Reka is an MCP server with 17 tools an agent can call, among them ask_video, create_group, delete_group. It answers at https://mcp.reka.ai/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 10 of 10 times since 4 September 2026; the last check, on 17 October 2026, succeeded.
Understand your videos with Reka AI — search, ask questions, and extract insights.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
ask_video | 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. Inputs: question, video_id, start, end, videos, conversation_id |
create_group | Create a new video group. Groups organize videos into collections. Returns the new group's ID and name. Inputs: name, rationale |
delete_group | Delete a video group. Videos in the group are not deleted — they are simply removed from the group. Inputs: group_id, rationale |
delete_video | Permanently delete a video and all its indexed data (transcript, captions, embeddings, etc.). This cannot be undone. Inputs: video_id, rationale |
get_captions | 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 feat Inputs: video_id, start, end, max_results, rationale |
get_feature_catalog | 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. Inputs: rationale |
get_scenes | 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 Inputs: video_id, max_results, rationale |
get_transcript | 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. Inputs: video_id, format, start, end, max_results, max_chars |
get_video | 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 Inputs: video_id, rationale |
index_video | 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_on Inputs: video_id, pipeline, scene_detection, rationale |
list_groups | List all video groups. Use list_videos with a group_id to see videos in a specific group. Inputs: rationale |
list_videos | 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) — fe Inputs: group_id, rationale |
search_videos | 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 Inputs: query, video_ids, group_id, max_results, rationale |
segment_video | 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 scr Inputs: video_id, prompts, start, end, threshold, rationale |
summarize_video | 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 in Inputs: video_id, rationale |
update_video | 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. Inputs: video_id, name, title, description, group_id, move_group |
upload_video | 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 inde Inputs: video_url, name, description, group_id, rationale |
Every block below points at https://mcp.reka.ai/mcp. Pick your client and copy.
claude mcp add --transport http reka https://mcp.reka.ai/mcp
{
"mcpServers": {
"reka": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://mcp.reka.ai/mcp"]
}
}
}{
"mcpServers": {
"reka": {
"url": "https://mcp.reka.ai/mcp"
}
}
}{
"servers": {
"reka": {
"type": "http",
"url": "https://mcp.reka.ai/mcp"
}
}
}{
"context_servers": {
"reka": {
"url": "https://mcp.reka.ai/mcp"
}
}
}{
"mcpServers": {
"reka": {
"serverUrl": "https://mcp.reka.ai/mcp"
}
}
}{
"mcpServers": {
"reka": {
"url": "https://mcp.reka.ai/mcp"
}
}
}name: Reka
version: 0.0.1
schema: v1
mcpServers:
- name: Reka
type: streamable-http
url: https://mcp.reka.ai/mcp{
"mcpServers": {
"reka": {
"httpUrl": "https://mcp.reka.ai/mcp"
}
}
}{
"mcpServers": {
"reka": {
"type": "http",
"url": "https://mcp.reka.ai/mcp"
}
}
}{
"mcpServers": {
"reka": {
"url": "https://mcp.reka.ai/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fmcp.reka.ai%2Fmcp&type=streamable_http&id=reka&name=Reka
It answered our last check on 17 October 2026 in 134 ms. Over 10 checks since 4 September 2026 it answered 10. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by reka.ai and served from mcp.reka.ai, the vendor's own domain: https://mcp.reka.ai/mcp.
17, as returned by the server's own tools/list on 8 September 2026: ask_video, create_group, delete_group, delete_video, get_captions, get_feature_catalog, get_scenes, get_transcript, and 9 more.
It answered our last check on 17 October 2026 in 134 ms. Over 10 checks since 4 September 2026 it answered 10.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://mcp.reka.ai/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: ai.reka. Endpoint host: mcp.reka.ai. ARD identifier: urn:air:ai.reka:mcp:mcp.
First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.