​
Quick Start

First, make sure you have a Cloudglue API key to authenticate with the service.

The Cloudglue MCP server lets you connect AI assistants like Claude Desktop and Cursor to Cloudglue’s video understanding capabilities through the Model Context Protocol.

Using the Cloudglue MCP server, you can bring advanced video analysis, transcription, and extraction features directly into your favorite AI chat applications. This allows your AI assistants to understand, analyze, and extract insights from video content without leaving your workflow - whether you’re looking to transcribe meetings, extract structured data from video clips, or have conversations about video collections.

​
Setup

​
1. Get API Key

Create a Cloudglue API key from cloudglue.dev. This key will authenticate the MCP server with your Cloudglue account.

​
2. Configure MCP Client

Configure your MCP client (Claude Desktop or Cursor) to use the Cloudglue MCP server:

Claude Desktop uses a configuration file to manage MCP servers:

  1. Open the Claude menu on your computer and select “Settings…”
  2. Click on “Developer” in the left-hand bar of the Settings pane
  3. Click on “Edit Config”

This will open your claude_desktop_config.json file (located at ~/Library/Application Support/Claude/claude_desktop_config.json on macOS or %APPDATA%\Claude\claude_desktop_config.json on Windows).

Add the following configuration to the file:

{
  "mcpServers": {
    "cloudglue": {
      "command": "npx",
      "args": [
        "-y",
        "@aviaryhq/cloudglue-mcp-server@latest"
      ],
      "env": {
        "CLOUDGLUE_API_KEY": "<YOUR-API-KEY>"
      }
    }
  }
}

Replace <YOUR-API-KEY> with your Cloudglue API key from step 1.

After updating the configuration, restart Claude Desktop completely.

​
3. Verify Installation

Once configured:

  • In Claude Desktop: You should see a slider icon in the bottom left corner of the input box. Click it to see the available Cloudglue tools.
  • In Cursor: The Agent will automatically detect and use relevant Cloudglue tools when needed.

​
Available Tools

Once configured, your AI assistant can access the following Cloudglue tools:

​
Chat with Videos

  • chat_with_video_collection: Get chat completion responses from your video collections

​
Transcribe and Extract Information

  • transcribe_cloudglue_video: Get rich multimodal transcripts from uploaded videos
  • transcribe_youtube_video: Get detailed descriptions of YouTube videos
  • extract_cloudglue_video_entities: Extract detailed entities from uploaded videos
  • extract_youtube_video_entities: Extract detailed entities from YouTube videos

​
Manage Videos and Collections

  • list_videos: View metadata for all accessible videos
  • get_video_info: Get information about specific videos
  • list_video_collections: View metadata for accessible collections
  • list_collection_videos: View videos in a specific collection

​
Access Rich Data

  • get_collection_rich_transcripts: Get rich transcripts from collection videos
  • get_collection_video_entities: Get extracted entities from collection videos

​
Troubleshooting

If the MCP server isn’t working:

  1. Ensure you have Node.js installed (node --version in terminal)
  2. Verify your API key is correct
  3. Restart the client application completely
  4. Check logs for any error messages

​
Resources