{"id":"com.hookdetector/hookdetector","slug":"com-hookdetector-hookdetector","title":"Hook Detector","description":"Real TikTok and Instagram hooks that already work, in any language, with why each travelled.","version":"2.4.0","publisher":{"kind":"domain","id":"hookdetector.com","label":"hookdetector.com","url":"https://hookdetector.com"},"website":"https://hookdetector.com","repository":"","remotes":[{"type":"streamable-http","url":"https://api.hookdetector.com/mcp","headers":[{"description":"Bearer hd_... API key. Get one free with no signup form: POST https://api.hookdetector.com/v1/accounts, or call the create_account tool without this header and pass api_key on each tool instead.","isSecret":true,"name":"Authorization"}]}],"packages":[],"published":"2026-09-25","updated":"2026-09-25","status":"online","auth":"","latency_ms":923,"checked":"2026-11-19","uptime":100,"checks":3,"tools":[{"name":"create_account","title":"","description":"Create an account and get an API key with free credits. Needs a beta access code\n    (access_code, HD-XXXX-XXXX; case and dashes do not matter): without one the error is\n    403 access_code_required, and a code that does not work is 403 invalid_access_code.\n    Ask for a code with request_access, or at hookdetector.com/access. No key needed for\n    this call. label is an optional note up to 120 ch","read_only":false},{"name":"showcase","title":"","description":"Real hooks this service has delivered, for a wait screen: talking heads only, each\n    hook_id, still_url (a JPEG, no key needed), platform, creator, views and line (the\n    banner on the video, else its opening line). The most viewed first, one per creator,\n    only what is already public on TikTok or Instagram: never a topic, an account or a run.\n    No key needed. Cached 10 minutes. Free. REST:","read_only":false},{"name":"find_hooks","title":"","description":"Start hook research on a topic across TikTok, Instagram and YouTube Shorts (Shorts\n    only, never long-form YouTube; platform \"youtube\"). platforms (since 2026-10-10, any of\n    \"tiktok\", \"instagram\", \"youtube\"; all three when left out) searches and delivers only\n    those: [\"instagram\"] is Instagram reels only.\n\n    What it does: searches both platforms, reads what each clip says and shows, and\n","read_only":false},{"name":"get_run","title":"","description":"A research run: its status, progress, charge and every hook it produced.\n\n    wait_seconds 0 to 50: wait up to that long for the run to finish, returning the\n    moment it is done or failed. Use wait_seconds=50 and call again while status is\n    \"queued\" or \"running\"; a fresh run needs about 3 or 4 such calls. progress has\n    stage, message and updated_at, plus counts once the research reports th","read_only":false},{"name":"list_runs","title":"","description":"Your research runs, newest first, without their results, limit 1 to 100 (default 20)\n    per page. Each run says its kind: \"short\" (find_hooks), \"long\" (find_long_hooks) or\n    \"packaging\" (find_packaging); pass kind to list only one. Returns {\"runs\": [...],\n    \"next_cursor\"}: pass next_cursor back as cursor for the next page; it is null on the\n    last. Same shape as GET /v1/runs. Next step: ope","read_only":false},{"name":"find_long_hooks","title":"","description":"Find long-form hooks: how the YouTube videos that beat their own channel open, on a\n    topic. Long-form YouTube only, never Shorts, TikTok or Instagram (for those: find_hooks).\n\n    What it does: searches YouTube for long-form videos on the topic, keeps only the\n    outliers (a video whose views are at least min_outlier times the median views of its\n    own channel's recent uploads; 2 by default)","read_only":false},{"name":"find_packaging","title":"","description":"Find packaging: the titles and thumbnails that earned the click on a topic, from\n    long-form YouTube videos that beat their own channel.\n\n    What it does: runs the same outlier search as find_long_hooks (long-form YouTube,\n    2023 or later, views at least min_outlier times the channel's usual), then looks at\n    each video's thumbnail beside its title and says what the pair is doing.\n\n    What","read_only":false},{"name":"save_preset","title":"","description":"Save filters under a name for one tab: \"long\", \"packaging\" or \"library\" (the bounds\n    are those of find_packaging's filters; a library preset may also hold min_comments,\n    max_comments, posted_within_days and language). The same name on the same tab replaces\n    it. Start a run from it with preset_id on find_long_hooks or find_packaging. At most 50\n    an account. Same as POST /v1/presets. Fre","read_only":false},{"name":"list_presets","title":"","description":"Your saved filter presets, the newest change first; tab (\"long\", \"packaging\",\n    \"library\") narrows. Same as GET /v1/presets. Free.","read_only":false},{"name":"delete_preset","title":"","description":"Delete one of your presets. Same as DELETE /v1/presets/{preset_id}. Free. Errors:\n    404 preset_not_found.","read_only":false},{"name":"write_titles","title":"","description":"Write 20 to 40 titles for your video, each borrowing the device and structure of one\n    real outlier (a video that beat its own channel): the finds of one of your runs, or the\n    shared index's videos nearest your topic by meaning. Each title: title, chars, first_40\n    (what a phone feed surely shows), device, borrows, and from (the real outlier: video_id,\n    title, channel, multiple, find_id)","read_only":false},{"name":"write_ideas","title":"","description":"Write ideas for new videos: each a title, a thumbnail concept (one visible action)\n    and the words to print, built on one to three real outliers (based_on, each with its\n    video_id, title, multiple, find_id and bend niche when it came from another niche).\n    constraints are rules every idea keeps (said in fits). band (10x, 5x, 2x) is the median\n    multiple of the finds behind the idea, never","read_only":false},{"name":"get_call","title":"","description":"One call of a priced tool (titles and the tools after it): tool, credits, charged,\n    status (pending, done, failed), request and result. Same as GET /v1/calls/{call_id}.\n    Free. Errors: 404 call_not_found.","read_only":false},{"name":"list_calls","title":"","description":"Your calls of priced tools, newest first; tool (\"titles\", ...) narrows. Same as GET\n    /v1/calls. Free.","read_only":false},{"name":"find_similar","title":"","description":"The videos in the shared index nearest one of your finds (find_id from a Packaging or\n    Long form run), nearest first, never the find's own video. Each has distance (0 is the\n    same; measures says how it is computed), its numbers and its multiple over its\n    channel's median. A find not indexed yet is matched by its own words (matched_from).\n    Free. Same as GET /v1/finds/{find_id}/similar. ","read_only":false},{"name":"search_thumbnails","title":"","description":"Thumbnails in the shared index by what the picture shows (q), or like a picture\n    (image_url: read once by the model as subject, action, words and setting, then\n    searched). Each result has matched_by (text or meaning). Free; image reads at most 60\n    an hour. Same as GET /v1/index/thumbnails and POST /v1/index/thumbnails/by-image.","read_only":false},{"name":"score_package","title":"","description":"Score a package against the real outliers on its subject, part by part (title device,\n    length, words on the picture, faces, the words' role, contrast, brightness): each part\n    says how many outliers it matches; pattern_match (0 to 100) is the mean share: how much\n    the package resembles the subject's outliers, never a click-through rate or a prediction\n    (in our test it scored outliers ab","read_only":false},{"name":"preview_package","title":"","description":"Your package in a mock YouTube feed among a run's winners: view home, search, sidebar,\n    phone (marks where a phone cuts the title) or tv; theme dark or light; look normal, grey\n    or blur. Returns png_base64 and mine_at. Free. Same as POST /v1/packaging/preview.","read_only":false},{"name":"make_thumbnails","title":"","description":"Make 2 to 12 thumbnails (default 4): 3 different concepts first, then images (Nano\n    Banana 2.1, 1K or 4K), every printed word read back and checked letter by letter, a face\n    only from your photos or your channel's own thumbnails. Answers at once with call_id and\n    status pending; read it with get_thumbnails until done. 4 credits a delivered 1K image, 12\n    a 4K one, charged only for what ","read_only":false},{"name":"get_thumbnails","title":"","description":"A thumbnails call: status, concepts and every image so far (url signed for 7 days,\n    width, height, words, words_checked, cost_usd). Same as GET /v1/thumbnails/{call_id}. Free.","read_only":false},{"name":"edit_thumbnail","title":"","description":"Edit one thumbnail (an image of your thumbnails call, or a picture you send): op erase,\n    edit, face_swap, text, text_variations, upscale, fix, crop or color. crop and color are\n    free; upscale 12; the rest 4 (a version each for text_variations), charged only for what\n    is delivered. Answers at once; read it with get_thumbnails. Same as POST /v1/thumbnails/edit.","read_only":false},{"name":"recreate_thumbnail","title":"","description":"New thumbnails for your video with a YouTube video's own thumbnail as the layout\n    reference (2 to 4 images, every printed word checked); priced as make_thumbnails. Same as\n    POST /v1/thumbnails/recreate; read it with get_thumbnails.","read_only":false},{"name":"optimize_video","title":"","description":"New packages (4, 8 or 12) for your published video: the original scored first against\n    the real outliers on its subject, then each new package (title, thumbnail with every word\n    checked, what it tests) scored the same way, best first, with vs_original. 10 credits a\n    delivered package. Answers at once; read it with get_optimize. Same as POST /v1/optimize.","read_only":false},{"name":"get_optimize","title":"","description":"An Optimize call: the original's score and every new package so far. Same as GET\n    /v1/optimize/{call_id}. Free.","read_only":false},{"name":"ab_set","title":"","description":"Pack 2 or 3 images of one of your thumbnails, edit or Optimize calls for YouTube\n    Studio's Test and Compare: a zip of A, B, C (1280x720, under 2 MB) and a note of what each\n    tests. Free. Same as POST /v1/ab.","read_only":false},{"name":"get_find","title":"","description":"One result of a long or packaging run with every field: the video, its numbers and\n    the opening or the package analysis. find_id comes from a run's finds (get_run) or from\n    list_kept_finds. Same shape as GET /v1/finds/{find_id}. Free. Errors: 404\n    find_not_found, 422 for an id that is not a UUID.","read_only":false},{"name":"keep_find","title":"","description":"Keep or reject a find (a long-form hook or a package): verdict is \"keep\" (default)\n    or \"reject\", and the last verdict wins. The verdict is the video's on that tab: every\n    find of the same video you have there carries it, so a later run that finds the video\n    again shows it already kept. Kept videos come back from list_kept_finds, across all\n    runs. Returns {\"find_id\", \"verdict\"}. Same as","read_only":false},{"name":"clear_find_decision","title":"","description":"Undo keep_find: the video goes back to having no verdict, on every find of it, and\n    leaves list_kept_finds.\n    Returns {\"find_id\", \"verdict\": null}. Clearing a find with no decision is the same\n    success, so a retry is safe. Same as DELETE /v1/finds/{find_id}/decision. Free.","read_only":false},{"name":"list_finds","title":"","description":"The index: every video your long and packaging runs found, across all runs, one\n    entry a video on each tab (its newest read, with the keep or reject made on the\n    video). Each is a full find object: the title and thumbnail_url as YouTube shows them,\n    views, channel_median_views, outlier (views over the channel's usual) and\n    outlier_score (0 to 100 on one fixed scale, so entries from dif","read_only":false},{"name":"remix_find","title":"","description":"Make it mine, for a long-form opening or a package: write up to n (1 to 5, default\n    3) new ones for your niche that keep one real find's structure. From a long find,\n    `written` holds openings: hook (what the creator says first), then (what the next half\n    minute has to deliver) and kept_structure, built on the find's template and its order\n    of beats. From a packaging find it holds packa","read_only":false},{"name":"list_remixes","title":"","description":"The remixes you paid for from one hook (hook_id) or one find (find_id), newest\n    first, each as its answer held it, with remix_id and created_at. Returns {\"remixes\":\n    [...]}. Free. 404 hook_not_found or find_not_found for one that is not yours. Same as\n    GET /v1/hooks/{hook_id}/remixes and GET /v1/finds/{find_id}/remixes.","read_only":false},{"name":"get_remix","title":"","description":"One remix you paid for (from remix_hook, remix_find or a chat turn), as its answer\n    held it. Free. 404 remix_not_found for one that is not yours. Same as GET\n    /v1/remixes/{remix_id}.","read_only":false},{"name":"list_kept_finds","title":"","description":"The videos you kept with keep_find (long-form hooks and packages), newest decision\n    first: one entry a video on each tab across all runs, or the kept finds of one run_id,\n    limit 1 to 100 (default 100) per page.\n    Returns {\"kept\": [...], \"count\": n on this page, \"next_cursor\"} with full find objects.\n    Same shape as GET /v1/finds/keeps. Free. Errors: 422 for a bad kind, run_id or cursor.","read_only":false},{"name":"export_run","title":"","description":"A finished run's hooks as a file a creator can open: format \"csv\" (default; one row\n    per hook, opens in any spreadsheet, formula-like cells defused with a leading quote),\n    \"json\" (the full hook objects) or \"md\" (Markdown notes, one section per hook).\n\n    Returns {\"filename\", \"content_type\", \"format\", \"content\"}, where content is the whole\n    file as text: write it to filename. The same byt","read_only":false},{"name":"get_hook","title":"","description":"One hook with every field: its opening line, transcript, watch_url and the\n    vertical player_url (null only for an unusable id or a photo post found before\n    2026-09-26; runs deliver single videos only). hook_id comes from get_run. Free.","read_only":false},{"name":"embed_hook","title":"","description":"Official TikTok or Instagram embed HTML for a hook, so the clip plays inside your\n    own page. kind is \"embed\", or \"fallback\" when the creator disabled embedding or the\n    clip is a photo post found before 2026-09-26 (then show thumbnail, which falls back to\n    the hook's still_url, and the transcript). For a plain vertical iframe use the hook's\n    player_url instead. Free.","read_only":false},{"name":"keep_hook","title":"","description":"Keep or reject a hook: verdict is \"keep\" (default) or \"reject\", and the last\n    verdict wins. A reject may say why: reason is off_subject, weak_opening, wrong_language,\n    low_quality, already_have or other, and note (up to 280 characters) your own words.\n    Kept hooks come back from list_keeps, across all runs. Free.","read_only":false},{"name":"clear_decision","title":"","description":"Undo keep_hook: the hook goes back to having no verdict, so it leaves list_keeps and\n    its export row carries none. Returns {\"hook_id\", \"verdict\": null}. Clearing a hook with\n    no decision is the same success, so a retry is safe. Same as DELETE\n    /v1/hooks/{hook_id}/decision. Free. Errors: 404 hook_not_found, 422 for an id that is\n    not a UUID.","read_only":false},{"name":"remix_hook","title":"","description":"Make it mine: write up to n new opening lines (1 to 5, default 3) for your niche\n    that keep a real hook's structure, the device that made it travel, with the subject\n    swapped for yours. hook_id is one of your hooks (from get_run, get_hook or\n    list_keeps); 404 hook_not_found otherwise. Leave mode out: \"intro\" (Write my intro) is\n    remix_find on a long-form find, and is 422 here, before a","read_only":false},{"name":"list_keeps","title":"","description":"The hooks you kept with keep_hook, newest decision first, across all runs or within\n    one run_id, limit 1 to 100 (default 100) per page. Returns {\"kept\": [...], \"count\": n\n    on this page, \"next_cursor\"} with full hook objects; pass next_cursor back as cursor\n    for more. Same shape as GET /v1/keeps. Free. Errors: 422 for a bad run_id or cursor.","read_only":false},{"name":"balance","title":"","description":"Your account and remaining credits right now: account_id, credits, key_prefix and\n    key_id of the key making this call, label, created_at, and that key's scopes,\n    credit_limit and expires_at, and user (the person signed in with Google, or null).\n    Same shape as GET /v1/me. A\n    run needs at least 40 credits and reserves up to 200. For spend, credits held by\n    in-flight runs and daily his","read_only":false},{"name":"delete_account","title":"","description":"Erase your account and everything in it, for good: every API key, run, hook, keep\n    or reject decision, conversation and message. Unspent credits go with it. It cannot\n    be undone.\n\n    confirm must be exactly \"delete my account\", or nothing happens (422\n    confirmation_required). Refused with 409 run_in_flight while a run is queued or\n    running: wait for it with get_run first. Returns {\"de","read_only":false},{"name":"chat","title":"","description":"One conversational turn, for an agent relaying a person's words. It either asks\n    ONE clarifying question (action \"clarify\"), answers about delivered hooks or the tool\n    (action \"answer\", run null, no credits), or starts a research run (action\n    \"research\", with the started run under \"run\"), exactly like POST /v1/chat.\n    Every response has suggestions: 0 to 4 follow-ups, [] for research.\n\n","read_only":false},{"name":"list_conversations","title":"","description":"Your chat conversations, most recently active first, limit 1 to 100 (default 30)\n    per page: conversation_id, title, created_at, updated_at, language, country and\n    messages (the count). Nullable language/country are the saved search picker settings.\n    Returns {\"conversations\": [...], \"next_cursor\"}; pass next_cursor back as cursor for\n    more. Same shape as GET /v1/conversations. Next step","read_only":false},{"name":"get_conversation","title":"","description":"One chat conversation: its newest messages in order (role, content, run_id,\n    created_at), a page of `limit`, with earlier_cursor for the older ones (null when the\n    page reaches the first message), and the runs those messages hold, with their hooks,\n    plus nullable language and country search picker settings. Same shape as GET\n    /v1/conversations/{conversation_id}. Free. Errors: 404 conve","read_only":false},{"name":"usage","title":"","description":"Your credits and what you have spent: credits (balance now), spent_total,\n    reserved_now (credits held by runs still in flight, refunded in part when they\n    finish), runs_total, last_30_days (one entry per UTC day: date, runs, charged) and\n    recent (your 20 newest runs). Same shape as GET /v1/usage. Free.","read_only":false},{"name":"list_keys","title":"","description":"Your API keys and what each may do. keys: key_id, name, prefix, created_at,\n    last_used_at and current (true for the key making this call). access, per key_id:\n    scopes, credit_limit, credits_used, expires_at and expired. scopes: the calling key's.\n    The original signup key has key_id \"original\". The keys themselves are never shown\n    again. Needs admin. Same shape as GET /v1/keys. Free.","read_only":false},{"name":"create_key","title":"","description":"Create another API key on your account, for example one per agent or machine, so\n    you can revoke one without touching the others. name is up to 60 characters.\n\n    Give the key only what it needs. scopes: any of \"read\" (read runs, hooks, keeps,\n    usage), \"write\" (keep, reject, undo, chat), \"research\" (start runs, which spend\n    credits), \"admin\" (manage keys, delete the account); all four wh","read_only":false},{"name":"revoke_key","title":"","description":"Revoke one of your API keys at once: key_id from list_keys, or \"original\" for the\n    signup key. Any key may revoke itself (the result says so, and that key stops working\n    immediately); revoking another needs admin. Never the last active key on the account\n    (409): create another with create_key first.\n\n    If a key leaked, pass key_id \"others\": every key of the account except the one you\n  ","read_only":false},{"name":"request_access","title":"","description":"Ask for the beta access code a new account needs (create_account's access_code).\n    email is where the code is sent; note is optional (who you are, up to 500\n    characters). The owner approves the request and the code is emailed at once; it works\n    once, in any agent or on the web. Returns status pending (waiting for approval) or\n    emailed (sent now). No key needed. Limited to 5 per address ","read_only":false},{"name":"list_access_requests","title":"","description":"Owner only: every access request, newest first, optionally only one status\n    (pending, approved, rejected). Each has request_id, email, note, status, code_id,\n    code_prefix, created_at and decided_at. Never a code. Needs the admin scope and an\n    admin account (403 admin_required otherwise). Free.","read_only":false},{"name":"approve_access_request","title":"","description":"Owner only: approve an access request. Makes a one-use code, marks the request\n    approved and emails the code. The code is in this result once, with emailed true or\n    false; when false, send it yourself or approve again (the unused code is revoked and\n    a new one sent). 409 request_already_decided once its code was used. Free.","read_only":false},{"name":"reject_access_request","title":"","description":"Owner only: reject a pending access request. Nothing is emailed. An approved or\n    rejected request is 409 request_already_decided. Free.","read_only":false},{"name":"list_access_codes","title":"","description":"Owner only: every access code, newest first, with code_id, code_prefix, email,\n    note, source, max_uses, uses, expires_at, revoked_at, created_at and usable. Never the\n    code itself. Free.","read_only":false},{"name":"create_access_code","title":"","description":"Owner only: make an access code to hand out. max_uses 1 to 100000 (default 1),\n    expires_in_days 1 to 365 (optional), note your own. email binds it to one person: then\n    only Google sign-in with that verified email redeems it, never the API or MCP; leave\n    it out for a code that works on every door. The code is in this result only. Free.","read_only":false},{"name":"revoke_access_code","title":"","description":"Owner only: revoke an access code (code_id from list_access_codes). It admits\n    nobody from now on; accounts it already made keep working. 404 access_code_not_found\n    for an unknown id. Free.","read_only":false},{"name":"admin_overview","title":"","description":"Owner only: the whole service at a glance, as GET /v1/admin/overview. Counts of\n    accounts and people; runs (total, last_24h, last_7d, failed_24h, in_flight); hooks;\n    credits (charged_24h, charged_7d, charged_total, balance_total); access\n    (pending_requests, active_codes, redemptions); search (credits_left, low,\n    accepting_runs; null when not read yet); and the running commit. Needs the","read_only":false},{"name":"admin_list_accounts","title":"","description":"Owner only: every account, newest first, as GET /v1/admin/accounts: {total,\n    accounts: [{id, email, name, label, credits, created_at, last_seen_at, runs, hooks,\n    charged_total, is_admin, admitted_by, keys_active}]}. Free.","read_only":false},{"name":"admin_adjust_credits","title":"","description":"Owner only: add or remove an account's credits, as POST\n    /v1/admin/accounts/{account_id}/credits. A change that would take the balance below\n    zero is 422 credits_below_zero and nothing changes; an unknown account is 404\n    account_not_found. Every change is audited (admin_list_actions). Returns {account_id,\n    credits, delta}.","read_only":false},{"name":"admin_list_runs","title":"","description":"Owner only: every account's research runs, newest first, as GET /v1/admin/runs:\n    {runs: [{run_id, account_id, email, topic, language, country, status, requested,\n    hooks, reserved, charged, failure_kind, error, created_at, finished_at}]}. Free.","read_only":false},{"name":"admin_list_actions","title":"","description":"Owner only: the audit of password sign-ins and credit changes, newest first, as GET\n    /v1/admin/actions: {actions: [{id, action, actor_email, target_account_id, detail,\n    created_at}]}. Free.","read_only":false},{"name":"list_strategies","title":"","description":"The hook strategy library: every kind of long-form hook the shared index holds at least\n    3 openings of, with its plain name, count, the median multiple of those videos over their\n    channels' usual views, the median hook length in seconds, the template most share, and up\n    to 3 real examples (title, hook as said, video_id, channel, multiple). Counted from the\n    index, never by a model; pub","read_only":false},{"name":"create_folder","title":"","description":"Make a named folder on one tab to file hooks or finds in. The same name again on\n    that tab (case and spaces aside) returns the folder already there with created false,\n    so a retry never makes two. At most 200 folders an account (409\n    folder_limit_reached). Returns the folder: folder_id, kind, name, item_count, cover,\n    shared, share_url, created. Same as POST /v1/folders. Free. Next: sa","read_only":false},{"name":"list_folders","title":"","description":"Your folders, the most recently changed first, each with item_count, up to 4 cover\n    thumbnails and its share link when shared. With hook_id or find_id, each folder also\n    has contains: the item id when it holds that video (any run's copy), else null.\n    Returns {\"folders\": [...], \"count\"}. Same as GET /v1/folders. Free.","read_only":false},{"name":"get_folder","title":"","description":"One of your folders and its items, newest filed first, limit 1 to 100 a page (page\n    with next_cursor). Each item has item_id, note, thumbnail_url, title and the full hook\n    or find object. Same as GET /v1/folders/{folder_id}. Free. Errors: 404\n    folder_not_found.","read_only":false},{"name":"rename_folder","title":"","description":"Rename a folder, change its description, or both. A name another folder on the tab\n    already has is 409 folder_exists. Returns the folder. Same as PATCH\n    /v1/folders/{folder_id}. Free.","read_only":false},{"name":"delete_folder","title":"","description":"Delete a folder, its items and its share link at once (the link stops working). The\n    hooks and finds in it, and their keeps, stay. Returns {\"folder_id\", \"deleted\": true}.\n    Same as DELETE /v1/folders/{folder_id}. Free. Errors: 404 folder_not_found.","read_only":false},{"name":"save_to_folder","title":"","description":"File one video in a folder of its tab: a find (find_id) or any public YouTube video\n    (video_id) in a long or packaging folder, a hook (hook_id) in a short one, with an\n    optional note. A video already in the\n    folder (the same find, another run's find of it, the same hook) returns that item with\n    created false; a note given then replaces its note. Filing does not keep it. Same as\n    POS","read_only":false},{"name":"edit_folder_item","title":"","description":"Set the note on one item of a folder. Returns the item. Same as PATCH\n    /v1/folders/{folder_id}/items/{item_id}. Free. Errors: 404 item_not_found.","read_only":false},{"name":"remove_from_folder","title":"","description":"Take one video out of a folder; the hook or find and its keep stay. Returns\n    {\"item_id\", \"removed\": true}. Same as DELETE /v1/folders/{folder_id}/items/{item_id}.\n    Free. Errors: 404 item_not_found (also on a second remove).","read_only":false},{"name":"share_folder","title":"","description":"Turn on a folder's share link: share_url is a public read-only page anyone with it\n    opens signed out (hookdetector.com/f/<token>); api_url is the same as JSON\n    (get_shared_folder). It shows the folder's name, description and items with their\n    notes, never anything about the account. A shared folder keeps its link. Same as\n    POST /v1/folders/{folder_id}/share. Free.","read_only":false},{"name":"unshare_folder","title":"","description":"Turn a folder's share link off: the old link stops working at once; share_folder\n    again makes a new one. Same as DELETE /v1/folders/{folder_id}/share. Free.","read_only":false},{"name":"get_shared_folder","title":"","description":"A shared folder as anyone with its link sees it: name, description, kind,\n    item_count and items (public fields and the owner's note), newest first, paged. No key\n    needed; limited per address (429). A link never made or turned off is 404\n    shared_folder_not_found. Same as GET /v1/shared/folders/{token}. Free.","read_only":false},{"name":"swipe_file","title":"","description":"Your swipe file: the title structures of the Packaging finds you kept or filed, each\n    title_template with its title_device, count (how many of those videos use it, one a\n    video) and best (the example with the highest outlier_score, 0 to 100). The most used\n    first; packages is how many videos were read, skipped how many had no structure. Same\n    as GET /v1/swipe. Free.","read_only":false},{"name":"share_run","title":"","description":"Share a finished Short form run as a public, read-only page anyone can open with the\n    link, no sign-in: each hook's spoken line, on-screen words, idea, plays, creator and its\n    video, in the Hook Detector skill page layout. Nothing about the account is on it.\n\n    Returns {\"run_id\", \"token\", \"url\"}; give the person the url\n    (https://hookdetector.com/p/<token>). Idempotent: a run keeps one ","read_only":false},{"name":"start_job","title":"","description":"Start a background job on Hook Detector's job runner. Only echo can be started by\n    hand: it waits `seconds` and answers `message` back with how many attempts it took (a\n    job survives a deploy). At most 3 an hour per account. Free. Same as POST /v1/jobs;\n    read it back with get_job.","read_only":false},{"name":"list_jobs","title":"","description":"This account's background jobs, newest first (tracker refreshes, alerts, reviews,\n    echo): status, attempts, credits, result or error. Free. Same as GET /v1/jobs.","read_only":false},{"name":"get_job","title":"","description":"One background job of this account. Same as GET /v1/jobs/{job_id}. Errors: 404\n    job_not_found for another account's job or an unknown id.","read_only":false},{"name":"search_index","title":"","description":"Search the shared index of public YouTube videos Hook Detector's runs measured, with\n    no run: words by text and meaning, or browse; filters for the multiple, views, long or\n    short, recency, channel size and language. Free. Same as GET /v1/index/search.","read_only":false},{"name":"random_outliers","title":"","description":"Outliers at random from the shared index (5x their channel's usual and over by\n    default), a different set each call. Free. Same as GET /v1/index/random.","read_only":false}],"server_info":{"name":"hookdetector","title":"Hook Detector","version":""},"category":"social","tags":["developer","hr","image-video"],"kind":"remote","source":"registry","submitted":{},"first_party":true,"domain_rank":null,"score":100,"indexable":true,"first_seen":"2026-09-25","stars":0,"badges":[],"sponsor":null,"page":"https://agentsindex.org/agents/com-hookdetector-hookdetector/"}