Frame.io MCP. Manage video assets and review feedback from your chat.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
Frame.io MCP Server lets you manage video assets and feedback directly from your AI client. List projects, retrieve asset metadata, and add time-coded comments without leaving your chat.
It's built for post-production teams that need a single source of truth for review cycles.
What your AI agents can do
Add comment
Posts a new, time-coded comment directly onto a specified video asset.
Get asset details
Retrieves the full metadata for a specific media asset.
Get my profile
Gets the current user's profile information on Frame.io.
Retrieves a list of projects belonging to a specific team, including key metadata.
Fetches full metadata for a single project, giving context on ownership and status.
Allows you to list files or folders within a project and retrieve detailed metadata for any specific media asset.
Retrieves all existing comments on an asset, and allows you to post new time-coded feedback directly.
Lists the unique links used to share media with external stakeholders for review.
Retrieves a list of all team members and people who have access to the project.
Lists folders and subfolders, helping you organize or find specific assets within the project structure.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
Frame.io MCP Server: 12 Tools for Video Workflow
Use these 12 tools to list, retrieve, and modify data for projects, assets, and comments within Frame.io.
019d759eadd comment
Posts a new, time-coded comment directly onto a specified video asset.
019d759eget asset details
Retrieves the full metadata for a specific media asset.
019d759eget my profile
Gets the current user's profile information on Frame.io.
019d759eget project details
Fetches comprehensive metadata about a given project.
019d759elist accounts
Lists all billing accounts associated with the user's Frame.io account.
019d759elist asset comments
Retrieves a list of comments left on a specific asset.
019d759elist assets
Lists media files or folder contents within a project scope.
019d759elist collaborators
Retrieves a list of all team members collaborating on a project.
019d759elist folders
Lists all folders and subfolders contained within a project's directory structure.
019d759elist projects
Lists all projects that belong to a specified team.
019d759elist review links
Lists the unique links used to share the project with external reviewers.
019d759elist teams
Lists all teams the user belongs to within Frame.io.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with Frame.io, then connect any of our 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
What you can do with this MCP connector
You're hooking up Frame.io to your AI client. This server lets your agent handle your video assets and feedback without you leaving your chat. You'll list projects, grab asset metadata, and drop time-coded comments right from the conversation. It's built for post-production crews who need one place for all their review cycles.
list_teams lets you see every team you belong to within Frame.io. list_projects then lists all projects attached to a specific team. You can also get get_project_details to pull comprehensive metadata on any single project, telling you about its ownership and status.
Need to manage assets? You've got list_assets to list all the media files or folder contents inside a project. You can also list_folders to see all the folders and subfolders in a project's directory. To get the deep details on any specific piece of media, run get_asset_details.
For feedback, you can list_asset_comments to pull a list of comments already left on an asset, and you't have to stop there; add_comment lets you post new, time-coded feedback directly onto that asset.
Want to know who's involved? list_collaborators retrieves a list of everyone—team members and other people—who have access to the project. You can also list_review_links to see the unique links you use to share the media with external reviewers. Finally, get_my_profile just grabs your current user profile information on Frame.io.
How Frame.io MCP Works
- 1 Subscribe to the Frame.io MCP Server on Vinkius Marketplace and enter your Personal Access Token.
- 2 Ask your AI agent to perform an action, like 'Show me the latest feedback on the 'Product Launch' video.'
- 3 The agent calls the necessary tool (e.g.,
list_asset_comments), fetches the data, and presents the structured feedback or project overview in plain text.
The bottom line is that your AI client runs the necessary Frame.io API calls in the background, letting you talk to your video assets instead of clicking through a dashboard.
Who Is Frame.io MCP For?
This is for post-production managers and creative directors who are tired of jumping between the Frame.io web UI and Slack just to track status. You need a single place to manage assets, review links, and feedback threads without leaving your primary chat interface.
Checks for new comments or updates project statuses instantly by asking the agent, eliminating the need to open the platform and manually check the 'Comments' tab.
Gets a real-time overview of project progress and review links across multiple teams by querying the agent, instead of having to check multiple dashboards.
Automates the retrieval of asset metadata and feedback threads for audit reports, saving hours of manual data compilation.
What Changes When You Connect
- You check for new comments or update project statuses instantly. Instead of opening Frame.io and navigating to the 'Comments' tab, just ask your agent to run
list_asset_comments. - You get a real-time project overview across teams. Running
list_projectsgives you status and ownership data without having to check multiple dashboards. - You automate data gathering for reports. By calling
get_asset_detailsandlist_asset_comments, your agent compiles metadata and feedback threads for audit reports instantly. - You maintain project context. Use
list_collaboratorsto immediately know who is involved in a project, skipping the manual process of checking the team roster. - You track external reviews easily. Running
list_review_linksshows exactly how and when your media is being shared with external stakeholders. - You keep your workflow moving fast. Fetching specific asset details or comments using the agent keeps your post-production flow active without context switching.
Real-World Use Cases
Need to confirm review status for a client video.
The client needs to know if the final video is ready for sign-off. Instead of logging into Frame.io and manually checking the project dashboard, you ask your agent to run list_review_links. The agent finds the links and tells you which external stakeholders have accessed them, giving you immediate status.
Compiling feedback from a massive shoot day.
A shoot day generates hundreds of assets and comments. You prompt your agent: 'What's the status of the 'Marketing Campaign' project?' The agent runs list_projects and then uses list_assets and list_asset_comments to pull all key feedback and metadata into one summary, solving the problem of scattered data.
Need to onboard a new team member into a project.
A project needs more eyes on it. Instead of manually going to the project settings to add users, you ask your agent to run list_collaborators and check the current roster. You get the list of people, confirming who needs to be added, keeping the process fast.
Audit trail for project sign-off.
The legal team needs proof that all assets were reviewed. You ask the agent to get project details using get_project_details, then use list_assets to grab metadata for every file, and finally use list_asset_comments to gather all feedback, creating a comprehensive, auditable record.
The Tradeoffs
Blindly listing all assets
Calling list_assets without providing a project ID or folder scope, hoping to get everything in one go. This results in an API error or a timeout because the system can't handle the massive, unfiltered query.
→
Always scope your request. First, run list_teams to find the team ID, then list_projects to find the specific project ID. Finally, use list_assets with the correct project_id and folder_id to get exactly what you need.
Ignoring time-coded feedback
Treating comments as simple text notes. You just ask for 'feedback on the video'. The agent might return a massive wall of text that doesn't pinpoint the exact moment the issue occurred.
→
Use the list_asset_comments tool. This tool specifically retrieves comments with time-coded markers, letting you tell the agent: 'Show me all comments on 'vid_9876' between 00:30 and 00:45'.
Assuming all assets are visible
Trying to view a file by name without checking permissions. The agent fails because the user lacks access, and you waste time troubleshooting a simple permissions issue.
→
First, run list_collaborators to confirm who has access to the project. If permissions are the issue, ask the agent to get_project_details to verify the overall project status before trying to access assets.
When It Fits, When It Doesn't
Use this MCP Server if your primary job involves managing video assets, tracking creative feedback, or coordinating review cycles. You need to interact with the structured data (metadata, comments, links) without leaving your chat.
Don't use it if you just need to store video files or manage billing accounts—you'd use a dedicated storage service or billing tool instead. If you only need to know who is in the team, list_collaborators is enough. If you need to know what assets are available, you need list_assets combined with list_folders to get the full context.
Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Frame.io. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This server provides 12 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Checking project status means clicking through five different dashboards.
Today, checking a single project's status is a mess. You open Frame.io, click on the project, then check the 'Assets' tab for metadata. Then you switch to the 'Comments' tab to see feedback. If you need to know who reviewed it, you check the 'Team' list, and if you need to know if the client saw it, you have to open a separate 'Review Links' page. It's a full context switch, every single time.
With this MCP server, you simply talk to your agent. You ask: 'What's the status of the 'Campaign' video?' The agent runs `get_project_details`, fetches the metadata, and immediately provides a concise summary of status, ownership, and key feedback—all in one conversation.
Adding feedback using the `add_comment` tool.
Before, if you wanted to approve a cut, you had to open the video, scrub to the exact second (say, 1:15), and type in the comment box. That required precise timing and multiple clicks.
Now, you just tell your agent: 'Add a comment to 'vid_9876' at 1:15: Great work, ready for export.' The agent handles the time-coding and posting, letting you give approvals instantly from your chat.
Common Questions About Frame.io MCP
How do I use the `list_assets` tool to find a specific file? +
The list_assets tool lists files and folders within a defined scope. You must provide the project and folder ID so the agent knows where to look. You can't just ask for a file name; you need the context.
What is the difference between `list_assets` and `list_folders`? +
Both list contents, but list_assets returns actual media files with their metadata. list_folders only lists the directory structure, helping you navigate the project library without getting file data.
Can I use `add_comment` to approve a video cut? +
Yes. You use the add_comment tool and specify the asset ID and the time-coded marker. The agent posts your feedback and approval directly into the project timeline.
Do I need to know the project ID to use `get_project_details`? +
Yes. The get_project_details tool requires the project ID to pull accurate metadata. The agent can help you find this ID first by running list_projects.
How do I check who has access to the project using `list_collaborators`? +
Simply prompt the agent to use list_collaborators. It retrieves the full list of users and roles involved in that project, giving you a complete view of the team.
How do I list all the projects I've worked on using the `list_projects` tool? +
The list_projects tool retrieves all projects associated with your team. You'll need to provide the team ID to get a full list. This helps you quickly identify which projects are active or stalled.
Can I check the metadata for an asset using `get_asset_details` if I only have the asset name? +
No, you must provide the full asset ID to use get_asset_details. The tool requires a unique identifier to pull the complete metadata. If you only have the name, run list_assets first.
What information can I get about the team members using `list_collaborators`? +
The list_collaborators tool lists all users who have access to the project. For each person, it provides their name, role, and current status within the project.
How do I get an Access Token for Frame.io? +
You can generate a Personal Access Token in the Frame.io Developer Portal at https://developer.frame.io.
Can I add comments with a specific timecode using the agent? +
Yes! The 'add_comment' tool accepts an optional 'timestamp' parameter in seconds, allowing you to pin your feedback to a specific moment in the video.
How do I see the assets inside a specific folder? +
Use the 'list_assets' tool and provide the Folder ID as the 'parentId'. The agent will return all files and sub-folders contained within that directory.
Is it possible to list external review links? +
Yes! Use the 'list_review_links' tool and provide the Project ID. The agent will retrieve all active shared links for that project.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Trello
Automate project management via Trello — list boards, manage lists, and inspect or create cards directly from any AI agent.
Quotable API
Access thousands of quotes — audit authors and tags via AI.
PingCode
Agile project management and R&D collaboration platform — manage work items, sprints, and wiki pages via AI.
You might also like
EmailOctopus
Equip your AI agent to manage email campaigns, track contact lists, and monitor reports via the EmailOctopus API.
IQAir
Monitor air quality and weather — audit pollution data and cities via AI.
Snipcart
Connect your headless e-commerce store to your AI. List orders, update fulfillment statuses, and manage customers seamlessly from your environment.