Add Flixly as an app/plugin in ChatGPT, a connector in Claude, or an MCP server in Cursor and other clients. Ask for a video, image, voiceover or other supported media task and it uses a model from the current MCP catalog — on your Flixly credits.
https://www.flixly.ai/api/mcpAdd this in your client's app, plugin, connector or MCP settings. You'll be asked to sign in once.
Pick where you want to use it.
Seven tools rather than one per model — so your client's tool list stays short and new MCP-eligible Flixly models show up automatically.
list_modelsBrowse the current MCP catalog — model ids, credit cost, supported durations, resolutions, aspect ratios and capabilities.
generate_imageText-to-image, or edit and restyle an existing image by passing image_url. The result is shown inline in the chat.
generate_videoText-to-video, or animate a still with image_url. Returns a task id to poll when a render runs long.
generate_audioText-to-speech for narration and voiceover, or a full music track from a description.
run_modelRun a model and task type returned by list_models for specialized work such as first-to-last-frame, reference-to-video, video translation or image-to-3D.
get_generationCollect the result of a generation that was still rendering. Free to call.
get_accountCredit balance, plan, rate limits and usage totals.
Try asking:
Same pricing
MCP generations cost exactly what the REST API and dashboard cost. No surcharge.
Auto refunds
A failed generation returns its credits automatically — you are never charged for a broken render.
Your plan's limits
Rate limits and parallel job limits follow your subscription, shared with the REST API.
Data access and generation history
A connected client can browse model and price metadata, read your credit balance, plan limits and usage totals, submit generations, and poll their status and outputs. It cannot retrieve passwords, payment details, session tokens or API-key values. MCP jobs appear in your Flixly generation history. Input and output media files are hosted for 30 days from upload and then automatically deleted; download files you want to keep. The prompt, model, settings and other history metadata may remain after the media expires.
Do I need an API key?
No. Claude, ChatGPT, Cursor and other remote-MCP clients use a sign-in flow — paste the URL, approve once, done. An API key is only needed for the stdio bridge, which exists for clients that can't reach a remote server.
How do I disconnect?
Remove Flixly from the client's app, plugin or connector settings, then revoke the dedicated credential under Flixly Dashboard → Settings → API keys. Revocation stops future MCP access immediately.
What does it cost?
The same credits as the rest of Flixly — nothing extra for MCP. Ask the model to check list_models before generating and it will tell you the cost first. Failed generations are refunded automatically.
Why did my video come back as a task id?
Video takes 30-300 seconds, which is longer than a single tool call should block. The job is already submitted and paid for; the model calls get_generation with that id to collect it. Ask it to check again rather than regenerating.
Can I use my own images as input?
Yes, as long as they're at a publicly reachable URL. Local file paths can't be read by a remote server. Upload to Flixly, or any public host, and pass the URL as image_url / video_url / audio_url.
Which models are available?
The current MCP-available set is the catalog returned by list_models. It includes eligible image, video, audio and 3D models with an active public execution path and server-authoritative pricing. Availability can change, and some models in the wider Flixly studio may not be exposed through MCP.
What account data can a connected client access?
The granted Flixly scopes let it browse model details and prices, read your credit balance, plan limits and usage totals, submit generations, and poll their results. Tool responses do not expose passwords, payment details, session tokens or API-key values.
Where are MCP generations saved?
They appear in your Flixly generation history like dashboard jobs. Input and output media files are hosted for 30 days from upload and then automatically deleted, so download anything you want to keep. History metadata such as the prompt, model and settings may remain after the media expires.