Rendley Mcp
About
Rendley’s MCP server gives your AI client a full video editor. Connect it once, then create and edit video by describing what you want, in the same chat you already work in. The client uses your own footage, your brand kit, and Rendley’s stock and AI tools, and hands back a finis
Details
- Transport
- SSE
Explore
- Connect once and create/edit videos by describing them.
- Drives the hosted Rendley editor in a browser.
- Supports both remote MCP and plain HTTP REST endpoints.
- Authenticates per request with the caller’s own API key or OAuth.
- Self-hostable; single‑tenant per instance.
- Browser launches lazily; concurrent requests reuse separate tabs.
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Rendley McpCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
- Bun >= 1.1 (or Docker)
- A Rendley account to connect with. Clients authenticate per request with their own API key (Settings → API Keys, guide) or OAuth sign-in. The server stores no key of its own.
list_workspaces
List the workspaces the user can access.
list_projects
List the video projects in a workspace, or across all of the user's workspaces if none is given.
create_project
Create a new video project. Defaults to the user's first workspace unless you pass one.
get_project
Get a single project's details, including its name, duration, and when it was last updated.
delete_project
Permanently delete a project and everything in it. This can't be undone.
get_account
Returns an overview of the user's account. Reports their plan and its status, credit balance, how much storage they have used and how much remains, how many projects, workspaces, and transcription minutes they have used against their limits, and whether they have access to the Brand Kit.
edit_video
Create or edit a video through text, using the user's own footage or letting Rendley supply it. Use it for any video creation or editing task.
export_project
Only use this when the user explicitly asks to export or download the video; creating or editing a project does not mean they want it exported. Render a project into a finished video file and wait for it. If the render finishes in time, this returns the download link; if it takes longer than a few minutes, it returns an export id, so call `check_export` with that id to keep waiting. Exporting through this tool needs a paid plan. If the user is on the free plan, tell them to open the project (…
check_export
Continue waiting for an export, using the export id export_project returned when it was still rendering. Waits up to a few minutes and returns the download link when ready, or asks you to call again if it is still going.
get_brandkit
List the workspace's brand kit, the saved brand colors and reusable assets such as logos, images, and music. Use it to find brand colors or assets to use in edit_video.
add_brand_colors
Add one or more brand colors (hex, e.g. #FF5A1F) to the workspace brand kit. The brand kit is a paid feature; if it isn't available on the user's plan, let them know it requires a paid plan.
add_brand_assets
Add assets to the workspace brand kit from the user's local files or from public links. Files return an upload_url each to PUT the bytes to; links are fetched and added right away. The brand kit is a paid feature; if it isn't available on the user's plan, let them know it requires a paid plan.
add_files
Add the user's own local or attached files to a project so edit_video can use them.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"rendley mcp": {
"rendley-mcp": {
"command": "bun",
"args": [
"dev",
"#",
"http://localhost:8787"
]
}
}
}
}McpServers
{
"rendley-mcp": {
"command": "bun",
"args": [
"dev",
"#",
"http://localhost:8787"
]
}
}The MCP server for Rendley. It gives an AI assistant a full video editor: connect it once, then create and edit video by describing what you want, in the same chat you already work in. Under the hood it drives the hosted Rendley editor in a browser and calls the hosted Rendley API on your behalf:
- Editor: https://app.rendley.com
- API: https://api.rendley.com/v1
The same agent is also reachable over plain HTTP (POST /v1/agent) for backends that don't speak MCP. See REST example.
There are two ways to use it:
1. Use the hosted server at https://mcp.rendley.com/mcp. Nothing to run. See Connect a client.
2. Self-host this server against the hosted Rendley API. See Self-host the server.
📖 Full documentation, with step-by-step setup guides and screenshots: docs.rendley.com/mcp
---
Connect a client
Any client that speaks remote MCP can connect. Point it at the endpoint and authenticate by signing in or with an API key:
https://mcp.rendley.com/mcp
- Sign in with Rendley (recommended): the client opens a Rendley sign-in tab and you approve access. Nothing to copy, and you can revoke it later.
- API key: the client sends an Authorization: Bearer YOUR_RENDLEY_API_KEY header. Create one at Settings → API Keys; see Get an API key.
Most clients accept a JSON config like this:
{
"mcpServers": {
"rendley": {
"url": "https://mcp.rendley.com/mcp",
"headers": { "Authorization": "Bearer YOUR_RENDLEY_API_KEY" }
}
}
}
For sign-in, drop the headers block and let the client run the browser flow.
The docs have illustrated, per-client walkthroughs:
- Claude: desktop, web, and Claude Code.
- Codex: the Codex desktop app and CLI.
- Other clients: any other client that speaks remote MCP, plus the mcp-remote bridge for local-only clients.
For Claude Code specifically:
claude mcp add --transport http rendley https://mcp.rendley.com/mcp \
--header "Authorization: Bearer YOUR_RENDLEY_API_KEY"
Try it
Ask the client what it can do, then try a simple request:
> What can Rendley do here?
> List my projects.
If it lists the Rendley tools and your projects, you're connected. From there, describe the video you want and the assistant creates a project, builds the edit, and returns a link.
---
Self-host the server
This repo is the MCP server only; it does not run the full Rendley stack locally. It talks to the hosted Rendley API and editor. When you self-host, point clients at your own https://<host>/mcp instead of https://mcp.rendley.com/mcp.
Requirements
- Bun >= 1.1 (or Docker)
- A Rendley account to connect with. Clients authenticate per request with their own API key (Settings → API Keys, guide) or OAuth sign-in. The server stores no key of its own.
Run locally
git clone https://github.com/rendleyhq/rendley-mcp.git
cd rendley-mcp
bun install
bun dev # http://localhost:8787
API_BASE_URL and APP_BASE_URL default to the hosted Rendley API and editor, so the server boots out of the box with no .env at all; copy .env.example only to point at a different stack. The server holds no credentials of its own: every request authenticates with the caller's own API key or OAuth token.
By default the server drives the editor with a local Chrome (BROWSER_MODE=local), so no extra infrastructure is needed. bun install downloads a bundled Chromium; with USE_CHROME_CHANNEL=true it prefers your installed Google Chrome and falls back to the bundled browser. Set HEADLESS=false to watch the editor in a visible window, and CPU_ONLY=true on machines without a usable GPU.
Verify it's up:
```bash
curl http://localhost:8787/health
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
