New: AI voiceover + auto-captions - script to captioned video in one API call. Read the announcement

LogoRenderly

Model Context Protocol

Ask your AI agent for a video. In whatever you already use.

Renderly runs a hosted MCP server. Point your AI client at one URL and it can render finished video from the templates you have already built - reading the fields, filling them in, checking the result, and only then spending a credit.

5 free credits · no card · hosted MCP, nothing to install

The whole integration, for most clients
{
  "mcpServers": {
    "renderly": {
      "url": "https://renderly.video/api/mcp"
    }
  }
}
Key names differ per client. Each page below carries the exact block that client wants.

Pick your client

12 clients, each with the setup it actually wants - the right file, the right key names, and the auth that works rather than the auth that looks like it should.

The free preview loop

Your agent can check its work before you pay for it

An agent filling in a template will get something wrong - a mistyped variable name, a headline too long for its line. Renderly gives it a way to find out for nothing. A preview takes the same arguments as a real render and resolves them exactly the same way, but produces no video and costs no credits.

  1. Preview0 credits
  2. Fix, preview again0 credits
  3. Once more0 credits
  4. Rendercredits charged

It can look at the frames

Append ?mode=grid and the preview page draws a labelled contact sheet spanning the whole video, as ordinary images. Any agent that can open a page and screenshot it can then see a collided caption or a wrong colour - the failures no validator catches.

?mode=grid

Or one exact moment

Append ?frame=N to check a specific instant, where N is the second you care about multiplied by the frame rate. The page publishes its own rate, so the agent works it out rather than guessing from the nearest tile on the grid.

?frame=N

And fix it in place

Pass the previewId back with corrected values and the same preview updates. The link never changes, so the agent reloads and looks again. A revision counter goes up each time, which is how it knows it is seeing its own latest attempt and not a cached earlier one.

previewId

The warning that saves the most credits. If a variable name does not match, Renderly ignores it silently and renders the authored default instead - so the video comes back looking fine and carrying the wrong text. A preview returns a resolved map of what actually applied plus an UNKNOWN_REPLACEMENT warning, which is how Your agent catches that before it becomes a charge.

The surface

Ten tools Your agent gets

You never call these by hand. Your agent picks the right one from what you asked for. They are listed because it is worth knowing which of them can cost you money - and that seven of the ten cannot.

They are thin wrappers over the same service layer the public REST API uses, so the two surfaces cannot drift apart.

Renderly MCP tools, what each does, and whether it costs credits
ToolWhat it doesCost
renderly_whoamiConnectConfirms the connection and reports your credit balancefree
renderly_list_projectsFindLists your own projects that have something to personalisefree
renderly_list_templatesFindLists the public system templatesfree
renderly_get_variablesFindReads which fields a template or project accepts, and their current valuesfree
renderly_preview_renderCheckResolves your values exactly as a render would, without producing a video - returns a public preview link, what actually applied, a credit quote and any warningsfree
renderly_create_renderRenderRenders the video. Annotated as not read-only, so clients ask before calling itcredits
renderly_get_render_statusTrackPolls the job and returns the finished video URLfree
renderly_generate_captionsAdd AITranscribes audio into word-synced captions you can drop straight onto a layercredits
renderly_generate_voiceoverAdd AITurns a script into narration saved to your media librarycredits
renderly_get_ai_jobAdd AIPolls a captions or voiceover job for its resultfree

Common questions

Before you connect anything

What is the Renderly MCP server?
It is a hosted Model Context Protocol server at https://renderly.video/api/mcp. An AI client connects to it and gains ten tools for working with your Renderly account: finding a template, reading which fields it accepts, previewing a result for free, rendering it, and polling until the video is ready. Nothing runs on your machine.
Which AI clients can connect to it?
Any client that speaks remote MCP over Streamable HTTP. We publish a page per client because the setup differs - one wants a command, another a JSON file with its own key names, a third only a dialog in its settings. The server is identical in every case.
Does connecting an AI agent cost more than rendering myself?
No. A render costs the same credits whoever asks for it: roughly one credit per minute of 1080p video, rounded up to the nearest half credit. Previews are free and unlimited, and seven of the ten tools cannot charge you at all.
Can an agent see the video it made, or only read data about it?
It can see it. A free preview returns a public link, and adding ?mode=grid draws a labelled contact sheet of frames as ordinary images. An agent that can open a page and screenshot it can look at the result and describe what is wrong before any credit is spent.
Does my AI agent get access to my whole Renderly account?
It acts as your account and no further: your templates, your projects, your credits. It cannot see another user's library. Renders draw from your balance, and the render tool is marked as not read-only so clients ask you to confirm before it runs.

Let your agent render the next one

Build a template once, then describe what you want. Previews are free, so the first thing you spend a credit on is a video you have already seen.