Reka

{
  "id": "aix_46a2732fa3",
  "name": "Reka",
  "operator": "(unclaimed - source: registry-official · publisher: ai.reka)",
  "description": "Understand your videos with Reka AI — search, ask questions, and extract insights.",
  "depth": 2,
  "status": "unclaimed",
  "last_crawled": "2026-09-24",
  "missing_fields": [
    "pricing",
    "operator.identity"
  ],
  "skills": [
    "summarize-docs"
  ],
  "protocols": {
    "mcp": "https://mcp.reka.ai/mcp",
    "a2a": null
  },
  "pricing": null,
  "regions": [
    "global"
  ],
  "languages": [
    "en"
  ],
  "reputation": {
    "tasks_completed": null,
    "dispute_rate": null,
    "p95_latency_ms": 483,
    "uptime_30d": 1,
    "onchain_volume_30d_usd": null
  },
  "aix_score": 70,
  "verification": {
    "identity": "none",
    "health": "probe/24h",
    "pricing": "unknown",
    "last_check": "2026-09-24T20:01:22.251Z"
  },
  "pricing_model": "unknown",
  "profile": {
    "mcp_server": "reka-vision",
    "mcp_version": "0.1.10",
    "tool_count": 17,
    "tools": [
      {
        "name": "upload_video",
        "description": "Upload a video from a URL. Returns a video_id. Local file paths are not accepted; upload files outside the MCP server and pass a reachable video_url. The upload runs asynchronously — poll get_video until status is 'uploaded', then call index_video to enable search and analysis."
      },
      {
        "name": "list_videos",
        "description": "List all videos in your account, or filter to a specific group by passing group_id. Shows upload status and which features have been indexed for each video. Each video's 'url' is a short-lived HTTPS presigned URL (expires within hours) — fetch immediately and do not store; call list_videos or get_video again for a fresh URL when needed."
      },
      {
        "name": "get_video",
        "description": "Get detailed information about a video including upload status, metadata (duration, resolution, fps), and per-feature indexing status. Use this to check if upload or indexing is complete. The 'url' field is a short-lived HTTPS presigned URL (expires within hours) — fetch immediately and do not store; call get_video again for a fresh URL when needed."
      },
      {
        "name": "update_video",
        "description": "Update a video's display name, title, description, or move it to a different group. At least one field must be provided. To remove a video from its group, pass group_id as null."
      },
      {
        "name": "delete_video",
        "description": "Permanently delete a video and all its indexed data (transcript, captions, embeddings, etc.). This cannot be undone."
      },
      {
        "name": "create_group",
        "description": "Create a new video group. Groups organize videos into collections. Returns the new group's ID and name."
      },
      {
        "name": "list_groups",
        "description": "List all video groups. Use list_videos with a group_id to see videos in a specific group."
      },
      {
        "name": "delete_group",
        "description": "Delete a video group. Videos in the group are not deleted — they are simply removed from the group."
      },
      {
        "name": "index_video",
        "description": "Index a video for search, QA, or full analysis. Processes the video through a pipeline of AI features. Typically takes 3-7 minutes; longer for long videos or the 'full' pipeline. Times out after 10 minutes by default.\n\nPipelines:\n- search_only: transcription + captions + embeddings (enables search_videos)\n- qa_only: transcription + captions (enables ask_video)\n- full: transcription + captions + embeddings (enables all tools)\n\nScene detection is enabled by default and produces scene boundaries for get_scenes. Pass scene_detection=False to skip it.\n\nPrerequisites: if using video_id, the video mu"
      },
      {
        "name": "search_videos",
        "description": "Find WHEN and WHERE something happens across your videos. Returns timestamped results ranked by relevance — use these timestamps as start/end in ask_video for focused analysis.\n\nThis is the recommended first step for most questions. Instead of asking ask_video about the entire video, search first to narrow down the relevant moments.\n\nEach result's 'video_url' is a short-lived HTTPS presigned URL (expires within hours) — fetch immediately and do not store; call search_videos or get_video again for a fresh URL when needed.\n\nRequires search_only or full pipeline."
      },
      {
        "name": "ask_video",
        "description": "Ask a question about one or more videos with visual analysis. Most effective on focused time ranges — use start/end to specify the segment to analyze.\n\nBEFORE calling this tool, read the reka://docs/guide resource for recommended workflows. In most cases, you should first:\n- search_videos to find WHEN something happens, then pass those timestamps here as start/end\n- segment_video to detect and locate specific objects\n- get_transcript to read what was said\n\nFor single-video questions, pass video_id with start/end. For cross-video questions, pass videos — a list of video references with start/en"
      },
      {
        "name": "segment_video",
        "description": "Detect objects in a video segment using text prompts. Describe what to look for and get per-frame detections with bounding boxes and confidence scores.\n\nPrompt tips:\n- Use broad, visual categories: 'animal', 'vehicle', 'person', 'text on screen'\n- Specific labels ('rabbit', 'Toyota') are less reliable — the detector matches visual patterns, not semantic concepts\n- Best for confirming whether a category of object appears in a time window, not for precise identification\n\nHow to pick a time range:\n- Use search_videos to find WHEN something appears, then pass those timestamps here\n- Use get_scenes"
      },
      {
        "name": "get_transcript",
        "description": "Get the spoken words in a video. Use this instead of ask_video when you need to read what was said — it returns the actual text, not a summary.\n\nUse start/end to narrow results for long videos.\n\nRequires the transcript feature to be indexed."
      },
      {
        "name": "get_captions",
        "description": "Get AI-generated visual descriptions of what happens on screen. Use this to understand the visual content without watching — each caption describes a short segment with timestamps.\n\nUse start/end to narrow results.\n\nRequires the captions feature (qa_only or full pipeline)."
      },
      {
        "name": "get_scenes",
        "description": "Get detected scene boundaries with start/end timestamps. Use this to understand the video's structure, then pass scene timestamps as start/end to:\n- ask_video for per-scene contextual analysis\n- segment_video to detect specific objects per scene (scenes typically fit in segment_video's 15s max range)\n\nRequires transcript indexed with scene detection (on by default; skipped only if index_video was called with scene_detection=False)."
      },
      {
        "name": "get_feature_catalog",
        "description": "List available video analysis features with their dependencies and descriptions. Use this to understand what features exist and what pipelines to use with index_video."
      },
      {
        "name": "summarize_video",
        "description": "Start here. Get a compact overview of a video: metadata, which features are indexed, a transcript preview, and scene count. Use this to decide which tools to call next — then use segment_video to detect specific objects in time ranges of interest."
      }
    ],
    "profiled_at": "2026-09-24T20:01:22.251Z"
  },
  "unreachable": false
}