mcp.film / Model Hubs / Imagine MCP
Imagine MCP
One OAuth endpoint onto ImagineArt's video, image and music models — 96 tools, no keys.
What it does
ImagineArt's official remote MCP exposes its whole generation catalogue through a single OAuth endpoint: text-to-video against Sora, Veo, Kling 3, Seedance, Runway, Hailuo, Wan and Luma; stills from Seedream, Flux, Imagen and Midjourney; plus music, upscaling, background removal and two guided pipelines (Ad Studio, Fashion Studio). For a filmmaker-agent it is a one-connection route to several flagship video models that have no first-party MCP, billed against one credit balance instead of six vendor accounts.
Connect
https://mcp.imagine.art
claude mcp add --transport http imagine https://mcp.imagine.art
{
"mcpServers": {
"imagine-art": {
"command": "npx",
"args": [
"-y",
"mcp-remote",
"https://mcp.imagine.art"
]
}
}
}
{
"mcpServers": {
"imagine-art": {
"url": "https://mcp.imagine.art"
}
}
}
Field notes
Announced 15 Sep 2026, so this is a day-one listing — the endpoint is live and serves OAuth protected-resource metadata, but nothing here has been stress-tested across a production week. No free tier: ImagineArt's cheapest plan is Basic at $13/mo for 3,000 credits, and MCP calls draw on the same platform credits as the web app, so an agent on an empty balance gets nothing. The vendor claims 96 tools but publishes no tool list, hence tools_sample is null — run tools/list once connected. ImagineArt's own connect page documents the custom-connector UI rather than a CLI command; the claude mcp add form above is the standard HTTP-transport equivalent for the endpoint its metadata advertises (resource https://mcp.imagine.art/), not a command quoted from the vendor. Hard output ceilings to plan around: stills up to 4K, clips of five or ten seconds depending on the model, music around thirty seconds — this is a shot-generation hub, not a long-form tool. The vendor's own setup blog posts have already 410'd, which tells you something about the documentation's half-life. Broader, better-proven aggregators: fal, replicate, kie-ai.
Also in Model Hubs
Midjourney in an agent — plus Kling, Luma, Hailuo, Hunyuan, Wan, Suno via PiAPI.
Run Veo, Seedance, Kling, Runway, Suno, ElevenLabs, FLUX and more through one local MCP.
Official Runware MCP for image, video, audio, 3D, upscaling, and model search.
Hosted OAuth MCP for 20+ video, image, audio and 3D models, with a credit preview on every call.
One hosted endpoint to search, run and chain 1,000+ image, video and audio models.
Hosted OAuth MCP onto BudgetPixel's image, video, music, SFX and Topaz upscale catalogue.
Pairs well with
Hosted MCP for AKOOL face swap, character swap, image-to-video, TTS and avatar lookup.
Studio MCP for talking avatars, locked recurring characters, and batched output.
Official bitHuman CLI server: build avatar agents from a face image and render WAV-driven talking video locally.