Kaltura MCP Server

A Model Context Protocol (MCP) server that provides secure, read-only tools for managing Kaltura API operations. This server enables AI assistants to

Remote serverstreamable-httpPython

What is the Kaltura MCP MCP server?

A Model Context Protocol (MCP) server that provides secure, read-only tools for managing Kaltura API operations. This server enables AI assistants to search, discover, and analyze Kaltura media content safely. That is what the kaltura mcp mcp server brings to an AI assistant: the same capability, reachable through the Model Context Protocol rather than a separate app or dashboard.

The short version

  • Media Discovery — Search and browse media entries with advanced filtering
  • Content Analysis — Access captions, transcripts, and attachment content
  • Category Management — Browse and explore content categories
  • Analytics — Retrieve viewing analytics and performance metrics
  • Secure Access — Read-only operations with comprehensive input validation
  • Session Management — Automatic session handling with configurable expiry

The tools it exposes

The server publishes 13 tools. What each one is for:

  • Parameters — entry_id (required)
  • get_analytics — General analytics data for reporting and analysis
  • get_analytics_timeseries — Time-series data optimized for charts
  • get_video_retention — Detailed viewer retention analysis throughout videos
  • get_realtime_metrics — Live analytics updated every ~30 seconds
  • get_quality_metrics — Quality of Experience (QoE) and streaming performance
  • get_geographic_breakdown — Location-based analytics at various granularities
  • list_analytics_capabilities — Discover all available analytics functions
  • Configuration — For remote/hosted deployment, additional environment variables are required:
  • Prompts — The server provides intelligent prompts to guide users through complex workflows:
  • Resources — The server exposes frequently-used data as cached resources:
  • Infrastructure — The Infrastructure tool exposed by this server

Getting it running

Because this one is hosted, setup is mostly authentication — you point your client at the endpoint and approve access. Nothing runs on your machine, so there is no runtime to keep patched.

What it needs from you

Configuration is passed through the environment: KALTURA_REMOTE_SERVER_URL, KALTURA_REMOTE_ACCESS_TOKEN, JWT_SECRET_KEY, SERVER_HOST, OAUTH_CLIENT_ID, OAUTH_CLIENT_SECRET. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

How it compares

Among the cloud and infrastructure options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. Kaltura MCP's toolset — Parameters, get_analytics, get_analytics_timeseries and 10 more — is a fair guide to whether it matches your workflow. It is maintained by zoharbabin; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Kaltura MCP's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Things to watch

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • With 13 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch Kaltura MCP.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
Parametersentry_id (required)
get_analyticsGeneral analytics data for reporting and analysis
get_analytics_timeseriesTime-series data optimized for charts
get_video_retentionDetailed viewer retention analysis throughout videos
get_realtime_metricsLive analytics updated every ~30 seconds
get_quality_metricsQuality of Experience (QoE) and streaming performance
get_geographic_breakdownLocation-based analytics at various granularities
list_analytics_capabilitiesDiscover all available analytics functions
ConfigurationFor remote/hosted deployment, additional environment variables are required:
PromptsThe server provides intelligent prompts to guide users through complex workflows:
ResourcesThe server exposes frequently-used data as cached resources:
InfrastructureThe Infrastructure tool exposed by this server.
EnterpriseThe Enterprise tool exposed by this server.

How to install the Kaltura MCP MCP server

{
  "mcpServers": {
    "kaltura": {
      "command": "uvx",
      "args": ["kaltura-mcp"],
      "env": {
        "KALTURA_REMOTE_SERVER_URL": "your-value",
        "KALTURA_REMOTE_ACCESS_TOKEN": "your-value",
        "JWT_SECRET_KEY": "your-value",
        "SERVER_HOST": "your-value",
        "OAUTH_CLIENT_ID": "your-value",
        "OAUTH_CLIENT_SECRET": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
KALTURA_REMOTE_SERVER_URLEndpoint or connection string the server talks to.Yes
KALTURA_REMOTE_ACCESS_TOKENCredential the server authenticates with.Yes
JWT_SECRET_KEYCredential the server authenticates with.Yes
SERVER_HOSTEndpoint or connection string the server talks to.Optional
OAUTH_CLIENT_IDConfiguration value read at startup.Optional
OAUTH_CLIENT_SECRETCredential the server authenticates with.Yes

Example prompts to try

  • Use Kaltura MCP to Parameters.
  • Use Kaltura MCP to get analytics.
  • Use Kaltura MCP to get analytics timeseries.

Frequently asked questions

It connects Kaltura MCP to MCP-compatible AI assistants such as Claude and Cursor, exposing 13 tools (Parameters, get_analytics, get_analytics_timeseries, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Kaltura MCP directly.