Reka MCP: search and question your videos from an AI app

Bring Reka video understanding into Claude, ChatGPT or Cursor

1. 1Click Connect Reka free. There's no sign-in, so its tools are ready at once.
2. 2Most tools read or analyze, such as `search_videos` and `get_transcript`. `delete_video` permanently removes a video and its indexed data, so switch it off, along with `delete_group`, unless you want your AI app cleaning up.
3. 3Add ContextGate to your AI app as a connector or MCP server. The steps for each app are on the Works with page.
4. 4Ask your AI app to find when a product appears in one of your videos, then open Activity to see the `search_videos` call.

Search inside your videos

• Upload a video from a URL with `upload_video`, then index it for search and questions with `index_video`.
• Find when and where something happens across your videos with `search_videos`, then ask about that segment with `ask_video`.
• Read what was said with `get_transcript`, or get descriptions of what's on screen with `get_captions`.
• Detect objects in a segment with `segment_video`, with bounding boxes and confidence scores for each frame.

Reka's server has 17 tools; these are some of them.

Protect your video library

• Switch off `delete_video` and `delete_group`; they're hidden from your AI app and refused if called.
• Use a policy to warn or block before `update_video` renames a video or moves it to another group.
• Activity records every Reka call, from uploads to questions.

What you get with Reka and ContextGate

• Your AI apps can use RekaClaude, Cursor, ChatGPT and other AI apps reach Reka through the one ContextGate connection you add to them.
• You choose which tools they can useSwitch off any Reka tool you don't want used. It's hidden from your AI apps and refused if called.
• Every call is checked and recordedYour policies check each call (for example, personal data is hidden and secrets are blocked), and Activity keeps a record of it.

ContextGate sees only the tool calls that go through it, not your AI app's built-in tools or your chats.

Reka tools

Examples of what your AI apps can do in Reka. You'll see the exact list of tools after you connect it.

• upload_videoUpload 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
• list_videosList 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. Eac
• get_videoGet detailed information about a video including upload status, metadata (duration, resolution, fps), and per-feature indexing status. Use this to check if uplo
• update_videoUpdate 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
• delete_videoPermanently delete a video and all its indexed data (transcript, captions, embeddings, etc.). This cannot be undone.
• create_groupCreate a new video group. Groups organize videos into collections. Returns the new group's ID and name.
• list_groupsList all video groups. Use list_videos with a group_id to see videos in a specific group.
• delete_groupDelete a video group. Videos in the group are not deleted — they are simply removed from the group.
• index_videoIndex 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 th
• search_videosFind WHEN and WHERE something happens across your videos. Returns timestamped results ranked by relevance — use these timestamps as start/end in ask_video for f
• ask_videoAsk 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. BEFORE c
• segment_videoDetect objects in a video segment using text prompts. Describe what to look for and get per-frame detections with bounding boxes and confidence scores. Prompt
• get_transcriptGet 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. Use start/end t
• get_captionsGet AI-generated visual descriptions of what happens on screen. Use this to understand the visual content without watching — each caption describes a short segm
• get_scenesGet detected scene boundaries with start/end timestamps. Use this to understand the video's structure, then pass scene timestamps as start/end to: - ask_video f
• get_feature_catalogList available video analysis features with their dependencies and descriptions. Use this to understand what features exist and what pipelines to use with index
• summarize_videoStart 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 ca