Kaltura MCP Server

Instructions

Implementation Reference

• src/kaltura_mcp/tools/media.py:83-124 (handler)

  Main handler function that executes the tool: validates entry ID, retrieves the media entry via KalturaClient, handles errors, and returns formatted JSON with comprehensive metadata.

  async def get_media_entry(manager: KalturaClientManager, entry_id: str) -> str:
      """Get detailed information about a specific media entry."""
      if not validate_entry_id(entry_id):
          return json.dumps({"error": "Invalid entry ID format"}, indent=2)
  
      try:
          client = manager.get_client()
          entry: KalturaMediaEntry = client.media.get(entry_id)
      except Exception as e:
          return handle_kaltura_error(e, "get media entry", {"entry_id": entry_id})
  
      return json.dumps(
          {
              "id": entry.id,
              "name": entry.name,
              "description": entry.description,
              "mediaType": safe_serialize_kaltura_field(entry.mediaType),
              "createdAt": datetime.fromtimestamp(entry.createdAt).isoformat()
              if entry.createdAt
              else None,
              "updatedAt": datetime.fromtimestamp(entry.updatedAt).isoformat()
              if entry.updatedAt
              else None,
              "duration": entry.duration,
              "tags": entry.tags,
              "categories": entry.categories,
              "categoriesIds": entry.categoriesIds,
              "thumbnailUrl": entry.thumbnailUrl,
              "downloadUrl": entry.downloadUrl,
              "plays": entry.plays,
              "views": entry.views,
              "lastPlayedAt": datetime.fromtimestamp(entry.lastPlayedAt).isoformat()
              if entry.lastPlayedAt
              else None,
              "width": entry.width,
              "height": entry.height,
              "dataUrl": entry.dataUrl,
              "flavorParamsIds": entry.flavorParamsIds,
              "status": safe_serialize_kaltura_field(entry.status),
          },
          indent=2,
      )

• src/kaltura_mcp/server.py:73-86 (registration)

  Tool registration in MCP server's list_tools(): defines name, detailed usage description, input schema requiring 'entry_id', enabling the tool for LLM calls.

  types.Tool(
      name="get_media_entry",
      description="Get complete metadata for a single video/media file. USE WHEN: You have a specific entry_id and need full details (title, description, duration, tags, thumbnail, status). RETURNS: Complete media metadata including URLs, dimensions, creation date. EXAMPLE: After search finds entry_id='1_abc123', use this to get full video details.",
      inputSchema={
          "type": "object",
          "properties": {
              "entry_id": {
                  "type": "string",
                  "description": "The media entry ID (format: '1_abc123' or '0_xyz789')",
              },
          },
          "required": ["entry_id"],
      },
  ),

• src/kaltura_mcp/server.py:76-85 (schema)

  JSON schema defining tool input: object with required 'entry_id' string parameter.

  inputSchema={
      "type": "object",
      "properties": {
          "entry_id": {
              "type": "string",
              "description": "The media entry ID (format: '1_abc123' or '0_xyz789')",
          },
      },
      "required": ["entry_id"],
  },

• src/kaltura_mcp/tools/__init__.py:21-26 (helper)

  Imports the get_media_entry handler from media.py module, making it available for import from tools package.

  from .media import (
      get_download_url,
      get_media_entry,
      get_thumbnail_url,
      list_media_entries,
  )

• src/kaltura_mcp/tools/__init__.py:47-47 (helper)

  Adds get_media_entry to __all__ for easy import via from tools import get_media_entry.

  "get_media_entry",