Fire in da houseTop Tip:Paying $100+ per month for Perplexity, MidJourney, Runway, ChatGPT is crazy - get all your AI tools in one site starting at $15 per month with Galaxy AIFire in da houseCheck it out free

cloudglue-mcp-server

MCP.Pizza Chef: aviaryhq

The CloudGlue MCP Server is an official MCP server that integrates the CloudGlue API with AI assistants like Cursor and Claude Desktop. It transforms video content into structured data optimized for large language models, enabling advanced video understanding and interaction. This server facilitates seamless connection between video data and AI workflows, enhancing real-time context and actionable insights from video collections.

Use This MCP server To

Convert video content into structured data for LLM processing Integrate video understanding into AI assistant workflows Enable real-time video data context for AI models Automate video metadata extraction for search and analysis Enhance video-based customer support with AI insights Streamline video content indexing for knowledge management Facilitate multi-step reasoning on video data with LLMs

README

CloudGlue MCP Server

NPM Version License MCP Discord

Connect CloudGlue to Cursor, Claude Desktop, and other AI assistants to unlock the power of video collection understanding. CloudGlue helps your videos into structured data ready for LLMs.

📖 Resources

  • Model Context Protocol
  • CloudGlue API Docs
  • Terms of Service
  • Privacy Policy
  • Pricing

By using the CloudGlue SDK and/or the MCP server, you agree to the CloudGlue Terms of Service and acknowledge our Privacy Policy.

Setup

1. API Key

First, get a CloudGlue API Key from cloudglue.dev, this will be used to authenticate the MCP server with your CloudGlue account.

2. Configure MCP client

Next, configure your MCP client (e.g. Claude Desktop) to use this MCP server. Most MCP clients store the configuration as JSON, for cloudglue-mcp-server this would look like the following:

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

Replace <YOUR-API-KEY> with the API Key created in step 1. Alternatively instead of the environment variable you could pass in the API key to the server via the --api-key CLI flag.

Local Development Setup

1. API Key

First, get a CloudGlue API Key from cloudglue.dev, this will be used to authenticate the MCP server with your CloudGlue account.

2. Install and build server locally

You can build this server locally via:

npm install
npm run build

3. Configure MCP client

Next, configure your MCP client (such as Cursor) to use this server. Most MCP clients store the configuration as JSON in the following format:

{
  "mcpServers": {
      "cloudglue-mcp-server": {
          "command": "node",
          "args": [
              "/ABSOLUTE/PATH/TO/PARENT/FOLDER/cloudglue-mcp-server/build/index.js",
              "--api-key",
              "<YOUR-API-KEY>"
          ]
      }
  }
}

Tools

The following CloudGlue tools are available to the LLM:

Chat with Videos

  • chat_with_video_collection: Returns a chat completion response from a video collection given a prompt, can be used to search for information in the video collection to quickly answer questions or find videos relevant to a query

Describe and Extract Information from Videos

  • describe_cloudglue_video: Returns detailed description of a video uploaded to CloudGlue.
  • extract_cloudglue_video_entities: Returns detailed entities extracted from a video uploaded to CloudGlue.
  • describe_youtube_video: Returns detailed description of a YouTube video.
  • extract_youtube_video_entities: Returns detailed entities extracted from a YouTube video.

Manage Video Files, Collections and Generated Artifacts

  • get_video_info: Returns information about a video given a cloudglue video url
  • list_videos: Returns metadata about videos that the user has access to
  • list_video_collections: Returns metadata about video collections that the user has access to
  • list_collection_videos: Returns metadata about videos in a given collection
  • get_collection_video_description: Returns detailed description of a video in a given collection
  • get_collection_video_entities: Returns detailed entities extracted from a video in a given collection

Contact

cloudglue-mcp-server FAQ

How do I connect the CloudGlue MCP Server to my AI assistant?
You can connect it by configuring your AI assistant (e.g., Cursor, Claude Desktop) to use the CloudGlue MCP Server endpoint, enabling video data integration.
What types of video data does the CloudGlue MCP Server support?
It supports various video formats and extracts structured metadata suitable for LLM consumption.
Is the CloudGlue MCP Server compatible with multiple LLM providers?
Yes, it works with OpenAI, Claude, Gemini, and other LLM providers supporting MCP.
How does the CloudGlue MCP Server handle privacy and data security?
It adheres to CloudGlue's privacy policy and terms of service, ensuring secure handling of video data.
Can I customize the data extraction process from videos?
Yes, the server allows configuration to tailor metadata extraction to your specific needs.
What are the prerequisites for deploying the CloudGlue MCP Server?
You need access to the CloudGlue API and an MCP-compatible AI assistant or client.
Where can I find documentation for the CloudGlue MCP Server?
Documentation is available at https://docs.cloudglue.dev, including API references and integration guides.
Does the CloudGlue MCP Server support real-time video data processing?
Yes, it supports real-time context feeding to LLMs for dynamic video understanding.