How to Connect Vimeo to Gemini via MCP

💡 No install? Use cloud.anythingmcp.com directly. Sign in, click Connectors → Vimeo, paste your credentials, mint an MCP API key and you're done. No Docker, no git clone, no local server.

Vimeo + Gemini

Let your AI work with your Vimeo account: list and search your videos, read details, folders, showcases, comments, captions and transcripts, upload a video from a link and change titles, descriptions and privacy after your confirmation. Uses a personal access token from a Vimeo developer app of your own.

Prerequisites

See the full setup instructions baked into the connector (visible in the in-app store when you select the connector). The required environment variables for this connector are:

VIMEO_ACCESS_TOKEN

Step 1 — Get credentials

1. Sign in at developer.vimeo.com/apps with the Vimeo account the AI should work with and click Create an app. Any name and description will do; choose that only you will access the app, and accept the terms.
2. On the app page open Generate an access token, choose Authenticated (you) and tick the scopes Public, Private, Edit, Upload and Stats. Tick Delete only if you will switch on vimeo_delete_video. Click Generate.
3. Copy the token, which is shown only once, into VIMEO_ACCESS_TOKEN and install the connector.
4. Check the setup with vimeo_get_me: it shows the account, the plan and the upload quota.

The token does not expire. It stops working when you delete it on the app page or delete the app. Scopes cannot be added to an existing token: generate a new one and replace the old one.

What it reads: your videos, newest first or by search over title, description, chapters and tags, with privacy, status, plays and tags; all details of one video; folders and showcases and the videos in them; comments; and captions and subtitles, auto-generated ones included, which the AI can read as a timed transcript. Captions and transcripts work for videos your account owns.

Asks before every change: vimeo_upload_video_from_url adds a video to your account, and vimeo_update_video changes the title, description, language, password or privacy. The AI tells you what will change, and for privacy who will be able to watch, then waits for your yes. Privacy changes apply at once for everyone who has the link.

Uploads from a link: Vimeo fetches the file itself (a pull upload). The link must point straight to the video file, not to a web page, and stay reachable for 24 hours. Vimeo then transcodes the video, and the AI can follow the progress with vimeo_get_video. Uploads count against your plan's storage and weekly quota.

Privacy options: anybody, unlisted (anyone with the link), nobody (only you), password, contacts, Vimeo users, your team, or hidden on vimeo.com and playable only where it is embedded. Free plans cannot use every option; Vimeo answers 400 or 403 then.

Switched off at install: vimeo_delete_video deletes a video for good. To use it, generate a token with the Delete scope and switch the tool on; the AI then asks for an explicit yes for that exact video.

Ids: the id of a video is the number in its vimeo.com link. In the API, folders are called projects and showcases are called albums; the AI handles the difference for you.

Common errors: 401 (error code 8000 or 8003): the token is wrong or was deleted; generate a new one. 403: the token lacks a scope such as Upload or Edit, or your plan does not allow the action. 404: the video, folder or showcase does not exist or belongs to another account. 429: too many requests; the limits depend on your plan, so wait and try again.

The connector does not download video files or handle live events, analytics reports, webhooks, chapters, thumbnails, players or team members.

Step 2 — Install the adapter

curl -fsSL https://raw.githubusercontent.com/HelpCode-ai/anythingmcp/main/docker-compose.quickstart.yml -o docker-compose.yml
printf 'JWT_SECRET=%s\nENCRYPTION_KEY=%s\n' "$(openssl rand -hex 32)" "$(openssl rand -hex 32)" > .env
docker compose up -d

Step 3 — Add the connector in Gemini

Your server URL: in AnythingMCP, open MCP Servers → the server this connector is on, and copy its URL (https://cloud.anythingmcp.com/mcp/…). Use it wherever this guide shows YOUR_SERVER_ID.

Gemini CLI reads MCP servers from ~/.gemini/settings.json (on Windows %USERPROFILE%\.gemini\settings.json). Add:

{
  "mcpServers": {
    "anythingmcp": {
      "httpUrl": "https://cloud.anythingmcp.com/mcp/YOUR_SERVER_ID",
      "headers": { "X-API-Key": "YOUR_MCP_API_KEY" }
    }
  }
}

1. Create an MCP API key in AnythingMCP under MCP Servers → your server → API keys, and paste it in place of YOUR_MCP_API_KEY.
2. Save the file and restart gemini.
3. Run /mcp inside Gemini CLI (or gemini mcp list in your shell): anythingmcp should show as connected.
4. Start prompting: Gemini CLI can now call the Vimeo tools.

Available tools

Example prompts

• "List my ten most recent videos with title, duration and privacy."
• "Read the transcript of our Product Launch 2026 video and summarize it in one paragraph with the three main points."
• "Which videos in the Customer Webinars folder are still public? Make them unlisted, but show me the list first."
• "Upload the video at https://example.com/files/onboarding-2.mp4 as Onboarding Part 2, visible only to me."
• "Summarize the comments on my latest video and tell me which questions came up most."

FAQ

Where does Gemini CLI look for MCP servers? In ~/.gemini/settings.json for your user, or in .gemini/settings.json inside a project. gemini mcp list shows each server and whether it connects.

Next steps

• Connector landing page
• Connect to Claude
• Connect to ChatGPT