What is a Frame.io MCP?
A Frame.io MCP is a server that gives your agents access to data and functionality from Frame.io through a set of callable tools. Your agents can use these tools to list and organize projects, retrieve files and version stacks, pull timecoded review comments, create share links, and more.
Frame.io doesn't offer an MCP server purpose built for Frame.io, but you can use one from a third-party platform, like Merge Agent Handler.
How can I use the Frame.io MCP server?
The use cases naturally depend on the agent you've built, but here are a few common ones:
- Review feedback aggregation: When an editor uploads a new cut to Frame.io, an agent can pull all timecoded comments from the asset and compile them into a structured summary, then post that summary to a Slack channel or project management tool so the team can act on feedback without logging into Frame.io
- Asset delivery tracking: An agent can monitor a Frame.io project for files that have reached a final approval state and automatically generate share links for client delivery, eliminating the manual step of creating and distributing links after sign-off
- Cross-tool project sync: When a new project is created in a tool like Asana or Jira, an agent can automatically create a corresponding Frame.io project and folder structure, keeping production assets organized alongside task tracking from day one
- Post-production reporting: An agent can scan active Frame.io projects for assets with open comments, group them by project and assignee, and generate a weekly status report for production leads without anyone manually checking review queues
What are popular tools for Frame.io's MCP server?
Here are some of the most commonly used tools:
list_projects: retrieves all projects within a workspace, including metadata like creation date and owner. Useful for agents that need to scan active productions or build a cross-project status view
get_file: fetches a single file record including its review status, version information, and associated metadata. Call this when an agent needs full context on an asset before taking a downstream action
list_comments: returns all comments on a file, including timecode positions and commenter details. Good for workflows that aggregate review feedback or detect unresolved notes on a delivery
create_comment: adds a comment to a file at a specified timecode, which agents can use to annotate assets programmatically based on output from another system or analysis step
create_share: generates a share link for a file or project with configurable permissions. Helpful when an agent needs to deliver assets to an external reviewer or client after an approval event is detected
move_file: moves a file to a different folder or project. Use this when an agent needs to reorganize assets based on status changes, such as moving approved files into a delivery folder automatically
What makes Merge Agent Handler's Frame.io MCP server better than alternative Frame.io MCP servers?
Here are just a few reasons to use Merge Agent Handler's Frame.io MCP server over building your own or using another:
- Enterprise-grade security and DLP: Merge Agent Handler includes data loss prevention controls that let you block or redact sensitive fields before they reach an agent. For Frame.io, this means you can prevent client asset URLs, share links, and confidential review notes from being exposed even when the agent has broad read access
- Managed authentication and credentials: Merge stores and refreshes Frame.io credentials on your behalf. You never hand raw OAuth tokens to an agent or deal with token expiry breaking a production workflow
- Real-time observability and audit trail: Every tool call made against Frame.io is logged with a timestamp, tool name, input parameters, and response metadata. You can trace exactly what an agent read, moved, or commented on without building any custom instrumentation
- Tool Packs and controlled access: Tool Packs let you bundle specific Frame.io tools with tools from other connectors into a single scoped MCP endpoint. An agent built for client delivery gets share link creation and file retrieval, but not delete or workspace management tools
How can I start using Merge Agent Handler's Frame.io MCP server?
You can take the following steps:
1. Create or log into your Merge Agent Handler account.
2. Install the Merge CLI by running pipx install merge-api, then run merge configure to link the CLI to your Merge account and merge login to authenticate your session.
3. Register the Agent Handler MCP server with Claude Code by running claude mcp add --transport http agent-handler https://ah-api.merge.dev/mcp. Then open Claude Code and run /mcp to confirm agent-handler appears with a connected status.
4. Select agent-handler from the MCP list. This opens a browser window where you select which integrations to authenticate. Choose Frame.io and complete the auth flow. Merge stores and manages the credentials going forward.
5. Open a Claude Code session and start querying Frame.io data directly. The first time you use a Frame.io tool, a Magic Link may appear to complete connector authentication.
Note: If you want to connect Merge Agent Handler's Frame.io MCP with internal or customer-facing agentic products, you can follow the steps in our docs.
Can employees use Merge to connect their AI tools to Frame.io?
Yes, Agent Handler for Employees lets your employees connect Claude, ChatGPT, Microsoft Copilot, Cursor, and other MCP-compatible AI tools to Frame.io without bypassing IT governance.
Instead of setting up direct connections with personal credentials that IT can't monitor or revoke, each employee authenticates through Agent Handler and gets individual credentials tied to their identity.
IT also provisions access by role or group via SCIM. A video editor, for example, gets Frame.io access to review and annotate cuts, Slack to share feedback with the team, and Google Drive to pull source assets; while a creative director gets Frame.io access to track project approvals, Asana to manage production timelines, and Slack to align stakeholders on delivery milestones.
Every tool call an employee's AI makes to Frame.io is also inspected against your DLP rules and logged to a searchable audit trail, giving security teams full visibility into what data was accessed and by whom.