Back to tracker
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
- delete_project_groupdelete · Delete a project group by projectGroupId.滴答清单: To-Do List & CalendarDIDA
PluginrequiredProductivity - delete_taskdelete · Delete a task by projectId and taskId.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- fetchfetch · Fetch the full contents of a task by its ID.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- filter_tasksfilter · Filter tasks by various criteria including date range, project IDs, priority, tag, kind and status.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- get_commentget · Get comments for a task by projectId and taskId.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- get_focusget · Get a single focus record by focusId and type.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- get_focuses_by_timeget · Get focus records by time range and type. The time range must not exceed one month.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- get_habitget · Get habit details by habitId.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- get_habit_checkinsget · Get habit check-ins by habitIds and yyyyMMdd int stamp range.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- get_project_by_idget · Get project details by projectId.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- get_project_with_undone_tasksget · Get project details and all undone tasks in the project by projectId.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- get_task_by_idget · Get full task details by taskId.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- get_task_in_projectget · Get a task by projectId and taskId.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- get_user_preferenceget · Get user preferences including timezone settings.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- list_columnslist · List all columns in a project by projectId.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- list_completed_tasks_by_datelist · Get completed tasks based on specified search criteria including project IDs and date range.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- list_countdownslist · List all countdowns of the current user.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- list_habit_sectionslist · List all habit sections of the current user.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- list_habitslist · List all habits of the current user.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- list_project_groupslist · List all project groups of the current user.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- list_project_memberslist · List members of a shared project. Use a returned username when assigning a task in that project.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- list_projectslist · List projects. Supports offset/limit pagination; unpaginated results also include virtual "inbox".滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- list_tagslist · List all tags of the current user.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- list_undone_tasks_by_datelist · List undone tasks within a date range. The maximum range is 14 days between startDate and endDate.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- list_undone_tasks_by_time_querylist · List undone tasks by time query: today, last24hour, last7day, tomorrow, next24hour, next7day.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- move_taskmove · Move tasks to different projects. Used for reorganizing tasks across projects.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- searchsearch · Search tasks in TickTick. Return a list of relevant result with IDS, title and URLs.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- search_tasksearch · Search tasks by keyword. Returns a list of matching tasks with taskId, title, and url.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- unassign_taskunassign · Remove the assignee from a task in a shared project.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- update_columnupdate · Update an existing column in a project by columnId.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- update_habitupdate · Update an existing habit by habitId.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- update_projectupdate · Update an existing project by projectId.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- update_project_groupupdate · Update an existing project group by projectGroupId.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- update_taskupdate · Update a task. Set parentId='' to detach; set startDate/dueDate to "1970-01-01T00:00:00.000+0000" to clear.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- upsert_habit_checkinsupsert · Create or update check-ins for a habit by habitId.滴答清单: To-Do List & CalendarDIDAPluginrequiredProductivity
- Add rule result evidenceadd · Attach evidence to a rule result (only for evidence-type rules).OpenlayerOpenlayerPluginrequiredAI
- Create frameworkcreate · Create a custom compliance/governance framework in a workspace.OpenlayerOpenlayerPluginrequiredAI
- Create inference pipelinecreate · Create a new inference pipeline in a project.OpenlayerOpenlayerPluginrequiredAI
- Create presigned upload URLcreate · Get a URL to upload a commit bundle to.
Used instead of `push_commit` on the shared remote server, which can't read a
directory on your machine. Tar your project directory yourself, then
multipart-POST it to the returned `url`: include every entry of `fields` as a
form field, and add the tar as a `file` field LAST in the form (required by
S3). Then call `finalize_commit` with the returned `storage_uri`.OpenlayerOpenlayerPluginrequiredAI
- Create projectcreate · Create a new project in the user's workspace.OpenlayerOpenlayerPluginrequiredAI
- Create rulecreate · Create a governance rule in a workspace.OpenlayerOpenlayerPluginrequiredAI
- Create testcreate · Create a test (goal) in a project.OpenlayerOpenlayerPluginrequiredAI
- Delete ruledelete · Delete a governance rule (custom rules only; built-in rules cannot be deleted).OpenlayerOpenlayerPluginrequiredAI
- Delete testdelete · Permanently delete a test and all of its results. This cannot be undone.
Prefer ``update_test(test_id, archived=True)`` unless the test should truly
disappear: archiving hides the test while preserving its result history, and
is reversible. Deleting is appropriate for cleaning up a test that was created
by mistake.OpenlayerOpenlayerPluginrequiredAI
- Evaluate data sourceevaluate · Trigger evaluation of every monitoring test on a data source over a time range.
The pipeline-wide counterpart to ``evaluate_test``, which runs one test at a
time. Useful for backfilling results after adding tests or after late data
arrives.
Runs asynchronously: the response carries a background-task ID and a status
URL. The requested timestamps are aligned to the tests' evaluation-window
boundaries during execution, so the window actually evaluated may be slightly
wider than the one requested.
Unlike ``evaluate_test``, this route takes no overwrite flag -- use
``evaluate_test`` when you need to overwrite existing results for one test.OpenlayerOpenlayerPluginrequiredAI
- Evaluate testevaluate · Trigger a one-off evaluation of a monitoring test over a time range.OpenlayerOpenlayerPluginrequiredAI
- Fetch data source rowsfetch · Fetch rows (traces / inference data points) from a data source.
Use this to inspect the structure and contents of production traces -- e.g.
to understand which columns exist before proposing tests.
Rows come back untrimmed, so they include each test's judge score
(``openlayer_metric_score_*`` / ``openlayer_llm_rubric_score_*``) alongside
the judge's explanation in the matching ``*_explanation_*`` column. To go the
other way -- from a failing test to the rows that caused it -- use
``fetch_failed_rows_for_goal``.OpenlayerOpenlayerPluginrequiredAI
- Fetch data source sessionsfetch · Fetch session-level aggregations for a data source.
Sessions group related traces/records; use this to analyze conversation or
request sessions before proposing session-level tests.OpenlayerOpenlayerPluginrequiredAI
- Fetch failed rows for goalfetch · Fetch the rows that made a test fail, with per-row judge scores and the
LLM judge's explanation (reasoning) for each score.
This is how you answer "why did this test fail on this row?" -- each returned
row carries a ``judge_scores`` list of
``{score_column, score, test_name, explanation}``, where ``explanation`` is
the judge's written justification, the same text the UI shows in the record
detail panel.
Rows are selected using a 3-tier filter strategy:
1) Prefer pre-computed rowsBody.columnFilters from the goal result
(update measurement names with llmSettingHash if available; invert
operators to target failed rows).
2) Otherwise construct aggregate metric filters (latency/cost/tokens).OpenlayerOpenlayerPluginrequiredAI
- Finalize commitfinalize · Create a commit from a bundle already uploaded via create_presigned_upload_url.OpenlayerOpenlayerPluginrequiredAI
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.