MCP App Store
by KeenEthics
Jockey by TwelveLabs icon

Jockey by TwelveLabs MCP Server for Claude and ChatGPT

By TwelveLabs, Inc.

Overview

Connect your photo and video library to Claude. Ask Jockey to find any person, place, or moment across your entire photo and video collection. Get answers with grounded citations and playback rendered through the Jockey Interactive Language (JIL). Powered by TwelveLabs' Marengo and Pegasus models.

How to connect

  1. Claude: Open the Jockey by TwelveLabs listing in the Claude connectors directory and choose Connect. Claude listing Jockey by TwelveLabs exposes 12 tools here.
  2. ChatGPT: Open the Jockey by TwelveLabs listing in the ChatGPT app directory and choose Connect. ChatGPT listing Jockey by TwelveLabs exposes 13 tools here.

Tools

jockey_add_media

ChatGPT
Add one or more videos/images to a knowledge store in a single call. Each item in `items provides exactly one of: - source: a media URL the platform fetches server-side — a direct-download link reachable from the public internet, up to 4 GB each. YouTube, TikTok, and Instagram links to one video or post are also accepted; profile, channel, and playlist links are not. Google Drive URLs are not fetched; use an available Drive data connector. Or - asset_id: an asset you already hold (e.g. from a prior add), registered directly into this store, no re-upload. Plus optional asset_type (video/image) and metadata. Prefer one batched call over many single-item calls. If the user's files are only on their own device (no public URL, no existing asset_id), or they want to import from Google Drive, use jockey_request_upload_link instead. Each input is registered as a KS item (a source is first created as an asset, then waited on until it finishes processing) — reported per item via an outcome field (branch on it, not on error prose): - added: registered (item_id set; poll jockey_list_knowledge_store_items with item_ids until ready before querying). - asset_pending: the asset is still being processed and is not yet registered (asset_id set). Retry jockey_add_media with that asset_id after a short wait — an immediate retry may defer again while it is still processing. Expected deferral, not a failure. - registration_pending: the asset reached ready and registration was attempted but did not resolve in time (asset_id set). Retry jockey_add_media with that asset_id NOW — the asset is ready and re-registering is idempotent (usually succeeds immediately). Expected deferral, not a failure. - registration_failed: registration rejected — see error_code / retriable. - asset_failed: the media failed processing (terminal). - rejected: the source could not be turned into an asset. When retriable is true, re-add the same input. Otherwise a re-add of the same URL won't change the result: correct a fixable URL problem (e.g. an expired link) first; an unsupported source or media that could not be retrieved (e.g. private/removed) needs a different source. Each result echoes its input_index (0-based) and source (the URL or asset_id given) so every outcome ties back to the exact input. counts is the authoritative per-outcome tally and summary` a one-line recap. One bad input does not fail the batch. Required scopes: jockey:read, jockey:write, jockey:ingest.

jockey_create_knowledge_store

ChatGPT
Create a new Jockey knowledge store for the authenticated tenant. Accepts a `name (human-readable label) and optional description and metadata; the new KS starts empty. Follow up with jockey_add_media` to add media (videos or images). Required scopes: jockey:read, jockey:write.

jockey_list_artifacts

ChatGPT
List the user's saved pages, newest first, with each page's share_id and title. Use it when they want to see or reopen something they saved earlier, then pass the share_id to jockey_open_artifact. It does not show a page. Required scopes: jockey:read.

jockey_list_filterable_fields

ChatGPT
List the metadata keys a search on one knowledge store can filter by, with each key's value types, operators, and an example value. Read it before setting a search's `metadata_filter or enrichment_filter`: a value must match the key's stored type. A key carried by few items may be missing here and still filter. Required scopes: jockey:read.

jockey_list_knowledge_store_items

ChatGPT
List items in a knowledge store, or fetch specific items by id. Each item comes with its backing asset's descriptive metadata under `asset: title, duration_sec and size_bytes, so you can answer 'what's in this store and how long is each item' from one call, with no per-item follow-up and no grounded query. Omit item_ids to page the store; pass item_ids to fetch just those items — use this to poll an item's status after jockey_add_media until it is ready`. Required scopes: jockey:read.

jockey_list_knowledge_stores

ChatGPT
List the knowledge stores the user can use, or fetch one by id. The list holds the user's own stores and stores shared with them; each store's `access is owned or shared. When presenting the list, show owned and shared stores as separate groups, and don't describe a shared store as the user's own. Omit knowledge_store_id to page the list (page 1-based, page_limit) — use this to discover existing store ids before querying or adding media. Pass knowledge_store_id to fetch just that store (returned as a one-element list); add include_readiness=true` to attach a per-status readiness summary (queued / pending / processing / ready / failed, plus total) so you can tell whether it is ready to query without listing its items. Required scopes: jockey:read.

jockey_open_artifact

ChatGPT
Show a previously saved page in the chat. Pass artifact_id to open a saved HTML page, including one created in Mosaic. Otherwise pass a share_id from the save result or from jockey_list_artifacts, or the page's artifact_url. Each call loads a fresh copy of the page. It does not create or change the page. Required scopes: jockey:read.

jockey_query

ChatGPT
Ask a natural-language question and get a grounded answer with inline citations to the items and video clips it draws from. Use this when the client model must build an explicit downstream deliverable such as custom HTML or JSON, or when the user explicitly asks for text or prose only, even when that output cites playable media. Returns no interactive widget. For multi-turn, pass back the `session_id from a prior response to continue; history is kept server-side per session, so you need not resend earlier turns. For quick, simple semantic visual or audio retrieval, or raw ranked match rows, use jockey_search. If the answer is expected to reference specific clips, moments, or images and the user did not request an explicit downstream or text-only output, use jockey_render_response`.

jockey_record_feedback

ChatGPT
Record a viewer's reaction to a rendered result: a thumbs up/down, an optional written comment, or a dismissal. Invoked by the result widget itself when the viewer interacts with its feedback prompt.

jockey_refresh_artifact_media

ChatGPT
Grant one video on a saved page again. Invoked by the saved-page widget when the video's playback grant is about to expire.

jockey_render_response

ChatGPT
Answer a natural-language question as a native interactive visual for playback or browsing, such as a gallery, comparison, timeline, highlight reel, breakdown, or grouped view. PREFER THIS whenever the answer is expected to reference one or more specific clips, moments, or images. Show them here instead of only describing them in text. This covers ordinary show, play, browse, find, pull up, where does X happen, reel, montage, and gallery requests in any language, including Korean 보여줘 or 틀어줘. It also covers enumerations, summaries, and explanations that draw on specific media. HIGHER-PRIORITY EXCEPTION. Use `jockey_query instead when the user explicitly requests text or prose only, or a downstream deliverable such as custom HTML or JSON, even when it cites playable media. For multi-turn, pass back the session_id from a prior response to continue. intent_hint / title / ks_name tune the rendered layout. Use jockey_search` for quick, simple semantic visual or audio retrieval, or raw ranked match rows.

jockey_add_media

Claude

jockey_create_knowledge_store

Claude

jockey_list_artifacts

Claude

jockey_list_filterable_fields

Claude

jockey_list_knowledge_store_items

Claude

jockey_list_knowledge_stores

Claude

jockey_open_artifact

Claude

jockey_query

Claude

jockey_render_response

Claude

jockey_save_artifact

Claude

Similar Apps

Listed on MCP App Store

Listed on MCP App Store

Add this badge to your site or README. It links to this page.

HTML

<a href="https://mcp-app-store.keenethics-labs.com/app/jockey"><img src="https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg" alt="Listed on MCP App Store" width="220" height="44"></a>

Markdown

[![Listed on MCP App Store](https://mcp-app-store.keenethics-labs.com/badges/listed-on-mcp-app-store.svg)](https://mcp-app-store.keenethics-labs.com/app/jockey)