Reka
Understand your videos with Reka AI — search, ask questions, and extract insights.
我該用這個嗎
品質與安全性
根據工具定義與協定合規性的自動化分析。
上下文成本
這是每次將伺服器的工具載入模型上下文時所消耗的約略 token 數量。數量越高，可用於其他工作的注意力就越少。
安裝
一鍵安裝
將以下內容加入你的 `claude_desktop_config.json` 檔案：
{
"mcpServers": {
"mcp": {
"command": "uvx",
"args": [
"reka-mcp"
]
}
}
}可執行的套件
0.1.10stdio遠端端點
https://mcp.reka.ai/mcpstreamable-http它能做什麼
工具清單
工具（17）
🟡upload_video(video_url, name, description, group_id, rationale)
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.
輸入結構描述
{
"type": "object",
"properties": {
"video_url": {
"title": "Video Url",
"type": "string"
},
"name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Name"
},
"description": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Description"
},
"group_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Group Id"
},
"rationale": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Rationale"
}
},
"required": [
"video_url"
],
"title": "upload_videoArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "upload_videoOutput"
}🟢list_videos(group_id, rationale)
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.
輸入結構描述
{
"type": "object",
"properties": {
"group_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Group Id"
},
"rationale": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Rationale"
}
},
"title": "list_videosArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "list_videosOutput"
}🟢get_video(video_id, rationale)
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.
輸入結構描述
{
"type": "object",
"properties": {
"video_id": {
"title": "Video Id",
"type": "string"
},
"rationale": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Rationale"
}
},
"required": [
"video_id"
],
"title": "get_videoArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "get_videoOutput"
}🔴update_video(video_id, name, title, description, group_id, ...)
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.
輸入結構描述
{
"type": "object",
"properties": {
"video_id": {
"title": "Video Id",
"type": "string"
},
"name": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Name"
},
"title": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Title"
},
"description": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Description"
},
"group_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Group Id"
},
"move_group": {
"default": false,
"title": "Move Group",
"type": "boolean"
},
"rationale": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Rationale"
}
},
"required": [
"video_id"
],
"title": "update_videoArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "update_videoOutput"
}🔴delete_video(video_id, rationale)
Permanently delete a video and all its indexed data (transcript, captions, embeddings, etc.). This cannot be undone.
輸入結構描述
{
"type": "object",
"properties": {
"video_id": {
"title": "Video Id",
"type": "string"
},
"rationale": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Rationale"
}
},
"required": [
"video_id"
],
"title": "delete_videoArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "delete_videoOutput"
}🟡create_group(name, rationale)
Create a new video group. Groups organize videos into collections. Returns the new group's ID and name.
輸入結構描述
{
"type": "object",
"properties": {
"name": {
"title": "Name",
"type": "string"
},
"rationale": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Rationale"
}
},
"required": [
"name"
],
"title": "create_groupArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "create_groupOutput"
}🟢list_groups(rationale)
List all video groups. Use list_videos with a group_id to see videos in a specific group.
輸入結構描述
{
"type": "object",
"properties": {
"rationale": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Rationale"
}
},
"title": "list_groupsArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "list_groupsOutput"
}🔴delete_group(group_id, rationale)
Delete a video group. Videos in the group are not deleted — they are simply removed from the group.
輸入結構描述
{
"type": "object",
"properties": {
"group_id": {
"title": "Group Id",
"type": "string"
},
"rationale": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Rationale"
}
},
"required": [
"group_id"
],
"title": "delete_groupArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "delete_groupOutput"
}🟢index_video(video_id, pipeline, scene_detection, rationale)
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. Pipelines: - search_only: transcription + captions + embeddings (enables search_videos) - qa_only: transcription + captions (enables ask_video) - full: transcription + captions + embeddings (enables all tools) Scene detection is enabled by default and produces scene boundaries for get_scenes. Pass scene_detection=False to skip it. Prerequisites: if using video_id, the video must be in 'uploaded' status. Use get_video to check status before calling this tool.
輸入結構描述
{
"type": "object",
"properties": {
"video_id": {
"title": "Video Id",
"type": "string"
},
"pipeline": {
"default": "search_only",
"enum": [
"search_only",
"qa_only",
"full"
],
"title": "Pipeline",
"type": "string"
},
"scene_detection": {
"default": true,
"title": "Scene Detection",
"type": "boolean"
},
"rationale": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Rationale"
}
},
"required": [
"video_id"
],
"title": "index_video_hostedArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "index_video_hostedOutput"
}🟢search_videos(query, video_ids, group_id, max_results, rationale)
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. This 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. Each 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. Requires search_only or full pipeline.
輸入結構描述
{
"type": "object",
"properties": {
"query": {
"title": "Query",
"type": "string"
},
"video_ids": {
"anyOf": [
{
"items": {
"type": "string"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Video Ids"
},
"group_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Group Id"
},
"max_results": {
"default": 10,
"title": "Max Results",
"type": "integer"
},
"rationale": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Rationale"
}
},
"required": [
"query"
],
"title": "search_videosArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "search_videosOutput"
}🟢ask_video(question, video_id, start, end, videos, ...)
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. BEFORE calling this tool, read the reka://docs/guide resource for recommended workflows. In most cases, you should first: - search_videos to find WHEN something happens, then pass those timestamps here as start/end - segment_video to detect and locate specific objects - get_transcript to read what was said For single-video questions, pass video_id with start/end. For cross-video questions, pass videos — a list of video references with start/end each. For follow-up questions, pass conversation_id from the previous response. You can add start/end to drill into a specific moment while keeping the conversation context. Requires qa_only or full pipeline.
輸入結構描述
{
"type": "object",
"properties": {
"question": {
"title": "Question",
"type": "string"
},
"video_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Video Id"
},
"start": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Start"
},
"end": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "End"
},
"videos": {
"anyOf": [
{
"items": {
"$ref": "#/$defs/VideoContext"
},
"type": "array"
},
{
"type": "null"
}
],
"default": null,
"title": "Videos"
},
"conversation_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Conversation Id"
},
"rationale": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Rationale"
}
},
"required": [
"question"
],
"$defs": {
"VideoContext": {
"properties": {
"video_id": {
"title": "Video Id",
"type": "string"
},
"start": {
"title": "Start",
"type": "number"
},
"end": {
"title": "End",
"type": "number"
}
},
"title": "VideoContext",
"type": "object"
}
},
"title": "ask_videoArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "ask_videoOutput"
}🟢segment_video(video_id, prompts, start, end, threshold, ...)
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. Prompt tips: - Use broad, visual categories: 'animal', 'vehicle', 'person', 'text on screen' - Specific labels ('rabbit', 'Toyota') are less reliable — the detector matches visual patterns, not semantic concepts - Best for confirming whether a category of object appears in a time window, not for precise identification How to pick a time range: - Use search_videos to find WHEN something appears, then pass those timestamps here - Use get_scenes to scan systematically — call segment_video once per scene (scenes typically fit in the 15s window) - Or pass any range you already know Maximum range is 15 seconds per call; for longer spans, make multiple calls with consecutive windows. Does NOT require any feature indexing — works on any uploaded video.
輸入結構描述
{
"type": "object",
"properties": {
"video_id": {
"title": "Video Id",
"type": "string"
},
"prompts": {
"items": {
"type": "string"
},
"title": "Prompts",
"type": "array"
},
"start": {
"title": "Start",
"type": "number"
},
"end": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "End"
},
"threshold": {
"default": 0.5,
"title": "Threshold",
"type": "number"
},
"rationale": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Rationale"
}
},
"required": [
"video_id",
"prompts",
"start"
],
"title": "segment_videoArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "segment_videoOutput"
}🟢get_transcript(video_id, format, start, end, max_results, ...)
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. Use start/end to narrow results for long videos. Requires the transcript feature to be indexed.
輸入結構描述
{
"type": "object",
"properties": {
"video_id": {
"title": "Video Id",
"type": "string"
},
"format": {
"default": "text",
"enum": [
"text",
"segments",
"words"
],
"title": "Format",
"type": "string"
},
"start": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Start"
},
"end": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "End"
},
"max_results": {
"default": 100,
"title": "Max Results",
"type": "integer"
},
"max_chars": {
"default": 10000,
"title": "Max Chars",
"type": "integer"
},
"rationale": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Rationale"
}
},
"required": [
"video_id"
],
"title": "get_transcriptArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "get_transcriptOutput"
}🟢get_captions(video_id, start, end, max_results, rationale)
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. Use start/end to narrow results. Requires the captions feature (qa_only or full pipeline).
輸入結構描述
{
"type": "object",
"properties": {
"video_id": {
"title": "Video Id",
"type": "string"
},
"start": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "Start"
},
"end": {
"anyOf": [
{
"type": "number"
},
{
"type": "null"
}
],
"default": null,
"title": "End"
},
"max_results": {
"default": 50,
"title": "Max Results",
"type": "integer"
},
"rationale": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Rationale"
}
},
"required": [
"video_id"
],
"title": "get_captionsArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "get_captionsOutput"
}🟢get_scenes(video_id, max_results, rationale)
Get 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 for per-scene contextual analysis - segment_video to detect specific objects per scene (scenes typically fit in segment_video's 15s max range) Requires transcript indexed with scene detection (on by default; skipped only if index_video was called with scene_detection=False).
輸入結構描述
{
"type": "object",
"properties": {
"video_id": {
"title": "Video Id",
"type": "string"
},
"max_results": {
"default": 200,
"title": "Max Results",
"type": "integer"
},
"rationale": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Rationale"
}
},
"required": [
"video_id"
],
"title": "get_scenesArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "get_scenesOutput"
}🟢get_feature_catalog(rationale)
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.
輸入結構描述
{
"type": "object",
"properties": {
"rationale": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Rationale"
}
},
"title": "get_feature_catalogArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "get_feature_catalogOutput"
}🟢summarize_video(video_id, rationale)
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.
輸入結構描述
{
"type": "object",
"properties": {
"video_id": {
"title": "Video Id",
"type": "string"
},
"rationale": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"default": null,
"title": "Rationale"
}
},
"required": [
"video_id"
],
"title": "summarize_videoArguments"
}輸出結構描述
{
"type": "object",
"properties": {
"result": {
"title": "Result",
"type": "string"
}
},
"required": [
"result"
],
"title": "summarize_videoOutput"
}社群
證據