Generate images, video and audio, and keep every result organized in a project.
Connects to the Windpaint media platform so Muse can generate images, video and audio from prompts or reference files, run multi step workflows such as product to ad, and keep outputs as assets and takes inside projects. Needs an API key and paid credits.
Try asking Muse: "Make three cozy kitchen product shots of my candle and save the best one to my project."
Source: Found in the official MCP Registry (ai.windpaint/windpaint) · First listed November 21, 2026
Each bar is one check, every 15 minutes. Green means it answered. Last checked 4 h ago.
What Muse can see: You sign in to your own account with it, so Muse can reach what that account allows. Read what it asks for before you agree.
Before it acts: Read what Muse plans to do before you approve it, and remove the app from Muse when you stop using it.
musedirectory.ai is not part of Meta. More about how Muse handles your information
Not in Muse's Connectors list yet, but Muse can still use it. Copy the request below and paste it into Muse. Muse asks before it shares anything with the app's site. Meta does not review apps used this way, so only use ones you trust. We tested this in the Muse app on September 24, 2026: Muse used an app's link directly this way and returned a live answer.
https://mcp.windpaint.ai/mcpNot in Muse's Connectors list yet. Muse can still use it: its page gives you a request to paste into Muse.
Windpaint is a remote MCP server, so any assistant that can add a custom connector by link can use it. Same link, same tools.
In ChatGPT, open Settings, then Connectors (called Apps & Connectors on some accounts).
Under Advanced settings, switch on Developer mode. That is what lets you add a connector by link.
Choose Create, give it a name, paste the link as the MCP server URL, and save. If it needs a sign-in, ChatGPT asks for it here.
Start a chat, open the tools menu, pick the connector, and ask. ChatGPT asks before it runs a tool the first time.
Custom connectors need a paid ChatGPT plan, and on Team, Enterprise and Edu accounts only an admin can add them. Our "Working" label means the server answered us; it cannot tell whether your plan lets you add it. All connectors that work in ChatGPT
In Claude, open Settings, then Connectors.
Choose Add custom connector, give it a name, and paste the link.
If it needs a sign-in, Claude sends you to it. Then turn the connector on in a chat from the tools menu and ask.
Custom connectors are available on paid Claude plans; on Team and Enterprise accounts an admin may need to add them. Our "Working" label means the server answered us; it cannot tell whether your plan lets you add it. All connectors that work in Claude
https://mcp.windpaint.ai/mcpResponse time at the last check: 173ms. Worked in 100% of checks over 30 days.
Screened, no issues found
Screening looks for known threats and hidden instructions at the time of the check, and runs again weekly and whenever the tool list changes. It cannot see the server's code, so only connect what you need and review what Muse asks to do. How screening works.
list_capabilitiesList what Windpaint can do. For each capability: description, output kind, whether a prompt is required and what it means, the input slots (name, accepted asset kinds, min/max count), and the models that implement it with `available`, licence, resolutions, qualities, durations, `list_lorasPlatform LoRAs (styles and looks) that generate and estimate_cost accept in `loras`. Each has a `slug`, a `family` matching a model's `lora_family` in list_capabilities, trigger words added to the prompt, and a default and max scale. Pass `model` (e.g. "z-image-turbo") to see onlestimate_costCredits a generation would cost, without running it. Same arguments as generate. Also validates the arguments and returns the model chosen and output width/height. `credits` is null when that tier has no price, which means it cannot be submitted; otherwise it is `unit_credits` x upload_assetUpload a reference image, start frame, video or audio file and get an asset id to pass as `inputs` ({slot: [asset ids]}; slot names come from list_capabilities). Give exactly one of: `path` (a local file; only when the server runs locally over stdio), `url` (a public http(s) URL generateRun a capability (see list_capabilities). `model` is optional; the capability's first available model, in list_capabilities order, is used. estimate_cost shows which model that is and its price. `inputs` maps slot names to asset ids, e.g. {"images": [id1, id2]} for image.edit or get_jobCurrent status of a generation job: queued, in_progress, completed, failed, nsfw or canceled. Completed jobs list produced assets under `outputs` (each with an asset id and url; also `images`/`video` as shortcuts), plus credits estimated and actually charged. `job_id` is the `reqwait_for_jobWait for a job to finish, polling for up to timeout_s seconds (max 600). Returns the final status, or the latest status with a note if it is still running; call again to keep waiting. `job_id` is the `request_id` returned by generate.download_assetGet a generated (or uploaded) file. `asset` is an asset id or the asset url from a job status. Locally (stdio) the file is saved to `path` (default: current directory, named after the asset id) and the saved path is returned. Remotely (HTTP) nothing is saved: a short-lived signedcancel_jobCancel a job that has not finished. A model call already running is not interrupted, but its result is discarded. Returns the job's status afterwards. `job_id` is the `request_id` returned by generate.list_recent_jobsMost recent generation jobs in one project, newest first (limit 1-200), with status, outputs and credits. The project is `project` if given, else the API key's default; jobs in other projects are not included, so to see everything call list_projects and pass each. Filter by `worklist_assetsAssets in a project, newest first: uploads and generated outputs, with kind, size, dimensions and the job that produced them. Use their ids as inputs to generate.get_balanceThe organization's credits: `available` (spendable now), `held` (reserved by running jobs, already excluded from available), totals `by_source` (plan, top-up, grant), the next expiry, and each credit lot. Jobs are refused when available credits are below their estimate; top-ups hlist_projectsProjects in the caller's organization. Every asset and job belongs to one; when a tool's `project` is omitted the API key's default project (or the organization's default) is used. `project` accepts a project id or slug. Set archived=true to include archived projects alongside accreate_projectCreate a project to keep a piece of work's assets and jobs together. Returns it with its id and slug. `kind` says what the project is for (general, film, game, ads, app; default general). It picks the project's icon and which presets, workflows and docs are shown first, and neverupdate_projectChange a project's name, slug, description or kind (general, film, game, ads, app). `project` is its id or slug. Only the fields given are changed; an empty `description` clears it. Returns the updated project.list_itemsItems in a project: named things a piece of work keeps coming back to, of kind character, place, object, style, sequence or set. Each has `id`, `slug`, `name`, `kind` and `starred_take_id`. Filter by `kind`. `project` is its id or slug. Items are addressed by id, slug or `@slug` get_itemOne item of a project. `item` is its id, slug or `@slug`.create_itemCreate an item in a project. `kind` is character, place, object, style, sequence or set. The `slug` (default: derived from `name`) is unique in the project and is how prompts and tools refer to it, as `@slug`. `parent_item_id` makes the item a shot of a sequence item. Pass the itlist_takesTakes of an item, i.e. the generations recorded against it: each with `id`, `status`, `is_starred` and `outputs` (assets with `url`). `item` is its id, slug or `@slug`. New takes are not starred automatically; review the outputs and call star_take on the one to keep.star_takeMark a take as the item's chosen one (the item's `starred_take_id`). `item` is its id, slug or `@slug`; `take_id` comes from list_takes. Returns the take.exportGet the files of starred takes: one entry per output asset, as in download_asset (saved to the current directory over stdio, or a short-lived signed URL over HTTP), tagged with `item` and `take_id`. Give `item` (id, slug or `@slug`) for one item, else every item in the project islist_workflowsReady-made workflows (e.g. text-to-clip, product-to-ad, effect presets): multi-step pipelines built on the capabilities. Each has an `inputs` form (name -> type, label, required, default, options for choices), its `outputs`, the steps it runs, `available` with `unavailable_reasonget_workflowOne workflow by slug, with its input form, outputs, steps, availability and credit estimate.estimate_workflowCredits a workflow run would cost with these inputs, without running it. Validates the inputs against the workflow's form. Media inputs take one asset id from upload_asset or an earlier job, a public https URL or a data: URI. Also returns `available_credits`, the organization's srun_workflowRun a workflow. `inputs` fills its form (see list_workflows): text and choice values as strings, media as one asset id, public https URL or data: URI each. Credits are the sum of its steps; the run reports estimate and actual. With wait=false (default) it returns the queued run wget_runA workflow run: status (queued, running, completed, failed, canceled), each step's status, generation request and outputs, the run's named `outputs`, and credits. wait=true polls up to timeout_s (max 600).list_runsRecent workflow runs, newest first (limit 1-200), optionally for one workflow slug.cancel_runCancel an unfinished workflow run; its pending and running steps and their generation jobs are canceled.https://mcp.windpaint.ai/mcpNot in Muse's Connectors list yet, but Muse can still use it. Paste this into Muse: "Use Windpaint to help me. It is a free service with an MCP server at https://mcp.windpaint.ai/mcp. It needs an API key from Windpaint; ask me to enter it through your secure credential prompt. Ask me before you share anything with it." Muse asks before it shares anything with the app's site. Meta does not review apps used this way, so only use ones you trust. We tested this in the Muse app on September 24, 2026: Muse used an app's link directly this way and returned a live answer.
At the last check (November 21, 2026, 16:30 UTC) the endpoint was working, answering in 173ms. Over the last 7 days it answered 100% of health checks. It is checked every 15 minutes.
It was screened on November 21, 2026 with the result "screened, no issues found". Screening checks the domain against threat feeds and reads the tools for hidden instructions and requests for passwords or card numbers. It cannot see the server's code, so grant only the access you need.
It exposes 28 tools, including list_capabilities, list_loras, estimate_cost, upload_asset. For example, you could ask Muse: "Make three cozy kitchen product shots of my candle and save the best one to my project."
This listing was added from public sources (Found in the official MCP Registry (ai.windpaint/windpaint)). If you build Windpaint, claim it to correct the details and get your badge.
Paste this on your site or README. It always shows the latest check.
<a href="https://musedirectory.ai/connector/windpaint"><img src="https://musedirectory.ai/badge/windpaint.svg" alt="Windpaint on musedirectory.ai" width="236" height="40"></a>