App

Frame.io integrations

Connect Frame.io to any other app, or use it from your AI client over MCP. Frame.io is Adobe's video review and collaboration platform. Automate it with smart dropdowns and instant notifications for comments, uploads, projects and more.

Connects with OAuthadobe.com

What the catalog holds today. Ask for anything missing and your agent reads the API documentation and adds it.

Build solutions, not workarounds.

What do you want to automate with Frame.io?

Ask the assistant

You'll sign in before anything runs. What you typed comes with you.

Connect your AI client

Give your AI client this address.

https://mcp.apiant.ai

One connection does both: ask your client to act in an app once, or have it build an automation that keeps running. Any client that takes a remote MCP server. Nothing to install. Create your free account, then sign in once in your browser.

Set it up in your client
Claude Code

Run this in the directory you want to work in.

claude mcp add --transport http -s project apiant-ai https://mcp.apiant.ai

Start Claude Code there, approve the server, and sign in in the browser page it opens.

Claude Code guide (opens in a new tab)
Claude, web and desktop

Open Customize, then Connectors, then Add custom connector, and paste the address. On Team and Enterprise an owner adds it first.

Setup guide (opens in a new tab)
Cursor

Add the address to your MCP configuration as a server URL. Cursor signs you in in your browser.

Setup guide (opens in a new tab)
Zed

Open Settings, then AI, then MCP Servers, then Add Server, then Add Remote Server.

Setup guide (opens in a new tab)
Codex and the ChatGPT desktop app

Open Settings, then MCP servers, then Add server, and choose Streamable HTTP. From the terminal, Codex takes the address with its own add command and then signs you in.

Setup guide (opens in a new tab)
Any other MCP client

Paste the address where the client asks for a remote MCP server URL, and name the server apiant-ai where it lets you. APIANT's skills reach the client over the same connection.

Setup guide (opens in a new tab)

Pair it

Connect Frame.io with another app

What your agent can do with Frame.io

Triggers and actions 9 triggers · 15 actions

  • Trigger
    Comment Completed

    Triggers when a comment is marked as completed. Shows live data from your projects.

  • Trigger
    Comment Created

    Triggers when a new comment is created.

  • Trigger
    Comment Updated

    Triggers when a comment is updated.

  • Trigger
    File Created

    Triggers when a file is first created, but before it is uploaded and processed.

  • Trigger
    File Deleted

    Triggers when a file is deleted. Note: Only deletion metadata is available, not the original file content.

  • Trigger
    File Ready

    Triggers when a newly uploaded file has been fully processed and is available for preview, comments, sharing, and downloads.

  • Trigger
    File Upload Completed

    Triggers when a file has been fully uploaded to Frame.io and is ready for processing.

  • Trigger
    Metadata Value Updated

    Triggers when a metadata value is updated. Shows live data from your projects. Prioritizes Status field changes (Approved, In Review, etc.) for workflow automation.

  • Trigger
    Project Created

    Triggers when a new project is created. Shows live data from your workspace.

  • Action
    Create Comment

    Creates a new comment on a file.

  • Action
    Create Folder

    Creates a new folder within a project.

  • Action
    Create Project

    Creates a new project within a workspace.

  • Action
    Create Share

    Creates a new share.

  • Action
    Create Version Stack

    Create a new version stack to group related asset versions together.

  • Action
    Create Workspace

    Creates a new workspace within an account.

  • Action
    Custom API Request (SDK)

    Make a custom request to the Frame.io v4 API using the official SDK with guided method selection.

  • Action
    Delete File

    deletes a file, firing the file.deleted webhook.

  • Action
    Show Project Details

    Get detailed information about a specific project.

  • Action
    Show Share

    Returns one share by id.

  • Action
    Show Workspace

    Returns a single workspace's details.

  • Action
    Update Comment

    Updates an existing comment with new text, annotation, or completion status.

  • Action
    Update File Metadata

    sets metadata field values (field_definition_id + value) on one or more file_ids; fires metadata.value.updated.

  • Action
    Update Project

    Updates an existing project name, status, or access restrictions.

  • Action
    Upload File From URL

    Upload a file to Frame.io from a remote URL (like Google Drive, AWS S3, etc.)

Reviews

What our customers say

Questions

Frame.io, answered

Is there a Frame.io MCP server?

APIANT's MCP server at https://mcp.apiant.ai works with Frame.io. Add that address to any AI client that takes a remote MCP server and sign in once in your browser. Your client can then run Frame.io actions on demand, or have APIANT build, test and run automations that use Frame.io. Nothing to install.

What can start an automation from Frame.io?

Any of Frame.io's 9 triggers in the catalog, including Comment Completed, Comment Created, Comment Updated and File Created. Describe the moment in plain language and your agent picks the right one.

What can your agent do in Frame.io?

Any of Frame.io's 15 actions, including Create Comment, Create Folder, Create Project and Create Share. Your agent maps the data both ways and tests every scenario before it ships.

Can I use Frame.io directly from Claude, ChatGPT or Cursor?

Yes. Connect your AI client to APIANT once and it works with Frame.io two ways. Ask it to do something in Frame.io once and it runs that action on the spot. Ask for an automation and your agent builds it, tests every scenario and keeps it running on its own. A one-off action uses your plan's tasks the same way an automation step does.

Do I need to write code against the Frame.io API?

No. APIANT connects to the Frame.io API for you, and you sign in to Frame.io once with OAuth. Describe what you want in plain language and your agent builds it on the Frame.io triggers and actions in the catalog. If you need an endpoint that is not there yet, your agent reads the Frame.io API documentation and adds it.

Which apps can Frame.io connect to?

Any app in the catalog; the list on this page pairs Frame.io with each of them. If the other app is missing, point your agent at its API documentation and it builds the connector.

What happens when something fails?

Your agent works that out for you. It plans the failure paths along with the happy path, then tests every scenario before it ships.

Is there a free plan?

Yes. Every plan includes the agent, including free, and building from your own AI client spends no assistant credits.