Video generation for AI agents
Let an assistant produce a finished, publishable video rather than an asset that still needs editing. Connect over MCP in a minute, or call 65 REST endpoints directly.
Connect in a minute
MCP video generation: one address for Claude, ChatGPT, Grok, Claude Code and Cursor
Add the hosted MCP server to your assistant and sign in with OAuth. It has 44 tools, it is on every plan, and an account's owners and admins can connect it.
ChatGPT and Cursor need a paid plan on their side. Any other MCP client works too.
- Connect your AI assistant.
- Add MakeAIVideo to Claude, ChatGPT, Grok, Claude Code, Cursor or any app that supports MCP with one address. You sign in once; there is no API key to paste.
- Ask in plain English.
- “Check what a 60 second explainer on our new pricing would cost, make it if it is under 300 credits, and send me the link.” It checks the cost before it spends anything.
- It makes the video.
- A finished MP4 with the script, voiceover, scenes, captions and any music, in your library to edit or download.
- And posts it if you ask.
- To the accounts you have connected, now or on a schedule, across 11 platforms.
MCP, API and CLI are included on every plan.
A finished file, not a part
Why an AI video agent finishes the job here
Most tools in this category return one component: a raw clip, a talking head, a voice track. An agent that receives a component cannot finish, because the remaining work is a human in a timeline. One call here returns the composed file, so the workflow completes.
- A composed MP4.
- Script, voiceover, scenes, captions and any music you ask for, in one 1080p file.
- Posting included.
- The same tools post the finished video to your connected accounts on 11 platforms, now or on a schedule.
- Same credits as the app.
- MCP, the API and the CLI are on every plan, with no separate API bill.
Connect an AI assistant
Where do you want to use it?
Paste this address:
https://mcp.makeaivideo.ai Copy addressJust ask it
“Make a 45-second explainer on why bread rises, 9:16, and give me the download link.”
For code, not a person
AI agents for video: built for a caller that is not a person
The things an unattended agent needs to spend safely, recover from a failure and know when a render is done.
estimate_video_costQuote the cost before spending it
estimate_video_cost is free and takes the same arguments as the create tools, so an agent can show a price and get approval before committing. It turns an irreversible spend into a confirmable one, which is the property that makes autonomous use safe at all.
whoami · get_creditsOrient itself for nothing
whoami, get_credits, list_voices, list_characters and list_templates all cost zero credits. An agent can check who it is, what it can afford and what is available without burning budget on exploration.
Idempotency-KeyRetry without paying twice
POST /videos accepts an idempotency key. A retried request returns the original video instead of creating and billing a second one, so a flaky network does not become a double charge.
429 · Retry-AfterPoll without being throttled
Rate limits are tiered by cost rather than applied flat. Reads and status polls are not rate limited; the tighter limits sit on generation itself. An agent watching a render never trips a limit by waiting.
error.code · request_idFail in a way code can branch on
Every response carries a stable envelope with an error code and a request id, so an agent can distinguish a validation problem from an out-of-credits problem without parsing prose.
video.readyGet called instead of waiting
Webhooks, set up through the API, push video.created, video.ready and video.failed to your endpoint, signed with HMAC-SHA256, so a long render does not hold a conversation or a process open.
Install
Start MCP video generation in one line
Point any MCP client at https://mcp.makeaivideo.ai and sign in with OAuth, or run @makeaivideo/mcp locally over stdio. Source for every package is on GitHub, MIT licensed.
Pricing
AI video agent pricing: access comes with every plan
MCP, the REST API and the CLI are on all four plans. An agent's renders draw on the same monthly credits as the app, with no separate API bill. Plans start at $9 a month.
Lite
The cheapest way in, with every video mode included.
$9/month
or $90 a year, 2 months free
450credits a month
About 4 stock-footage videos
or about 1 AI cinematic video
30 seconds each, every month
- Post and schedule to 2 social accounts
- Videos up to 10 minutes
- Every mode, including Talking Avatar and Image to Video
- Full HD 1080p export, no watermark
Solo
For one creator posting every week.
$19/month
or $190 a year, 2 months free
1,000credits a month
About 10 stock-footage videos
or about 2 AI cinematic videos
30 seconds each, every month
- Post and schedule to 4 social accounts
- More than double the credits of Lite
- Videos up to 10 minutes
- Every mode, including Talking Avatar and Image to Video
Plus
Most popularLong-form, your branding and a team of three.
$29/month
or $290 a year, 2 months free
1,600credits a month
About 16 stock-footage videos
or about 3 AI cinematic videos
30 seconds each, every month
- Post and schedule to 6 social accounts
- Stock-footage videos up to 40 minutes
- Brand Kit: your logo as a watermark on every video
- 3 team seats with admin and member roles
Pro
For teams and channels running at volume.
$49/month
or $490 a year, 2 months free
2,800credits a month
About 29 stock-footage videos
or about 6 AI cinematic videos
30 seconds each, every month
- Post and schedule to 10 social accounts
- Lowest price per credit of any plan
- Stock-footage videos up to 40 minutes
- 10 team seats with admin and member roles
7-day free trial for new customers: $0 today, card required, 500 trial credits, and trial videos are capped at 10 seconds of script. Video counts are estimates for 30-second videos, rounded down. Plan credits refresh every billing month and do not roll over.
Every plan includes
- Every way to make a video: prompt, script, talking avatar, image and character swap
- 15 visual styles, captions, music and voices
- Full HD 1080p export, never a watermark
- Post and schedule to 11 platforms
- Video in 24 languages
- API, MCP server and CLI for ChatGPT, Claude or any AI agent
Busy month? Top-up packs from $9: a one-time purchase, and the credits never expire. Compare plans and packs
AI agents for video FAQs
Connecting an assistant, controlling what it spends, and what it gets back.
Something else? Visit the help center
Can ChatGPT or Claude generate video with MakeAIVideo?
Yes. The hosted MCP server at mcp.makeaivideo.ai connects to any MCP client over streamable HTTP with OAuth, so the assistant generates video as a tool call rather than by you pasting an API key into a script.
What does the agent get back, a clip or a finished video?
A finished video. One call returns an MP4 with the script written, the voiceover recorded, scenes generated, captions timed to the audio and music if you ask for it. There is no editing step left for a human, which is what lets an agent workflow complete rather than stall.
How do I stop an agent spending all my credits?
Estimate first. estimate_video_cost is free and returns the exact credit cost before anything is created, and get_credits reports the live balance including in-flight reservations. API keys can also be scoped to read only, which removes the ability to spend entirely.
Is there a local option, or is it hosted only?
Both. The hosted server needs nothing installed. @makeaivideo/mcp on npm runs the same tools locally over stdio for clients that cannot reach an HTTP endpoint.
Does agent access cost extra?
No. MCP and API access are on every plan with no separate rate card, and renders draw on the same monthly credit allowance as the app. Plans start at $9 a month for 450 credits.
Which agent frameworks work with it?
Anything that speaks MCP, including Claude, Claude Code, Grok, ChatGPT and Cursor (both on their own paid plans) and custom clients. Anything that cannot speak MCP can call the REST API directly with a bearer key.