<picture> <source media="(prefers-color-scheme: dark)" srcset="https://bfl.ai/brand/logotype-white.svg"> <source media="(prefers-color-scheme
. The flux mcp mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 6 defined tools rather than through you.
Everything the assistant can do here goes through one of these:
generate_image — Generate 1–8 images in parallel. Covers text-to-image, edits, multi-reference composition, style transfer, inpainting-style edits, andvto — Virtual try-on — dress a person (or pet) in a garment, hat, sunglasses, shoes, bag, or any wearable from a reference image. Preserves face, hairgenerate_variations — Produce N more images in the same direction as a previous generation (identified by request_id). Defaults to 4, max 8get_history — List recent generations as a thumbnail grid with per-tile Variations / Edit / copy / download actions. Keyset pagination, date filtersget_credits — Return your remaining BFL credit balanceModels — The full catalog, per-model reference-image limits, and the FLUX Tools (vto) are also exposed as the bfl://models MCP resourceBeing a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.
Plenty of developer tooling servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Flux MCP's toolset — generate_image, vto, generate_variations and 3 more — is a fair guide to whether it matches your workflow. It is maintained by black-forest-labs; worth a glance at recent repository activity before you build anything load-bearing on it.
SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.
| Tool | What it does |
|---|---|
| generate_image | Generate **1–8 images in parallel**. Covers text-to-image, edits, multi-reference composition, style transfer, inpainting-style edits, and outpainting — all through prompts. |
| vto | **Virtual try-on** — dress a person (or pet) in a garment, hat, sunglasses, shoes, bag, or any wearable from a reference image. Preserves face, hair, and pose; only the worn item changes. |
| generate_variations | Produce N more images **in the same direction** as a previous generation (identified by request_id). Defaults to 4, max 8. |
| get_history | List recent generations as a **thumbnail grid** with per-tile Variations / Edit / copy / download actions. Keyset pagination, date filters. |
| get_credits | Return your remaining BFL credit balance. |
| Models | The full catalog, per-model reference-image limits, and the FLUX Tools (vto) are also exposed as the bfl://models MCP resource. |
{
"mcpServers": {
"FLUX": {
"serverUrl": "https://mcp.bfl.ai"
}
}
}Configuration as documented by the project. Restart the client after saving.
Kill hallucinated APIs — version-accurate, up-to-date library documentation injected straight into context.
Microsoft's official browser automation server — drive a real browser through the accessibility tree, no screenshots needed.
GitHub's official server — repos, issues, pull requests, Actions and code security, straight from your assistant.
Issue tracking at the speed of conversation — Linear's official hosted server with OAuth and zero install.
Local repository surgery — status, diffs, commits, branches and history for any repo on disk.
Timezone sanity for AI — current time anywhere and correct conversions, without the model doing date math.