com.tweetsmash/mcp

Est-ce que com.tweetsmash/mcp est sûr ?

Au dernier audit MCP Hub, le serveur MCP « com.tweetsmash/mcp » est classé « Non encore testé ». Référencé dans l'annuaire. Seul le pentest comportemental fait foi, et il n'a pas encore été exécuté sur ce serveur. Le verdict est réévalué en continu ; consultez la fiche pour l'état à jour.

Méthode : MCP Hub analyse la description de chaque outil (couche 1) et, pour le verdict fort, exécute le serveur dans une micro-VM isolée avec leurres et réseau bloqué (couche 2). On publie des noms et des compteurs, jamais le contenu brut renvoyé par un outil.

Les 53 outils

• add_labels_to_tweets≈ 216 tokens

  Add a label to a list of tweets. Can use an existing label by ID or create a new label by name. Either label_id or label_name must be provided.

  Paramètres, retour & exemple (3)

  Paramètres

  • label_id · string · optionnel
    ID of existing label (use either label_id or label_name)
  • tweet_ids · array · requis
    Array of tweet IDs to add the label to
  • label_name · string · optionnel
    Name of the label to create/add (use either label_id or label_name)

  Exemple d'appel

  {"name": "add_labels_to_tweets", "arguments": {"tweet_ids": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• archive_bookmarks≈ 210 tokens

  Archive, unarchive, delete, undelete, or mark read/unread a list of bookmarks by id (max 500). This is a bulk write; for destructive actions (delete) confirm with the user first. Reports how many changed.

  Paramètres, retour & exemple (2)

  Paramètres

  • action · string · requis · archive | unarchive | delete | undelete | read | unread
    The action to apply.
  • tweet_ids · array · requis
    Bookmark ids to act on (max 500).

  Exemple d'appel

  {"name": "archive_bookmarks", "arguments": {"action": "archive", "tweet_ids": []}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• archive_bookmarks_by_filter≈ 207 tokens

  Apply archive/unarchive/delete/undelete to EVERY bookmark matching a filter, in one call. Destructive by nature — confirm with the user before delete. Reports counts.

  Paramètres, retour & exemple (5)

  Paramètres

  • tags · array · optionnel
  • value · string · optionnel
  • action · string · requis · archive | unarchive | delete | undelete
    The action to apply to every match.
  • filter · string · optionnel
  • search_query · string · optionnel

  Exemple d'appel

  {"name": "archive_bookmarks_by_filter", "arguments": {"action": "archive"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• compose_mash_digest≈ 198 tokens

  Compose one of the user's Digest 2.0 digests NOW rather than waiting for its schedule. SPENDS A DIGEST CREDIT and takes about a minute, so only call it when the user asks for a fresh digest — not to inspect the current one (use get_mash_digest_issue for that). Returns an issue_id to read back once composing finishes.

  Paramètres, retour & exemple (1)

  Paramètres

  • digest_id · string · requis
    Which digest to compose, from list_mash_digests.

  Exemple d'appel

  {"name": "compose_mash_digest", "arguments": {"digest_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• correct_interest≈ 365 tokens

  Record the user's correction to an inferred interest, using a key from get_interests. Corrections are sticky — they survive every future recompute. Use `confirm` when they agree, `rename` for their own wording, `hide` to stop using an interest while keeping its history, `boost` when they want it weighted higher. `forget` is different and IRREVERSIBLE: it erases the underlying history so the topic cannot re-form — only use it when the user clearly asks to delete, and say what it means first.

  Paramètres, retour & exemple (3)

  Paramètres

  • value · string · optionnel
    Required for rename: the user's own name for this interest.
  • action · string · requis · confirm | boost | rename | hide | forget
    confirm = the user says this is right (keeps it alive as it ages); boost = they want it weighted higher; rename = give it their own name; hide = stop showing or using it, evidence kept; forget = ERASE the underlying history, irreversible.
  • interest_key · string · requis
    The interest's key, exactly as returned by get_interests.

  Exemple d'appel

  {"name": "correct_interest", "arguments": {"action": "confirm", "interest_key": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• create_share_link≈ 208 tokens

  Create a public, read-only share link for a set of bookmarks (explicit ids or everything matching a filter). Returns a share_url valid for 7 days. Free plans share up to 10 bookmarks.

  Paramètres, retour & exemple (5)

  Paramètres

  • tags · array · optionnel
  • value · string · optionnel
  • filter · string · optionnel
  • tweet_ids · array · optionnel
    Explicit ids to export. Omit to export everything matching the filter, or the whole library.
  • search_query · string · optionnel

  Exemple d'appel

  {"name": "create_share_link", "arguments": {"tags": [], "value": "texte", "filter": "texte", "tweet_ids": [], "search_query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• create_smart_view≈ 190 tokens

  Create a Smart View from a filter so the user can reuse it. Provide a name and the base_query (filter).

  Paramètres, retour & exemple (5)

  Paramètres

  • name · string · requis
    View name.
  • base_query · string · optionnel
    The filter query that defines the view.
  • description · string · optionnel
  • default_sort · string · optionnel
  • triage_buckets · ? · optionnel
    Optional tab/bucket definitions.

  Exemple d'appel

  {"name": "create_smart_view", "arguments": {"name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• delete_digest_preference≈ 120 tokens

  Remove a digest schedule by id.

  Paramètres, retour & exemple (1)

  Paramètres

  • id · string · requis
    The digest preference id.

  Exemple d'appel

  {"name": "delete_digest_preference", "arguments": {"id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• delete_label≈ 262 tokens

  Delete a label from the account entirely — the label itself plus every bookmark's assignment of it. The BOOKMARKS are not deleted; they simply lose this label. IRREVERSIBLE: before calling, tell the user how many bookmarks carry the label (list_labels returns the count) and get an explicit yes. To take a label off SOME bookmarks instead, use remove_labels_from_tweets. If the name matches more than one label the call fails with the candidates — re-run with label_id.

  Paramètres, retour & exemple (2)

  Paramètres

  • label_id · string|number · optionnel
    The label's id. Use this when a name matched more than one label.
  • label_name · string · optionnel
    Name of the label to delete, exactly as it appears in list_labels.

  Exemple d'appel

  {"name": "delete_label", "arguments": {"label_id": 1, "label_name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• delete_smart_view≈ 115 tokens

  Delete a Smart View by slug.

  Paramètres, retour & exemple (1)

  Paramètres

  • slug · string · requis
    The smart view slug.

  Exemple d'appel

  {"name": "delete_smart_view", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• fetch_recent_bookmarks≈ 218 tokens

  Force-pull the user's most recent bookmarks from the X API now (server-side). Requires a connected X account; if the account only syncs via the browser extension, this reports that a browser sync is needed. Use when the user asks to refresh / fetch their latest saves. For Twitter-list freshness, use get_list_tweets instead.

  Paramètres, retour & exemple (2)

  Paramètres

  • max · number · optionnel
    How many recent bookmarks to pull (max 800).
  • force · boolean · optionnel
    Force the pull even if a recent sync exists.

  Exemple d'appel

  {"name": "fetch_recent_bookmarks", "arguments": {"max": 1, "force": true}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• forget≈ 136 tokens

  Delete a saved library preference by key (optionally narrowed by kind). Use when the user changes their mind or asks you to drop something.

  Paramètres, retour & exemple (2)

  Paramètres

  • key · string · optionnel
    The memory key to forget.
  • kind · string · optionnel

  Exemple d'appel

  {"name": "forget", "arguments": {"key": "texte", "kind": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_author_preferences≈ 104 tokens

  The user's stated author preferences for list digests: `boost` = never-miss authors, `hide` = muted authors.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_author_preferences", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_bookmark≈ 231 tokens

  Get a single saved bookmark with FULL content in one call — the full X Article body, the unrolled thread, notes, and (optionally) replies. Use `include` (comma list of article,thread,notes,replies) to narrow it; defaults to article,thread,notes. Use this when the user wants to read or summarize a specific saved tweet/thread/article in depth.

  Paramètres, retour & exemple (2)

  Paramètres

  • id · string · requis
    The tweet/bookmark id to fetch.
  • include · string · optionnel
    Comma list of extra content to include: article,thread,notes,replies. Defaults to article,thread,notes.

  Exemple d'appel

  {"name": "get_bookmark", "arguments": {"id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_bookmark_count≈ 414 tokens

  Get the total count of user's bookmarks with optional filtering. Useful for understanding the size of bookmark collections before listing them.

  Paramètres, retour & exemple (9)

  Paramètres

  • tag · string · optionnel
    Filter by tag
  • author · string · optionnel
    Filter by author username. Use this parameter when the user wants to find tweets by a specific author (e.g., 'Show tweets by @user'). Do NOT use 'q' for author names.
  • posted_to · string · optionnel
    Filter tweets posted before this date (ISO 8601 string)
  • media_type · string · optionnel · thread | media | replies | notes | links | article
    Filter by kind: thread · media (images/video) · replies · notes · links (posts linking out) · article (a native X Article — use this when someone says "article", not `links`)
  • posted_from · string · optionnel
    Filter tweets posted after this date (ISO 8601 string)
  • bookmarked_to · string · optionnel
    Filter bookmarks added before this date (ISO 8601 string)
  • hide_archived · boolean · optionnel
    Hide archived bookmarks
  • is_unread_only · boolean · optionnel
    Filter to only unread bookmarks
  • bookmarked_from · string · optionnel
    Filter bookmarks added after this date (ISO 8601 string)

  Exemple d'appel

  {"name": "get_bookmark_count", "arguments": {"tag": "texte", "author": "texte", "posted_to": "texte", "media_type": "thread", "posted_from": "texte", "bookmarked_to": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_bookmark_sync_status≈ 152 tokens

  Show whether a specific bookmark has synced to a given integration connection.

  Paramètres, retour & exemple (2)

  Paramètres

  • tweet_id · string · requis
  • connect_id · string · requis
    The integration connection id.

  Exemple d'appel

  {"name": "get_bookmark_sync_status", "arguments": {"tweet_id": "texte", "connect_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_connection_status≈ 165 tokens

  Check whether the user's tweets can be pulled: the X (Twitter) API connection (connected / disconnected), whether the browser extension has synced recently, and a rolled-up can_pull + how (x_api or extension). Use this before a sync, or when the user asks why bookmarks aren't updating. Note: the extension is browser-only and can't be driven by an agent.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_connection_status", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_interests≈ 200 tokens

  Read what this user is actually interested in, inferred from their saved bookmarks, hand labels, questions and digest clicks — not from anything they typed. Returns topics with a 0-1 strength, whether each is active this week, and a `coverage` field saying how much evidence exists (`lite` means a new account: treat it as a first guess and check before relying on it). Use it to prioritise, filter or explain — then confirm with the user rather than asserting it back as fact. Evidence itself is not returned.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_interests", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_library_overview≈ 155 tokens

  A snapshot of the whole library: total bookmarks, unread, untagged, breakdown by type (threads/media/links/notes), every label with its count, and the years covered. Use this FIRST for anything open-ended (organise, clean up, learn from my saves, 'how many do I have per topic') instead of paging through bookmarks.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_library_overview", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_list_digests≈ 86 tokens

  List past Twitter-list email digests for the user.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_list_digests", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_list_tweets≈ 334 tokens

  Get recent tweets for a followed X list — the latest, or (sort=POPULARITY) the top/trending tweets in a look-back window. Serves a cached copy when it's fresh and otherwise fetches from X automatically, so it always returns real tweets; `meta.source` says cache or fetched and `meta.cache_age_hours` how old it is. Pass max_age_hours:0 to force a refresh. Get connect_id from list_twitter_lists. hours defaults to 24.

  Paramètres, retour & exemple (5)

  Paramètres

  • sort · string · optionnel · LATEST | POPULARITY
    LATEST or POPULARITY (trending/top).
  • hours · number · optionnel
    Look-back window in hours (default 24).
  • limit · number · optionnel
  • connect_id · string · requis
    The list connection id (the `connect_id` from list_twitter_lists).
  • max_age_hours · number · optionnel
    How stale cached tweets may be before refetching from X (default 4). Pass 0 to force a fresh fetch.

  Exemple d'appel

  {"name": "get_list_tweets", "arguments": {"connect_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_mash_digest_issue≈ 212 tokens

  One digest issue in full: its title, intro, every section, and per item the summary, why it was picked and why it matters to this user. Use it to answer 'what was in my digest?', 'why was this in there?' or to carry on a conversation about something the user just read. Items carry tweet IDS, not post text — resolve them with get_bookmark if the user asks about a specific post.

  Paramètres, retour & exemple (1)

  Paramètres

  • issue_id · string · requis
    The issue id, from list_mash_digest_issues.

  Exemple d'appel

  {"name": "get_mash_digest_issue", "arguments": {"issue_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_me≈ 107 tokens

  Get the current user's account: identity, current plan and status, and usage (e.g. AI chat credits). Use this to answer 'who am I' / 'what plan am I on'.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_me", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_skill≈ 313 tokens

  Get the full playbook for a task: when to use it, the exact tool sequence with the arguments that matter, tips, and the pitfalls that cause empty results. `name` takes EITHER an exact skill name (learn_from_bookmarks, organise_into_themes, cleanup_library, list_intelligence, get_my_data_out, find_that_thing, stay_on_top, diagnose_sync, connect_your_tool) OR a plain description of the job — both resolve. You do NOT need list_skills first: if you already know what the user is trying to do, call this directly with their request and skip the round trip. Reach for list_skills only to browse what exists.

  Paramètres, retour & exemple (1)

  Paramètres

  • name · string · optionnel
    Either an exact skill name (learn_from_bookmarks, organise_into_themes, cleanup_library, list_intelligence, get_my_data_out, find_that_thing, stay_on_top, diagnose_sync) or a plain description of the job — the closest match is returned either way, so passing the user's own words is fine.

  Exemple d'appel

  {"name": "get_skill", "arguments": {"name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_smart_view≈ 124 tokens

  Get a single Smart View by slug (its filter, tabs/buckets, and sort).

  Paramètres, retour & exemple (1)

  Paramètres

  • slug · string · requis
    The smart view slug.

  Exemple d'appel

  {"name": "get_smart_view", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_smart_view_bookmarks≈ 220 tokens

  List the bookmarks inside a Smart View, optionally scoped to one tab/bucket. Use the returned ids with archive_bookmarks / tagging tools to act on the view.

  Paramètres, retour & exemple (4)

  Paramètres

  • slug · string · requis
    The smart view slug.
  • limit · number · optionnel
    Page size (1-100).
  • bucket · string · optionnel
    Which tab/bucket of the view to read (default: all).
  • cursor · number · optionnel
    Numeric offset for the next page.

  Exemple d'appel

  {"name": "get_smart_view_bookmarks", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• get_sync_status≈ 110 tokens

  Show the user's app-sync integrations (Notion, Google Sheets, Zotero): whether each is connected/enabled, synced vs pending counts, and any errors.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "get_sync_status", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_bookmarks≈ 600 tokens

  List the user's Twitter BOOKMARKS — posts they deliberately saved. Never includes X Likes; use list_likes for those. Supports filtering and pagination. Supports filtering by read status, media type, author, tags, date ranges, and sorting options. IMPORTANT: Use this tool (with the 'author' parameter) when the user asks to show tweets by a specific author.

  Paramètres, retour & exemple (13)

  Paramètres

  • tag · string · optionnel
    Filter by tag
  • limit · number · optionnel
    Number of bookmarks to retrieve (1-100)
  • author · string · optionnel
    Filter by author username. Use this parameter when the user wants to find tweets by a specific author (e.g., 'Show tweets by @user'). Do NOT use 'q' for author names.
  • cursor · string · optionnel
    Pagination cursor for next page
  • sort_by · string · optionnel · POSTED_DATE_ASC | POSTED_DATE_DESC | OLDEST_FIRST | NEWEST_FIRST
    Sort order for results
  • posted_to · string · optionnel
    Filter tweets posted before this date (ISO 8601 string)
  • media_type · string · optionnel · thread | media | replies | notes | links | article
    Filter by kind: thread · media (images/video) · replies · notes · links (posts linking out) · article (a native X Article — use this when someone says "article", not `links`)
  • posted_from · string · optionnel
    Filter tweets posted after this date (ISO 8601 string)
  • sort_cursor · string · optionnel
    Cursor for pagination when using sort_by (use value from meta.sort_cursor of previous response)
  • bookmarked_to · string · optionnel
    Filter bookmarks added before this date (ISO 8601 string)
  • hide_archived · boolean · optionnel
    Hide archived bookmarks
  • is_unread_only · boolean · optionnel
    Filter to only unread bookmarks
  • bookmarked_from · string · optionnel
    Filter bookmarks added after this date (ISO 8601 string)

  Exemple d'appel

  {"name": "list_bookmarks", "arguments": {"tag": "texte", "limit": 1, "author": "texte", "cursor": "texte", "sort_by": "POSTED_DATE_ASC", "posted_to": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_digest_preferences≈ 104 tokens

  List the user's email-digest schedules (frequency, time, paused state) for bookmark and Smart View digests.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_digest_preferences", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_labels≈ 99 tokens

  List all user's labels with their usage counts. Useful for discovering existing labels before adding new ones.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_labels", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_likes≈ 580 tokens

  List the posts the user LIKED on X (not their bookmarks). Likes are a lighter signal than a save — use list_bookmarks for things the user deliberately saved, and this when the user explicitly asks about likes or about what they react to. Same filters and pagination as list_bookmarks.

  Paramètres, retour & exemple (13)

  Paramètres

  • tag · string · optionnel
    Filter by tag
  • limit · number · optionnel
    Number of bookmarks to retrieve (1-100)
  • author · string · optionnel
    Filter by author username. Use this parameter when the user wants to find tweets by a specific author (e.g., 'Show tweets by @user'). Do NOT use 'q' for author names.
  • cursor · string · optionnel
    Pagination cursor for next page
  • sort_by · string · optionnel · POSTED_DATE_ASC | POSTED_DATE_DESC | OLDEST_FIRST | NEWEST_FIRST
    Sort order for results
  • posted_to · string · optionnel
    Filter tweets posted before this date (ISO 8601 string)
  • media_type · string · optionnel · thread | media | replies | notes | links | article
    Filter by kind: thread · media (images/video) · replies · notes · links (posts linking out) · article (a native X Article — use this when someone says "article", not `links`)
  • posted_from · string · optionnel
    Filter tweets posted after this date (ISO 8601 string)
  • sort_cursor · string · optionnel
    Cursor for pagination when using sort_by (use value from meta.sort_cursor of previous response)
  • bookmarked_to · string · optionnel
    Filter bookmarks added before this date (ISO 8601 string)
  • hide_archived · boolean · optionnel
    Hide archived bookmarks
  • is_unread_only · boolean · optionnel
    Filter to only unread bookmarks
  • bookmarked_from · string · optionnel
    Filter bookmarks added after this date (ISO 8601 string)

  Exemple d'appel

  {"name": "list_likes", "arguments": {"tag": "texte", "limit": 1, "author": "texte", "cursor": "texte", "sort_by": "POSTED_DATE_ASC", "posted_to": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_mash_digest_issues≈ 198 tokens

  Past issues of the user's Digest 2.0, newest first — what arrived and when. Deliberately WITHOUT the content: pick one and call get_mash_digest_issue for the whole thing. Pass digest_id to narrow to one digest.

  Paramètres, retour & exemple (2)

  Paramètres

  • limit · integer · optionnel
    How many issues, newest first. Default 20.
  • digest_id · string · optionnel
    Narrow to one digest (from list_mash_digests). Omit for every digest.

  Exemple d'appel

  {"name": "list_mash_digest_issues", "arguments": {"limit": 1, "digest_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_mash_digests≈ 152 tokens

  The user's Mash Digest 2.0 digests — the AI-composed ones. An account can have SEVERAL (a morning read and an evening skim are two digests, not two sections of one), so START HERE and use the returned `id` for the other digest tools. Returns each digest's name, where its sections read from, and its schedule.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_mash_digests", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_past_digests≈ 113 tokens

  List past digests sent to the user's email, newest first. This is Digest 1.0 (the cluster pipeline). For the AI-composed Digest 2.0, use list_mash_digests.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_past_digests", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_skills≈ 155 tokens

  START HERE for any open-ended request. Lists the task playbooks this server supports — systematic learning from bookmarks, organising into themes, cleaning up, X-list intelligence, exporting data out, finding a half-remembered save, digests, and diagnosing sync. Each names when to use it; call get_skill for the exact tool sequence.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_skills", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_smart_views≈ 101 tokens

  List the user's Smart Views (saved filtered views). Each has a slug you pass to the other smart-view tools.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_smart_views", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• list_twitter_lists≈ 126 tokens

  List the X (Twitter) lists the user follows in Tweetsmash. Returns each list's name plus its `connect_id` — pass that to get_list_tweets / send_list_digest. START HERE for any 'what's in my list' request.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "list_twitter_lists", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• preview_list_ranking≈ 376 tokens

  Rank a followed X list exactly the way the digest ranker would, WITHOUT sending anything, and show the work: each unit carries its rank_signals (lane_fit = matches what the user builds/studies, affinity = an author they trust, engagement, substance, noise demotions) plus author groups (`group_size` + `related_items` = several posts by one author, best one leading). Use this to answer 'what's worth reading in my list?', 'why was this picked?', or to check how a preference change would land. `meta.inert_dimensions` names signals that had no data for this pool.

  Paramètres, retour & exemple (5)

  Paramètres

  • sort · string · optionnel · auto | popular
    auto (the digest's blend) or popular (engagement-led).
  • limit · number · optionnel
    How many ranked units to return (default 20).
  • list_id · string · optionnel
    The X list id, if known.
  • connect_id · string · requis
    The list connection id (the `connect_id` from list_twitter_lists).
  • window_days · number · optionnel
    Look-back window in days (default 1).

  Exemple d'appel

  {"name": "preview_list_ranking", "arguments": {"connect_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• recall≈ 153 tokens

  Read back the user's saved library preferences (optionally filtered by a substring). Worth calling before an open-ended organise, summarise or cleanup task so you follow how they already like things done.

  Paramètres, retour & exemple (1)

  Paramètres

  • query · string · optionnel
    Optional substring to filter the preferences returned.

  Exemple d'appel

  {"name": "recall", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• remember≈ 366 tokens

  Save a durable PREFERENCE about how this user wants their bookmark library handled — the themes they organise by, topics to exclude, preferred summary length/format, which account is their main one. It carries across sessions AND into the Tweetsmash web app, which your own client memory cannot reach. Use it for lasting preferences the user states or confirms, not for general chat context, task state, or anything secret.

  Paramètres, retour & exemple (4)

  Paramètres

  • key · string · requis
    A short stable key, e.g. organising_themes or summary_format. Reusing a key updates that preference instead of duplicating it.
  • kind · string · requis · preference | style | fact | instruction
    preference = how they want the library handled (themes, exclusions); style = how output should read (length, tone, format); fact = a stable fact about their setup (main account, workflow); instruction = a standing rule.
  • mode · string · optionnel
  • value · string · requis
    The preference itself, in plain words. Never a secret, token or password.

  Exemple d'appel

  {"name": "remember", "arguments": {"key": "texte", "kind": "preference", "value": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• remove_labels_from_tweets≈ 167 tokens

  Remove a label from a list of tweets using label_name.

  Paramètres, retour & exemple (2)

  Paramètres

  • tweet_ids · array · requis
    Array of tweet IDs to remove label from
  • label_name · string · requis
    Name of the label to remove

  Exemple d'appel

  {"name": "remove_labels_from_tweets", "arguments": {"tweet_ids": [], "label_name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• revoke_share_link≈ 124 tokens

  Revoke a previously created share link by its token.

  Paramètres, retour & exemple (1)

  Paramètres

  • token · string · requis
    The share link token to revoke.

  Exemple d'appel

  {"name": "revoke_share_link", "arguments": {"token": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• search_bookmarks≈ 698 tokens

  Search through a user's Twitter bookmarks using keyword search (q), semantic search (vector_search_term), or author filtering (author). At least one of q, vector_search_term, or author should be provided. IMPORTANT: Use the 'author' parameter for filtering by author, not the 'q' field.

  Paramètres, retour & exemple (15)

  Paramètres

  • q · string · optionnel
    Keyword or text search query for finding bookmarks by exact words or phrases in tweet content. Do NOT use this for author names - use the 'author' parameter instead.
  • tag · string · optionnel
    Filter by tag
  • limit · number · optionnel
    Number of bookmarks to retrieve (1-100)
  • author · string · optionnel
    Filter by author username. Use this parameter when the user wants to find tweets by a specific author (e.g., 'Show tweets by @user'). Do NOT use 'q' for author names.
  • cursor · string · optionnel
    Pagination cursor for next page
  • sort_by · string · optionnel · POSTED_DATE_ASC | POSTED_DATE_DESC | OLDEST_FIRST | NEWEST_FIRST
    Sort order for results
  • posted_to · string · optionnel
    Filter tweets posted before this date (ISO 8601 string)
  • media_type · string · optionnel · thread | media | replies | notes | links | article
    Filter by kind: thread · media (images/video) · replies · notes · links (posts linking out) · article (a native X Article — use this when someone says "article", not `links`)
  • posted_from · string · optionnel
    Filter tweets posted after this date (ISO 8601 string)
  • sort_cursor · string · optionnel
    Cursor for pagination when using sort_by (use value from meta.sort_cursor of previous response)
  • bookmarked_to · string · optionnel
    Filter bookmarks added before this date (ISO 8601 string)
  • hide_archived · boolean · optionnel
    Hide archived bookmarks
  • is_unread_only · boolean · optionnel
    Filter to only unread bookmarks
  • bookmarked_from · string · optionnel
    Filter bookmarks added after this date (ISO 8601 string)
  • vector_search_term · string · optionnel
    Semantic search query for retrieving bookmarks based on meaning and context, not just keywords. Use for natural language questions or topic-based searches.

  Exemple d'appel

  {"name": "search_bookmarks", "arguments": {"q": "texte", "tag": "texte", "limit": 1, "author": "texte", "cursor": "texte", "sort_by": "POSTED_DATE_ASC"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• search_docs≈ 182 tokens

  Answer questions about Tweetsmash itself — features, how-to, pricing, plans, limits, account/subscription. Searches the bundled product guide and returns the most relevant sections for you to answer from. Call with an empty query to list the help topics.

  Paramètres, retour & exemple (1)

  Paramètres

  • query · string · optionnel
    What the user is asking about the product (pricing, a feature, how-to). Empty returns the list of help topics.

  Exemple d'appel

  {"name": "search_docs", "arguments": {"query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• send_list_digest≈ 151 tokens

  Build and email a digest of a Twitter list's high-signal tweets to the user now.

  Paramètres, retour & exemple (2)

  Paramètres

  • list_id · string · optionnel
    The X list id, if required.
  • connect_id · string · requis
    The list connection id.

  Exemple d'appel

  {"name": "send_list_digest", "arguments": {"connect_id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• set_author_preference≈ 272 tokens

  Remember how the user feels about an author in their list digests. action=boost → never miss this author's posts (they will always be included, low-signal ones collapsed rather than dropped); action=hide → mute them; action=clear → forget the preference. Use when the user says things like 'don't let me miss marclou's updates' or 'stop showing me X'. Takes effect from the next digest and in preview_list_ranking immediately.

  Paramètres, retour & exemple (2)

  Paramètres

  • action · string · requis · boost | hide | clear
    boost = never miss this author in list digests; hide = mute them; clear = remove any preference.
  • handle · string · requis
    The author's X handle, with or without the @.

  Exemple d'appel

  {"name": "set_author_preference", "arguments": {"action": "boost", "handle": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• setup_vector_store≈ 136 tokens

  Initialize the vector store for semantic bookmark search. CRITICAL: When vector/semantic search fails with 'Vector Store Not Setup' error, call this tool. This is an async operation that may take a few minutes for large bookmark collections.

  Paramètres, retour & exemple (0)

  Exemple d'appel

  {"name": "setup_vector_store", "arguments": {}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• tag_bookmarks_by_filter≈ 513 tokens

  Add a label to EVERY bookmark matching a filter, in a single call. Prefer this over listing then looping when the user says 'tag all my … as …'. Resolves an author name to its id automatically. Reports matched/tagged/failed counts.

  Paramètres, retour & exemple (12)

  Paramètres

  • q · string · optionnel
    Keyword search to scope which bookmarks get tagged.
  • tag · string · optionnel
    Filter by tag
  • author · string · optionnel
    Filter by author username. Use this parameter when the user wants to find tweets by a specific author (e.g., 'Show tweets by @user'). Do NOT use 'q' for author names.
  • label_id · string · optionnel
    Existing label id (use label_id or label_name).
  • posted_to · string · optionnel
    Filter tweets posted before this date (ISO 8601 string)
  • label_name · string · optionnel
    Label to create/apply (use label_id or label_name).
  • media_type · string · optionnel · thread | media | replies | notes | links | article
    Filter by kind: thread · media (images/video) · replies · notes · links (posts linking out) · article (a native X Article — use this when someone says "article", not `links`)
  • posted_from · string · optionnel
    Filter tweets posted after this date (ISO 8601 string)
  • bookmarked_to · string · optionnel
    Filter bookmarks added before this date (ISO 8601 string)
  • hide_archived · boolean · optionnel
    Hide archived bookmarks
  • is_unread_only · boolean · optionnel
    Filter to only unread bookmarks
  • bookmarked_from · string · optionnel
    Filter bookmarks added after this date (ISO 8601 string)

  Exemple d'appel

  {"name": "tag_bookmarks_by_filter", "arguments": {"q": "texte", "tag": "texte", "author": "texte", "label_id": "texte", "posted_to": "texte", "label_name": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• trigger_csv_export≈ 194 tokens

  Start a CSV export (explicit ids, a filter, or the whole library). Returns a job id; the file appears in the Export Center.

  Paramètres, retour & exemple (5)

  Paramètres

  • tags · array · optionnel
  • value · string · optionnel
  • filter · string · optionnel
  • tweet_ids · array · optionnel
    Explicit ids to export. Omit to export everything matching the filter, or the whole library.
  • search_query · string · optionnel

  Exemple d'appel

  {"name": "trigger_csv_export", "arguments": {"tags": [], "value": "texte", "filter": "texte", "tweet_ids": [], "search_query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• trigger_json_export≈ 195 tokens

  Start a JSON export (explicit ids, a filter, or the whole library). Returns a job id; the file appears in the Export Center.

  Paramètres, retour & exemple (5)

  Paramètres

  • tags · array · optionnel
  • value · string · optionnel
  • filter · string · optionnel
  • tweet_ids · array · optionnel
    Explicit ids to export. Omit to export everything matching the filter, or the whole library.
  • search_query · string · optionnel

  Exemple d'appel

  {"name": "trigger_json_export", "arguments": {"tags": [], "value": "texte", "filter": "texte", "tweet_ids": [], "search_query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• trigger_pdf_export≈ 210 tokens

  Start a PDF export of the user's bookmarks (explicit ids, everything matching a filter, or the whole library). Returns a job id; tell the user the file will appear in the Export Center.

  Paramètres, retour & exemple (5)

  Paramètres

  • tags · array · optionnel
  • value · string · optionnel
  • filter · string · optionnel
  • tweet_ids · array · optionnel
    Explicit ids to export. Omit to export everything matching the filter, or the whole library.
  • search_query · string · optionnel

  Exemple d'appel

  {"name": "trigger_pdf_export", "arguments": {"tags": [], "value": "texte", "filter": "texte", "tweet_ids": [], "search_query": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• update_digest_preference≈ 185 tokens

  Update a digest schedule (enable/pause, frequency, time) by id.

  Paramètres, retour & exemple (7)

  Paramètres

  • id · string · requis
    The digest preference id to update.
  • is_paused · boolean · optionnel
  • week_info · ? · optionnel
  • is_enabled · boolean · optionnel
  • time_to_read · ? · optionnel
  • schedule_time · string · optionnel
  • send_frequency · string · optionnel
    e.g. DAILY, WEEKLY.

  Exemple d'appel

  {"name": "update_digest_preference", "arguments": {"id": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

• update_smart_view≈ 164 tokens

  Update a Smart View (name, filter, tabs, sort) by slug.

  Paramètres, retour & exemple (6)

  Paramètres

  • name · string · optionnel
  • slug · string · requis
    The smart view slug to update.
  • base_query · string · optionnel
  • description · string · optionnel
  • default_sort · string · optionnel
  • triage_buckets · ? · optionnel

  Exemple d'appel

  {"name": "update_smart_view", "arguments": {"slug": "texte"}}

  Exemple de retour

  {"content": [{"type": "text", "text": "…"}]}

C'est votre serveur ?

Revendiquez-le sur l'espace créateur (preuve GitHub, domaine ou npm) pour afficher le badge « propriétaire vérifié » et lancer un pentest comportemental à la demande afin d'obtenir le badge « Vérifié ».

Créer un compte / revendiquer →

Source

https://mcp.tweetsmash.com/api/mcp