Plugin tracker

Tools

Explore what tracked Claude Connectors and ChatGPT Plugins can actually do. Search by tool, Plugin, Brand, category, verb, or access requirement.

Latest snapshot2026-09-12USmethodology registry-public-v1

Searchable tools

113,018

Authless tools

7,424

Auth required

100,766

Described tools

61,167

113,018 tools

List library showslist · List the shows in the library — the fastest way to learn what is actually here before you search. Call this FIRST when the user says something like 'anything new in my shows?' or when a search_episodes call comes back thin: it tells you, in one call, which shows exist, how many episodes each has, how many carry publisher transcripts, and when each last published. It is a library inventory, not a catalog of all podcasts — a show missing here simply has not been imported yet, which import_feed fixes. Ordered by title; optional limit (default 50, max 200). When it is due this also carries standing_feedback — what the user has written about their listening, verbatim, each note naming its show, so you can tell an old favourite from a show they abandoned before you start proposing anything.RovynRovynPluginrequiredConsumer & Lifestyle
Mint a player linkcreate · Mint a fresh universal link for an existing plan. The user taps it and the Rovyn app opens (or installs) straight to that plan. The plan is already on the user's Shelf regardless — a link never delivers, it only opens — so present it as the shortcut, not the handoff. create_plan ALREADY returns a player_link — do not call this right after creating a plan. Use it to re-share later, replace a lost link, or link a plan that predates links. Each call mints a new token; previously minted links stay valid until claimed. The token is the credential, so give the link only to the user in chat.RovynRovynPluginrequiredConsumer & Lifestyle
Record user feedbackrecord · Record what the user ACTUALLY SAID about a piece of content in conversation. Prefer user_feedback: their own sentence, quoted, not your paraphrase ('the second one was too basic, I wanted the operator view') — it is stored verbatim and comes back verbatim on the receipt, for you or for the next assistant. 'structured' is the optional one-tap convenience beside it: value (worth_my_time | not_worth_my_time), difficulty, length, flags (too_repetitive | too_promotional), free-form tags. Send at least one of the two, both when the user gave you both. If the user said it EARLIER (not this moment), set occurred_at to when they said it; if they are reacting to a specific pick, pass its recommendation_id so the receipt attributes the judgment. It lands in the same store the app's own feedback screen writes to and flows into the content's receipts immediately, where it outweighs passive consumption behavior. Only record what the user expressed — never synthesize feedback from your own reading of their history, and never rewrite their words into something tidier. Repeat submissions are fine; the store is append-only and the user may refine. Requires feedback:write.RovynRovynPluginrequiredConsumer & Lifestyle
Search library episodessearch · Look inside the USER'S LIBRARY — the shows already imported, the episodes resolved for them plus those shows' recent siblings, and their private feeds. This is NOT a search of the open podcast universe and NOT topic discovery: for that, use your own web search and ground the findings with resolve_content_batch. It is Postgres keyword full-text search over metadata (episode/show title, description, show notes, categories) — transcript text is not indexed in V1, so every result's match_basis disclosure currently reads 'metadata'; do not promise transcript-level matches. Query style: 2–4 distinctive keywords, not a sentence — all terms are tried together first, and if that finds nothing the server automatically retries with ANY term and ranks the results. The 'matched' field tells you which happened: 'all_terms' (tight match), 'any_terms' (loose — skim before recommending), 'none' (the library really does not have it; go web-search, then resolve_content_batch or import_feed). Empty results mean the library lacks it, never that the episode does not exist. When it is due the response carries standing_feedback — what the user has written about their listening, verbatim, notes about these shows placed first; already_listened still arrives on resolve verdicts, and get_recent_receipts with a content_id returns any one receipt whole. Use list_shows first if you do not know what is here. Note that a show which arrived by RESOLUTION is present but not complete — resolving writes that episode plus the feed's 50 most recent items, so if a deep back catalog comes up short, import_feed on its feed_url completes the show and the search is worth repeating.RovynRovynPluginrequiredConsumer & Lifestyle
Update a planupdate · Edit an existing plan with a batch of ops: add / remove / reorder / replace. Use it to substitute the picks create_plan reported as unresolved, to drop something the user disliked, or to reorder for the time they actually have. Added and replaced recommendations take a raw ref (content_type 'podcast_episode' plus episode_url / feed_url / guid and hints) just like create_plan, not only catalog ids. The batch is atomic: one rejected op leaves the plan untouched, and unlike create_plan an unresolvable add fails the whole batch (content_unavailable) — resolve_content_batch first if you are unsure. The user is the final editor: recommendations they locked in the app cannot be removed, replaced, or reordered ('locked_recommendation'), and lock/unlock are user-only ops. Returns the updated ConsumptionPlan plus total_duration_seconds.RovynRovynPluginrequiredConsumer & Lifestyle
Add checklist itemsadd · Append checklist items to a task. task_id from search/list_tasks. items is a list of 1 to 20 non-empty strings (each <=500 chars), appended after any existing items in order. Also accepts an 'occurrence:<series>:<date>' id from get_agenda — that edits ONLY that day of a recurring series, never the series itself.Simply-UsefulSimply-UsefulPluginrequiredProductivity
Add commentadd · Add a comment to a task on the user's behalf; everyone else on the task (owner, assignee, followers) is notified. task_id from search/list_tasks. body is the comment text (1 to 5000 characters). Requires the su.assign permission. Also accepts an 'occurrence:<series>:<date>' id from get_agenda — the comment lands on that ONE day of a recurring series.Simply-UsefulSimply-UsefulPluginrequiredProductivity
Add followeradd · Add one of the user's contacts as a follower on a task, giving them read+comment visibility; the contact is notified. Two-step: call first WITHOUT confirm to preview, then again with confirm=true to apply. Only the task's owner or current assignee can add followers, and the contact must have a Simply-Useful account (has_linked_user in list_contacts). task_id from search/list_tasks; contact_id from list_contacts. Requires su.assign.Simply-UsefulSimply-UsefulPluginrequiredProductivity
Add tags to taskadd · Put one or more tags on any task the user can edit, shared ones included (1-10 per call). tags takes NAMES or ids from list_tags. A name means, in order: a tag of the task's PROJECT, then the user's own, then a built-in — and a name matching none of those is CREATED as their own, so call list_tags first and reuse their words. On someone else's task the user's own tags are PRIVATE — nobody else sees them. task_id from search/list_tasks, or an 'occurrence:<series>:<date>' id from get_agenda (that day only).Simply-UsefulSimply-UsefulPluginrequiredProductivity
Add to Google Calendaradd · Put a task on the user's Google Calendar (only works when they have connected Google Calendar). The task must already have an upcoming schedule — schedule_task first if not; the calendar event mirrors that schedule and follows future changes. Owner-only; recurring tasks aren't supported yet. task_id from search/list_tasks. Idempotent — adding an already-added task just reports it's on the calendar.Simply-UsefulSimply-UsefulPluginrequiredProductivity
Archive taskarchive · Archive a task (hide it from active lists). task_id from search/list_tasks. Pass unarchive=true to restore it instead.Simply-UsefulSimply-UsefulPluginrequiredProductivity
Assign taskassign · Assign a task to one of the user's contacts; the contact is notified. Two-step: call first WITHOUT confirm to preview who will be notified, then again with confirm=true to actually assign and notify. task_id from search/list_tasks; contact_id from list_contacts — ANY active contact works; an external (non-app) contact gets an invitation link. Recurring tasks are refused when the server has recurring collaboration off. Requires the su.assign permission and explicit user confirmation on every call.Simply-UsefulSimply-UsefulPluginrequiredProductivity
Bulk edit tasksbulk · Apply ONE action to MANY tasks in a single call (1-100 task_ids). action: archive | unarchive | set_status (value todo/deferred/done) | set_priority (value default/medium/low/high) | add_tag / remove_tag (value = ONE tag name or id; add_tag creates a name list_tags doesn't have) | delete. delete is two-step: call without confirm to preview (count + first 10 titles, no change), then confirm=true. Per-item outcome {index, id, outcome: ok|not_found}. Prefer this over repeated single-task calls.Simply-UsefulSimply-UsefulPluginrequiredProductivity
Create projectcreate · Create a project (a container for tasks). Required: title (<=255). Optional: description (plain text, <=50k), status (in_progress — the default — completed, or archived; only pass one for a project the user says is already finished or put away). A color is assigned automatically. Returns the created project with its id.Simply-UsefulSimply-UsefulPluginrequiredProductivity
Create tagcreate · Create a tag (a label the user puts on tasks). Required: name (<=100 chars). Optional: project (id or title) makes it a PROJECT tag everyone in that project can use — only its owner or a co-owner may; without it the tag is the user's own. Call list_tags FIRST and reuse an existing tag where one fits: a name that already exists in the same place is returned unchanged, and the 'created' flag says which happened. The color is assigned automatically.Simply-UsefulSimply-UsefulPluginrequiredProductivity
Create taskcreate · Create a task or note. type 'task' (default) or 'note'. title <=130. Optional: description (plain text auto-formatted OR limited HTML, see the server instructions; <=50k), priority (default/medium/low/high), deadline (ISO date/datetime), project_id, checklist_items (<=20, each <=500), tags (<=10), schedule_start (ISO datetime or date) + schedule_duration_minutes (default 60) to schedule it. If the request implies a date/time ('Friday afternoon'), ALWAYS set schedule_start. Returns the new item's id.Simply-UsefulSimply-UsefulPluginrequiredProductivity
Create taskscreate · Create MANY tasks/notes in one call (1-50). items is a list of objects with the same fields as create_task (title required; type/priority/deadline/project_id/checklist_items/tags/schedule_start/schedule_duration_minutes optional; schedule items with temporal phrasing). atomic=true (default) = all-or-nothing (one bad item aborts all, error names its index); atomic=false = per-item results. Returns per-item {index, id, title} (or {index, error}) plus created_count. Prefer this over repeated create_task calls.Simply-UsefulSimply-UsefulPluginrequiredProductivity
Daily reviewdaily · Review a whole day in ONE call — use for 'plan my day' / 'what should I focus on' instead of chaining get_agenda + list_tasks + list_assignments. For that day (default today, their tz) returns: agenda (scheduled tasks, events, recurring days), overdue (open tasks due earlier), due_today (minus what the agenda shows), and assignments awaiting either side. An ARCHIVED project's work is left out. Empty sections are omitted; summary carries each full total. limit caps every section (default 10, max 50).Simply-UsefulSimply-UsefulPluginrequiredProductivity
Delete taskdelete · Delete a task. Two-step: call first WITHOUT confirm to get a preview of what will be deleted, then call again with confirm=true to actually delete it. task_id from search/list_tasks. Deleting a recurring-series master task ends its whole series (the preview says so).Simply-UsefulSimply-UsefulPluginrequiredProductivity
Fetchfetch · Fetch full details for one task, note or project by its id (prefixed 'task:<uuid>'/'note:<uuid>'/'project:<uuid>' from search/list_*, or a bare uuid). Returns id, title, a human-readable text rendering (status, priority, deadline, schedule, project, checklist with item ids, recent comments), a deep-link url and a metadata dict (checklist as {id, title, done}; timestamps ISO 8601, user's tz).Simply-UsefulSimply-UsefulPluginrequiredProductivity
Get agendaget · Get the user's plan for one day (default today, their timezone). Returns an ordered timeline of scheduled tasks and owned calendar events overlapping that local day, each with an ISO 8601 'start' (all-day items use 'YYYY-MM-DD'), plus a short summary. An archived project's tasks and repeats never appear. Pass date as YYYY-MM-DD for another day.Simply-UsefulSimply-UsefulPluginrequiredProductivity
List assignmentslist · List EXISTING task assignments — never a way to find a person: to look up a contact (e.g. to assign a task), use list_contacts. role='received' (default) shows tasks others assigned TO the user — status pending/pending_permission means it's awaiting the user's accept/decline (use respond_to_assignment); role='given' shows tasks the user assigned to others. Optional statuses filter (pending, pending_permission, accepted, declined, done, revoked). Returns total + cursor pagination.Simply-UsefulSimply-UsefulPluginrequiredProductivity
List contactslist · List the user's contacts, cursor-paginated (default 20, max 50). Each row has id, display name, status and whether the contact is a linked Simply Useful user. Never returns email or phone numbers.Simply-UsefulSimply-UsefulPluginrequiredProductivity
List projectslist · List the user's projects (owned and shared with them), cursor-paginated (default 20, max 50). BY DEFAULT only projects still IN PROGRESS — pass status='completed'|'archived' for those, or status='all' for every one. Each row has id (project:<uuid>), title, icon, status (in_progress/completed/archived), open/done task counts, and is_archived on archived rows. Falsey/empty fields are omitted. Change a status with set_project_status.Simply-UsefulSimply-UsefulPluginrequiredProductivity
List tagslist · List the tags the user can put on tasks, cursor-paginated (default 20, max 50), ordered built-in, then the user's own, then each project's (shared with everyone in that project). Each row has id (tag:<uuid>), name, scope (builtin/personal/project), project name and task_count. ALWAYS call this before tagging and reuse a tag that already means what you want — the tag tools CREATE any name they don't recognise, so an invented variant becomes a real second tag in the user's list.Simply-UsefulSimply-UsefulPluginrequiredProductivity
List taskslist · List/filter the user's tasks. Filters: status OR statuses (todo/deferred/done), project_id, priority, title_exact, title_contains, series_id, has_schedule, has_deadline, tags (names/ids, ANY-of), due_before/due_after (YYYY-MM-DD), include_archived. order_by: created_at/updated_at/deadline/title/priority ('-' reverses; priority is ranked). fields='detail' adds description + checklist/comment counts. An ARCHIVED project's tasks are hidden unless you pass its project_id. Cursor-paged (default 50, max 200).Simply-UsefulSimply-UsefulPluginrequiredProductivity
Remove followerremove · Remove a follower from a task. Pass contact_id to remove that contact (allowed for the task's owner or current assignee), or omit contact_id to stop following a task someone shared with the user. The removed follower loses access to the task; no notification is sent. task_id from search/list_tasks. Requires the su.assign permission.Simply-UsefulSimply-UsefulPluginrequiredProductivity
Remove from Google Calendarremove · Take a task off the user's Google Calendar (deletes the linked calendar event; the task itself and its schedule are NOT changed). Owner-only. task_id from search/list_tasks. Idempotent — removing a task that isn't on the calendar reports there was nothing to remove.Simply-UsefulSimply-UsefulPluginrequiredProductivity
Remove tags from taskremove · Take one or more tags off any task the user can edit (1-10 per call), leaving the tags themselves intact for other tasks. tags takes names or ids from list_tags; a name resolves against the task's project first, then the user's own tags, then the built-ins, and one that matches nothing is reported, never created. Another person's own tags on a shared task are invisible to the user, so those cannot be removed. task_id from search/list_tasks, or an 'occurrence:<series>:<date>' id from get_agenda.Simply-UsefulSimply-UsefulPluginrequiredProductivity
Respond to assignmentrespond · Accept or decline a task assignment the user received; the assigner is notified. assignment_id from list_assignments (a task id also works). action='accept' applies immediately to a pending assignment (also approves a pending collaboration request); an assignment already marked done can't be re-accepted — reopen via set_task_status instead. action='decline' is two-step: preview WITHOUT confirm, then confirm=true — declining is final and removes the task from the user's list. Requires su.assign.Simply-UsefulSimply-UsefulPluginrequiredProductivity
Schedule taskschedule · Schedule a task (replaces its one-off schedule). task_id from search/list_tasks; start is an ISO datetime (or date for all-day) in the user's timezone; optional duration_minutes (1-10080). An 'occurrence:<series>:<date>' id from get_agenda moves ONLY that day — the series rule is unchanged. recurrence (daily/weekly/monthly) makes a plain task repeat from start (weekly on its weekday, monthly on its day); owner-only. recurrence_end_date (YYYY-MM-DD) = last day; omit to repeat forever.Simply-UsefulSimply-UsefulPluginrequiredProductivity
Searchsearch · Search the user's tasks, notes and projects by keyword (case-insensitive substring over titles and descriptions). Returns matches, each with a prefixed id (task:/note:/project:), title and deep-link url. Pass a returned id to `fetch` for full details. An archived project's tasks are hidden (the project itself still matches). Default 20 results, max 50.Simply-UsefulSimply-UsefulPluginrequiredProductivity
Set checklist itemset · Toggle, rename, or remove ONE checklist item. task_id from search/list_tasks; item_id from fetch (its detail lists checklist items as {id, title, done}). Pass EXACTLY ONE of: done (true/false to set completion), title (rename, <=500 chars), or remove=true (delete the item). Returns the updated task. Also accepts an 'occurrence:<series>:<date>' id from get_agenda — that edits ONLY that day of a recurring series, never the series itself.Simply-UsefulSimply-UsefulPluginrequiredProductivity
Set project statusset · Set a project's status: in_progress (active), completed (finished, still visible), or archived (put away — the user's apps hide it AND its tasks). project_id from list_projects/search. The user may set any status on their own project; on someone else's they can move it between in_progress and completed only if they are a co-owner. Completing a project does NOT close its open tasks — the result says how many are still open, so offer to handle them.Simply-UsefulSimply-UsefulPluginrequiredProductivity
Set task priorityset · Set a task's priority. task_id from search/list_tasks. priority is one of default, medium, low, high. Also accepts an 'occurrence:<series>:<date>' id from get_agenda — that edits ONLY that day of a recurring series, never the series itself.Simply-UsefulSimply-UsefulPluginrequiredProductivity
Set task statusset · Set a task's status. task_id from search/list_tasks. status is one of todo, deferred, done. Marking done stamps completion and updates any linked assignment; reopening reverses it. Also accepts an 'occurrence:<series>:<date>' id from get_agenda; on a series someone SHARED with you only done/todo work — every other edit is the owner's.Simply-UsefulSimply-UsefulPluginrequiredProductivity
Task statstask · Summarise the user's tasks in ONE call (no paging): total, by_status, by_priority, by_project (top 20), duplicate_titles (title+count, top 20), archived_count, with_schedule, with_deadline, series_count (distinct recurring series). Pass include_archived=true to fold archived tasks into the counts. An archived project's tasks are left out of every figure. Use this to count or find duplicates instead of listing everything.Simply-UsefulSimply-UsefulPluginrequiredProductivity
Unschedule taskunschedule · Remove a task's one-off schedule. task_id from search/list_tasks. No-op if the task isn't scheduled; refuses tasks whose schedule belongs to a recurring series.Simply-UsefulSimply-UsefulPluginrequiredProductivity
Update taskupdate · Update a task's fields. task_id from search/list_tasks. Only provided fields change: title (<=130), description (plain text auto-formatted OR limited HTML: p, br, b/strong, i/em, u, a, ul/ol/li, h1-h3; <=50k; '' clears it), priority (default/medium/low/high), deadline (ISO date/datetime). clear_deadline / clear_project remove those; project_id moves it to a project. Also accepts an 'occurrence:<series>:<date>' id from get_agenda — that edits ONLY that day of a recurring series, never the series itself.Simply-UsefulSimply-UsefulPluginrequiredProductivity
Create data elementcreate · Create a new data element in a project. Data elements define how data is captured from the page/server for use in tags.Ingest LabsIngest LabsPluginrequiredMarketing
Create providercreate · Create a new provider (integration/extension) in a project. The intended flow is to GET an existing provider from a template/reference project, adapt the resource_params (e.g. remap data_element ids to the destination project), and POST the adapted definition here.Ingest LabsIngest LabsPluginrequiredMarketing
Create qualification criteriacreate · Create a new qualification criteria. The intended flow is to GET a QC from a reference project and POST the adapted definition (remapping any DE refs in qualification_criteria attributes to destination-project IDs).Ingest LabsIngest LabsPluginrequiredMarketing
Create tagcreate · Create a new tag under a provider. Tags define tracking/measurement configurations with resource parameter mappings.Ingest LabsIngest LabsPluginrequiredMarketing
Delete data elementdelete · Delete a data element from a project.Ingest LabsIngest LabsPluginrequiredMarketing
Execute Insights queryexecute · Run an Insights query against IDL dashboard data. Requires confirmed vendor_id (list_vendors if org unknown — never invent) and context_id plus at least one dimension or metric id from get_insights_schema. Provide interval_suffix (m|h|d|w) when selecting a dimension with dim_typ dt. Filters are dimension-only. Provide date_preset (uses vendor timezone) OR both from/to epoch seconds — not both. media_tags requires project_id (list_projects if project unknown). Always pass user_question with the user's original wording and query_intent explaining this query's role in answering it.Ingest LabsIngest LabsPluginrequiredMarketing
Get Insights schemaget · Get dimensions, metrics, mandatory filters, and classifications for a context_id from list_insights_contexts. Requires confirmed vendor_id (list_vendors if org unknown). Use dimension and metric **ids** (not display names) in execute_insights_query. Do not invent field ids.Ingest LabsIngest LabsPluginrequiredMarketing
Get data elementget · Get full details of a single data element by ID, including type-specific config (jsv.fn for JSV, mp_data_layer for MPDL, urlp for URLP, etc.). Use when list_data_elements does not surface enough detail (e.g. when copying a custom JSV DE).Ingest LabsIngest LabsPluginrequiredMarketing
Get projectget · Get details of a specific projectIngest LabsIngest LabsPluginrequiredMarketing
Get providerget · Get details of a specific provider including its resource parameters and data element mappingsIngest LabsIngest LabsPluginrequiredMarketing
Get provider templateget · Get details of a specific provider template including its resource parameters schemaIngest LabsIngest LabsPluginrequiredMarketing

Tool Explorer FAQ

What is Tool Explorer?

Tool Explorer indexes the callable tool names and descriptions attached to public registry profiles. It is useful for seeing what agents can actually invoke, not just which profile exists.

How do category and verb filters work?

Category filters use the live registry category rollup. Verb filters use the public tool insights rollup, so the page stays backed by the same read models as the tracker charts.

Why do auth requirements matter?

Auth requirements show whether a tool is likely usable without account connection, requires authentication, is private, or is unknown in the current snapshot.