "mcp-remote", "https://mcp.bfl.ai"] } } }

mcp-remoteopens a browser for OAuth, caches tokens to~/.mcp-auth/, and refreshes them automatically.

Generate a batch of options in one prompt

"Generate 4 editorial portrait variants — varied lighting, palette, and mood."

Or just one — when a single hero shot is what you need

"A top-down aerial photograph of shallow desert salt pools, intense direct sunlight."

Browse and reuse your full generation history

"Show me my recent FLUX generations."

Every generation is saved. Tap any tile to edit, vary, or download. Variations branch off any past image in one click.

Your client picks which tool to call based on your prompt — you don't need to invoke them by name.

The full catalog, per-model reference-image limits, the FLUX Tools (vto), and FLUX 3 video are also exposed as thebfl://modelsMCP resource.

generate_videorenders 24fps MP4 clips of 5–20 seconds with synchronized audio, up to 4 in parallel per call. Every request uses one of three modes:

- Prompts are proseFLUX 3 reasons about the prompt and plans the generation before rendering — describe the scene, the motion, and the sound. There is no seed or model parameter on video.
- Keyframesreference a prior result (request_id), an uploaded image, or a public URL. Optional per-keyframe timestamps (in seconds, ascending — set on all keyframes or none) pin exact positions in the clip; withdurationset toauto, the clip runs to the last timestamp (20 seconds max).
- Source videosforv2vare a priorgenerate_videoresult, an attached MP4 up to 50 MB, or a public MP4 URL.
- Format controls.duration: 5–20 seconds orauto(default).aspect_ratio:auto(default),21:9,2:1,16:9,4:3,1:1,3:4, or9:16.resolution:hd(default, 704p-class) orfhd(finished by a video upsampler on a 1080p-class canvas).generate_audio: on by default.
- Drafts are the way to explore.draft: truerenders a fast low-step preview of the exact planned generation (hdonly). Batch cheap drafts, pick the winner, andenhance_videore-renders it at full quality from itsrequest_id.
- Renders take minutes— long clips up to about an hour. The tool returns immediately with a pendingrequest_id; results survive closing the chat and resume automatically.
- Reference-based conditioning(identity and motion references) is not part of the video surface; a dedicatedr2vmode follows later.

Try these in your client once FLUX is connected:

Generate 4 editorial portrait variants — varied lighting, palette, and mood. Use FLUX.2 [pro] at 1440×1792.
A top-down aerial photograph of shallow desert salt pools at golden hour, intense direct sunlight, #FF6B6B and #F5E6D3 mineral deposits, FLUX.2 [max].
[attach an image] Add a camel on the sand. Preserve the rest of the composition exactly.
Generate a movie poster with the title "MIRAGE" in 1970s grindhouse type, high-contrast cyan and orange. Use FLUX.2 [flex].
[attach a selfie] Try this on me — a red Nike Tech Fleece hoodie, oversized fit.
[attach an image] Animate this into a 10-second clip — slow push-in, wind through the palms, distant surf.
Generate 3 draft videos of a paper lantern rising over a night market, each with a different camera move. I'll enhance the best one.
[click Variations on a past image] 4 more like this one, vary the lighting.

- Front-load the subject.Put the most important object, person, or scene first.
- Describe lighting."Soft golden hour light"or"overcast diffused studio light"gives the model useful direction.
- Use hex colors.#FF6B6B (coral pink)is more precise than"pinkish red".
- Quote rendered text.Use exact quoted strings for typography, labels, posters, and signs.
- Avoid negative prompts.FLUX responds to what you describe, not a list of what to avoid.
- Iterate from results.Use Variations for alternatives, or Edit to keep refining a generated image.

For the full FLUX prompting playbook, seeblack-forest-labs/skills.

- Claude Desktop / claude.ai:Settings → Connectors, confirm FLUX shows asConnected. If it failed silently, remove and re-add — make sure pop-ups aren't blocked so the OAuth window can open.
- Claude Code:claude mcp listshould show the server.
- Codex:codex mcp listshould showflux. Start a new Codex session after adding.
- Quick smoke test: ask your client"check my BFL credits".

- Claude.ai / Desktop:Settings → Connectors → toggle FLUX off and on, or clickReconnect.
- Claude Code:/mcpshows status and reauth. Full rebuild:

claude mcp remove FLUX claude mcp add --transport http FLUX https://mcp.bfl.ai
codex mcp remove flux codex mcp add flux --url https://mcp.bfl.ai

- Make sure you have a BFL account atbfl.ai.
- Disconnect and reconnect the connector to redo OAuth.
- Check the selected organization has sufficient credits.
- Ask your client to check your BFL credits to verify the balance.

Large batches, FLUX.2 [max], or complex edits take longer than smaller generations. Visual MCP clients update the image view automatically.

Video renders take minutes — long clips up to about an hour. They return a pending request immediately and resume automatically, even if you close the chat and come back later.

Your MCP client needs permission to upload attached media to BFL. If your client blocks outbound HTTPS from its sandbox, allow*.bfl.aior pass a public URL instead. Video uploads are MP4 only, up to 50 MB.

Disconnect the FLUX connector in your client and reconnect it. The OAuth flow will prompt you to select an organization again.

MCP and Agent Skills solve different problems:

- Docsdocs.bfl.ai
- Pricing
bfl.ai/pricing
- Status
status.bfl.ai
- Black Forest Labs
bfl.ai

AI Video, Image & Audio Generation with over 150 models

Convert photos to LEGO-style brick mosaic previews with AI-powered color quantization. MCP server for Claude, Cursor, and other AI agents.

Hosted remote MCP server for AI image and video generation from one Streamable HTTP endpoint.

a specialised AI text remover for photos and graphics

MCP server for OpenAI GPT image generation and editing

Style-locking AI image engine with a hosted MCP server. Define one master style and generate unlimited matching images.

Image and video understanding and generation

Google AI studio based imageneration MCP with option to extend it to other providers

AI interior design from your agent — restyle rooms, place furniture, and virtually stage spaces from a single photo.

A Model Context Protocol server for AI image generation and editing with Google's Gemini "Nano Banana" image models, via the Interactions API. Generate, edit, and iterate on images directly from Claude Code, Claude Desktop, Cursor, or any MCP-compatible client — with multi-turn editing, search grounding, interleaved storyboards, style-consistent icon sets, and image-from-video.

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.