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 snapshot2026-09-11USmethodology registry-public-v1
Searchable tools
113,017
Authless tools
7,424
Auth required
100,766
Described tools
61,166
113,017 tools
- List MCP serversagents · List the MCP servers registered in the workspace.ElevenLabsElevenLabs
PluginrequiredContent & Design - List agentsagents · List ElevenLabs Agents in the authenticated workspace.ElevenLabsElevenLabsPluginrequiredContent & Design
- List branchesagents · List the branches of an ElevenLabs Agent.ElevenLabsElevenLabsPluginrequiredContent & Design
- List conversation triage ticketsagents · List an agent's conversation triage tickets, ordered by most recently created first. These are tickets about the agent's own performance on a conversation (for triage with Architect), not tickets an agent opens for end users.ElevenLabsElevenLabsPluginrequiredContent & Design
- List conversationsagents · List conversations for the authenticated workspace, optionally filtered to a specific agent via agent_id.ElevenLabsElevenLabsPluginrequiredContent & Design
- List flow node typescreative · List the node types and models this workspace can actually run in its region, with their default model. Call this before adding a node rather than guessing a node type.ElevenLabsElevenLabsPluginrequiredContent & Design
- List knowledge baseagents · List the documents in the workspace knowledge base.ElevenLabsElevenLabsPluginrequiredContent & Design
- List phone numbersagents · List the phone numbers in the workspace.ElevenLabsElevenLabsPluginrequiredContent & Design
- List proceduresagents · List the procedures on an agent branch.ElevenLabsElevenLabsPluginrequiredContent & Design
- List test runsagents · List test-suite invocations (test runs) in the workspace.ElevenLabsElevenLabsPluginrequiredContent & Design
- List testsagents · List the agent response tests in the workspace.ElevenLabsElevenLabsPluginrequiredContent & Design
- List toolsagents · List the ElevenLabs Agent tools in the workspace.ElevenLabsElevenLabsPluginrequiredContent & Design
- List voicescreative · Search the voices this workspace can speak with, to choose one for a speech node instead of asking the user for a voice id.ElevenLabsElevenLabsPluginrequiredContent & Design
- Merge branchagents · Merge a source branch into its target branch.ElevenLabsElevenLabsPluginrequiredContent & Design
- Preview branch mergeagents · Preview the changes that merging a source branch would apply, without mutating anything.ElevenLabsElevenLabsPluginrequiredContent & Design
- Query agent knowledge base (RAG)agents · Run a RAG query against an ElevenLabs Agent's knowledge base.ElevenLabsElevenLabsPluginrequiredContent & Design
- Resolve conversation referenceagents · Resolve a conversation reference (e.g. a dashboard URL or share link) to its conversation.ElevenLabsElevenLabsPluginrequiredContent & Design
- Run flow nodescreative · Start generating on nodes that already exist. Charges the workspace, so poll creative_get_flow_run_status rather than calling this again.ElevenLabsElevenLabsPluginrequiredContent & Design
- Run testsagents · Run a suite of tests against an ElevenLabs Agent.ElevenLabsElevenLabsPluginrequiredContent & Design
- Save a designed voicecreative · Save one preview from creative_design_voice into the workspace's voice library, returning a voice_id usable with creative_generate_speech. Call this only once the user has picked which preview to keep.ElevenLabsElevenLabsPluginrequiredContent & Design
- Save view statecreative · For the view to call as its state changes, not for you — never call this yourself. Persists opaque UI state under view_state_id so a view reopened in an old chat can rehydrate what it showed.ElevenLabsElevenLabsPluginrequiredContent & Design
- Search conversation messagesagents · Search the text of conversation transcripts and return the matching messages, each with its conversation_id, transcript_index, message text, and relevance score. This is the only way to find conversations by something that was said; agents_list_conversations filters on structured attributes and cannot search transcript text. Wrap text_query in double quotes to match the terms as written (do this for error codes, identifiers, and anything a user pasted); leave it unquoted to match fuzzily, tolerating one character of difference per term. Neither form is a substring or phrase match -- a multi-word query matches messages containing all of the terms in any position -- so read the returned text before treating a hit as an occurrence. Results are messages, not conversations: deduplicate by conversation_id before counting.ElevenLabsElevenLabsPluginrequiredContent & Design
- Search knowledge baseagents · Search the workspace knowledge base by content.ElevenLabsElevenLabsPluginrequiredContent & Design
- Show flow resultscreative · Put a run's generations back in front of the user, rendering the same view a run starts with. Use this when the user should see results that are not already showing — for example after a run finished off-screen, or when the user asks to see something already generated. Call with the flow_id and session_ids a run returned.ElevenLabsElevenLabsPluginrequiredContent & Design
- Update MCP serveragents · Update the configuration of a registered MCP server.ElevenLabsElevenLabsPluginrequiredContent & Design
- Update a flow nodecreative · Update an existing node's model, parameters, prompt, or label. BEFORE passing model_parameters or model_id: call creative_get_model_schema(node_type, model_id) for the effective model_id during the current turn — parameter names and allowed values vary by model, and an invented name fails validation instead of being coerced. Switching model_id resets model_parameters and can change the node's input ports — the result's input_ports names the new ones, and orphaned_edges names any connection the switch dropped, which creative_connect_flow_nodes can then rewire. This never starts a generation; call creative_run_flow_nodes for that.ElevenLabsElevenLabsPluginrequiredContent & Design
- Update agentagents · Update common Conversational AI agent settings from a compact set of fields. API reference: https://elevenlabs.io/docs/api-reference/agents/updateElevenLabsElevenLabsPluginrequiredContent & Design
- Update branchagents · Update a branch of an ElevenLabs Agent.ElevenLabsElevenLabsPluginrequiredContent & Design
- Update code toolagents · Update a code tool. This PATCH replaces the whole tool config, so supply either `body` (the full replacement config) or all of name/description/source_code -- omitting `body` drops any parameters, execution_context, dynamic_variables, or response_mocks the tool previously had. Requires an Enterprise workspace plan. Docs: https://elevenlabs.io/docs/eleven-agents/customization/tools/code-toolsElevenLabsElevenLabsPluginrequiredContent & Design
- Update conversation triage ticketagents · Update a conversation triage ticket's comment, status, and/or assignee.ElevenLabsElevenLabsPluginrequiredContent & Design
- Update knowledge base documentagents · Update a knowledge base document's metadata.ElevenLabsElevenLabsPluginrequiredContent & Design
- Update phone numberagents · Update a phone number (e.g. assign it to an agent).ElevenLabsElevenLabsPluginrequiredContent & Design
- Update procedure draftagents · Update the draft of a procedure on an agent branch.ElevenLabsElevenLabsPluginrequiredContent & Design
- Update toolagents · Update an ElevenLabs Agent tool.ElevenLabsElevenLabsPluginrequiredContent & Design
- Upload a flow referencecreative · Use this when the user wants a file from their own machine as a reference for a generation — for example "change the cat to a dog in this image". Returns at once with a node_id already on the flow — wire it with connect_from right away. The node is EMPTY until the user picks a file in the rendered picker; once they do, it is uploaded into that same node, and completion is published as widget context. This starts no generation and spends no credits.
Not for an asset already in the workspace library — use creative_get_available_assets plus creative_add_flow_asset_node for that.ElevenLabsElevenLabsPluginrequiredContent & Design
- BaZi Chart 八字排盘bazi · Use this tool when the user asks to cast or interpret one or more concrete BaZi/Four Pillars charts, analyze luck cycles or annual influences from chart data, or compare relationship compatibility using BaZi charts. The chart subjects may be the user, other people, multiple people, public or historical figures, or hypothetical examples. Do not call it for general astrology explanations, comparisons between astrology systems, weather, entertainment recommendations, translation, chitchat, or other unrelated requests that need no concrete chart calculation. Merely mentioning Chinese astrology or BaZi is not enough reason to call the tool. For an unrelated request, answer directly without this tool even when the AskLingxi app is selected. Cast a BaZi (Four Pillars of Destiny) chart from a birth date, time, gender and birthplace — four pillars, five-element distribution and chart structure. Also known as 八字排盘 / 四柱命理 / 사주팔자 / 사주 명식 / 四柱推命. Requires the birth date (year, month, day) and gender. If either is missing, ask the user for it in chat before calling the tool; never guess or invent it. The birth hour and birthplace are optional but worth asking for in the same turn: without an hour the chart is cast with three pillars instead of four, and the birthplace only sets the time zone. Supports progressive slot filling across chat turns: keep the chart task pending and merge follow-up user input, but call this tool only after the required fields are complete. Pass `locale` set to the language the user is writing in. Figures come from the AskLingxi (asklingxi.com) engine's deterministic calculation — they are computed, not model-generated. For traditional-culture and entertainment interest only; not health, financial or other professional advice.AskLingxiAskLingxiPluginnoneConsumer & Lifestyle
- cancel_bookingcancel · Cancel an authenticated customer’s eligible StyleCliq appointment. Call only after the customer explicitly confirms they want to cancel it.StyleCliq Salon BookingStyleCliqPluginrequiredConsumer & Lifestyle
- create_bookingcreate · Create a pay-at-salon appointment for the authenticated customer. Call only after the customer explicitly confirms the final salon, stylist, services, date, and time. This creates a private reservation in StyleCliq; no payment is collected in ChatGPT.StyleCliq Salon BookingStyleCliqPluginrequiredConsumer & Lifestyle
- get_available_slotsget · Get available appointment times for one listed stylist at one published salon on a future date. It returns only available times, never other customers’ booking information.StyleCliq Salon BookingStyleCliqPluginrequiredConsumer & Lifestyle
- get_booking_detailsget · Get complete details for one booking owned by the authenticated customer.StyleCliq Salon BookingStyleCliqPluginrequiredConsumer & Lifestyle
- get_salon_detailsget · Get a published salon’s bookable services, stylist summaries, hours, amenities, and public review summary. It does not return contact details or precise coordinates.StyleCliq Salon BookingStyleCliqPluginrequiredConsumer & Lifestyle
- list_my_bookingslist · List the authenticated customer’s StyleCliq bookings with pagination and an optional lifecycle filter.StyleCliq Salon BookingStyleCliqPluginrequiredConsumer & Lifestyle
- rebook_bookingrebook · Create a fresh pay-at-salon appointment using services from an authenticated customer’s previous booking. It revalidates the salon, stylist, services, and requested slot; it never clones an old reservation. Call only after explicit confirmation.StyleCliq Salon BookingStyleCliqPluginrequiredConsumer & Lifestyle
- reschedule_bookingreschedule · Reschedule an authenticated customer’s eligible booking. Call only after the customer explicitly confirms the new date and time.StyleCliq Salon BookingStyleCliqPluginrequiredConsumer & Lifestyle
- search_salonssearch · Find published StyleCliq salons. Use city for location requests (for example, Bhubaneswar); use query only for a service or salon-name keyword. Returns all matching published salons up to the requested page limit, including open/closed status.StyleCliq Salon BookingStyleCliqPluginrequiredConsumer & Lifestyle
- Find UI Materialsfind · Find Uizze-hosted, license-recorded fonts, icons, animated icons, or Packs for a named role. Exact Pack content requires an explicit user selection.UizzeUizzePluginrequiredDeveloper Tools
- Find UI Referencesfind · Find one to three useful full-screen iOS references or complete hosted Web Pack visuals for a concrete UI question. For a new search, omit selectedIds or pass []. For exact inspection, pass only IDs copied from previous Uizze results; never invent IDs.UizzeUizzePluginrequiredDeveloper Tools
- Calcular Matriz del Destinocalcular · Calcula una Matriz del Destino a partir de una fecha de nacimiento. Úsalo cuando el usuario pida su matriz, energías, talentos, propósito, canal financiero o aspectos relacionales según la Matriz del Destino.Matriz del DestinoMatriz del DestinoPluginnoneConsumer & Lifestyle
- Calcular compatibilidad de parejacalcular · Calcula la Matriz de Compatibilidad de dos personas a partir de sus fechas de nacimiento. Úsalo cuando el usuario pregunte por compatibilidad, energía de la pareja, propósito compartido o dinámica financiera/relacional según la Matriz del Destino.Matriz del DestinoMatriz del DestinoPluginnoneConsumer & Lifestyle
- Cash positionget · Money actually received over a date range, split by payment method — the daily-close figure.GadgetOSGadgetOSPluginrequiredCommerce
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.