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 snapshot2026-09-13USmethodology registry-public-v1

Searchable tools

119,491

Authless tools

7,773

Auth required

107,252

Described tools

64,388

119,491 tools

Query restaurant metrics and forecastsexecute · Execute a metrics query against the ADECI backend API. Fetches sales and forecast data by selecting a metric and optional grouping dimensions. Use for direct data retrieval: revenue, units, clients, tickets, discount, cancellation. Pass ordinary named historical periods such as last_week and last_month unchanged; do not translate them into wall-clock ISO dates. ADECI resolves them from the selected restaurant's sales reference date, which may be its latest available sales date based on data recency, and returns the exact effective dates in data.metadata. Comparison periods previous_week and previous_month are resolved relative to the main period. Historical revenue, units, clients, and tickets can be broken into bounded 10-, 15-, 20-, or 30-minute intervals. Sub-hourly chronological output preserves dates and is limited to 1,008 potential buckets; time-of-day profiles collapse recurring clock slots and support up to 400 inclusive days. For sub_hourly use explicit start/end dates, source='sales', and no grouping, filters, comparison, ranking, or objectives. The shared client normalizes explicit sub-hourly dates to the authenticated restaurant's known sales bounds and reports that adjustment. Use covered_calendar_day_count only as a calendar-day denominator. Buckets contain whole eligible checks attributed by sale opening time, not revenue accrued during the interval. A zero may be an unobserved bucket or an observed net zero and does not distinguish closure, zero demand, returns/offsets, or missing imports. Opening-time results are descriptive, not causal or proof of profit. Supports multi-dimensional grouping via `group_by` array, including product taxonomy groupings, filtering, comparison, and ranking (top-N / bottom-N). The backend resolves the data source (sales vs forecast) from the timeframe automatically — use `source` only when you need to override this behaviour. Discount and cancellation are historical sales metrics only. Call search_catalog first when the query involves specific products, ingredients, families, or subfamilies.ADECIADECIPluginrequiredData & Analytics
Search products and ingredientssearch · Search the restaurant's product or ingredient catalog to resolve natural-language names into exact catalog IDs, families, or subfamilies. MUST be called BEFORE a metrics or KPI query whenever the query involves specific products, ingredients, families, or subfamilies. Use the returned IDs or family names to build filters entries (e.g. {"field": "product.id", "op": "in", "value": [<ids>]}) in subsequent tool calls.ADECIADECIPluginrequiredData & Analytics
Current hedge ratioscurrent · Show current FX hedge ratios given a base/default currency and one or more exposure currencies. ALWAYS call this tool when the user asks about hedge ratios, what to hedge, or their FX exposure — for example: 'my base is EUR, what is the hedge ratio against USD?', 'what are the hedge ratios for EUR vs USD and GBP?', or 'show me hedge ratios'. Do NOT answer hedge-ratio questions from general knowledge; always call this tool to get live data.FX HedgeC8 TechnologiesPluginrequiredFinance
Current hedge ratios (weighted)current · Show current FX hedge ratios using currency settings with optional weights and liability flags. Use this when the user specifies custom weights or percentages for each exposure currency, or marks an exposure as a liability (debt/payables). For simple hedge-ratio questions without custom weights, prefer current_hedge_ratios_simple.FX HedgeC8 TechnologiesPluginrequiredFinance
Detailed hedge analysisdetailhedge · Calculate detailed FX hedge analysis for a currency pair including spot rate, hedge ratio, direction, and monthly performance. Use when the user asks for a detailed hedge breakdown with custom currency settings or a specific hedge-ratio granularity (Step).FX HedgeC8 TechnologiesPluginrequiredFinance
Detailed hedge analysis (simple)detailhedge · Calculate detailed FX hedge analysis for a base currency and a single exposure currency, including spot rate, hedge ratio, direction, and monthly performance. Call this when the user asks for detailed hedge information on one specific pair — e.g., 'give me the detail hedge for EUR/USD'.FX HedgeC8 TechnologiesPluginrequiredFinance
Live FX ratesget · Get live FX exchange rates from the European Central Bank. Returns current rates for a base currency against one or more target currencies.FX HedgeC8 TechnologiesPluginrequiredFinance
Tako: Available Datatako · Find what data Tako holds on an entity or a metric, and the canonical name it holds it under. Best for: coverage questions themselves, or a metric's canonical name before a priced search. Put a company, person, or place in `q` to list the metrics tracked on it; put a metric in `q` to list the entities it covers. Add `metric` when you know the measure — you get the resolved pair and a ready-to-run `next_call`. Search on the canonical names it returns, not your own phrasing — `tako_search` matches the graph's names, not yours. A name here means the graph tracks it, not that a card exists. If the follow-up search comes back empty, say Tako has no card for it rather than rephrasing the query. Hand a node id to `tako_graph_related` to see what else connects to it.TakoTakoPluginrequiredData & Analytics
Tako: Fetch Contentstako · Fetch the full content behind a url: a web page's text, or an exportable Tako card's data rows. Batch up to 10 urls in one call — each one is billed and fails on its own. Fetch only cards that `tako_search` marked `exportable: true`. Rows bill per 1,000 delivered, so set `max_rows` when the recent rows are enough. If a page is long, such as a filing or an annual report, set `query` to get back only the passages that match. Best for: reading one source in full — a page you need to quote, or the rows behind a card you need to compute over.TakoTakoPluginrequiredData & Analytics
Tako: Graph Relatedtako · Explore what a graph node connects to — its metrics, the entities a metric covers, competitors, industry, index membership, and sources. Two modes. Pass `node_id` alone for the map: every relation group with its key, label, total, and its first 3 names. Pass `relation` to page one group, where each item comes back with the id that explores it. Read a key off the map rather than guessing — an unknown key returns an empty group, not an error. Best for: expanding a node you already resolved. Resolve a name to a node id with `tako_available_data` first. A metric listed here means the graph tracks it, not that a card exists — `tako_search` is the final check.TakoTakoPluginrequiredData & Analytics
Tako: Searchtako · Search Tako's data graph and the live web in one call: many results at once, as structured cards plus web results, with the top card rendered inline as a chart. It finds data; `tako_contents` fetches it. Each card carries a headline value, node ids, and a url — pass the url to `tako_contents` for rows (`exportable: true` cards) or a web result's full page text. When `exportable` is false the rows are locked — read the headline value from the card's `description`. Best for: breadth — fan out several narrow queries in parallel. Each query resolves one metric — for one entity, or a comparison set ("Apple revenue", "Nvidia vs AMD gross margin"); several metrics or topics in one query retrieve poorly. To learn what Tako covers, or a metric's canonical name, run `tako_available_data` first, then search on the canonical name it returns.TakoTakoPluginrequiredData & Analytics
Tako: Visualizetako · Create a public, permanent Tako card from data you already have — to chart data Tako already holds, use `tako_search`. Tako stores what you send, the card never expires, and anyone with the returned url can open it without signing in. Confirm the user wants a public card before you call, then give them the url. Never put sensitive data in `components`: no passwords, API keys, payment-card or bank details, health information, government identifiers, precise home addresses, or personal data the subject hasn't agreed to publish. Aggregate or anonymize it first, or decline. Each component is `{component_type, config}`, rendered top to bottom. A titled bar chart is two: {"components": [{"component_type": "header", "config": {"title": "Revenue"}}, {"component_type": "categorical_bar", "config": {"datasets": [{"label": "Sales", "units": "USD", "data": [{"x": "NA", "y": 500}]}]}}]}. Use `person_card` alone, never beside another component.TakoTakoPluginrequiredData & Analytics
Add Custom Itemadd · Add a custom item to the live Tingsapp item catalog after collecting dimensions and heavy-item status.TingsappTingsappPluginnoneOperations
Calculate Moving Routecalculate · REQUIRED live API call before sizes. Calculate route distance, duration, and ordered points using Tingsapp. Never estimate route data or continue if this call fails.TingsappTingsappPluginnoneOperations
Create Order Draftcreate · Create a Tingsapp draft order after the customer confirms the fixed price. Return the Tingsapp link and ask the customer to open it to complete the order. Do not place or claim payment for the order.TingsappTingsappPluginnoneOperations
Get Floorsget · REQUIRED live API call after items are confirmed. Fetch floor options from Tingsapp. Display only returned floor names; never invent, reuse, or autocomplete floor or stair options.TingsappTingsappPluginnoneOperations
Get Moving Priceget · REQUIRED final live API call for pricing. Fetch the fixed Tingsapp price from the live API after every required route, size, item, floor, date/time, and stop value has been collected from tools. Pass destination_items for the drop-off stop. Every item quantity must be allocated exactly once across all stops. Never calculate, estimate, or invent a price.TingsappTingsappPluginnoneOperations
Get Sizesget · REQUIRED after a successful calculate_moving_route call. Fetch live Tingsapp moving size choices from the API. Never answer with remembered or hard-coded sizes; display only the returned titles in exact API order.TingsappTingsappPluginnoneOperations
Prepare Floorsprepare · Fetch and validate pickup and destination floor objects from the live Tingsapp floor API by ID. Never construct floor objects manually. After this, ask for moving date/time and the mandatory stops question.TingsappTingsappPluginnoneOperations
Search Itemssearch · Search the live Tingsapp item catalog by name or code. Never invent item IDs, codes, names, or quantities.TingsappTingsappPluginnoneOperations
Select Sizeselect · Fetch the selected size again from the live Tingsapp API and return the exact price-ready size object plus API default items. Never accept or invent a size object from memory. Display only returned items.TingsappTingsappPluginnoneOperations
Show Moving Widgetshow · REQUIRED FIRST ACTION for broad-intent prompts such as "Moving app in Canada", "movers in Vancouver", or "moving price from Vancouver to Burnaby". Call this tool before greeting, asking for addresses, or giving any booking text. It renders the standalone Tingsapp moving widget in ChatGPT; then continue the moving workflow.TingsappTingsappPluginnoneOperations
Start Moving Quotestart · Use this before replying to any customer who wants to book a move, schedule movers, arrange a move, place a moving order, or get a Tingsapp moving quote. It returns the required workflow, prevents asking all missing details at once, and must be followed all the way through fixed-price calculation without adding fallback commentary.TingsappTingsappPluginnoneOperations
Build a TEAM 30 project planteam30 · Use this when a concrete project needs an ideal outcome, phases, completion criteria, QA evidence, and a safe next step. Do not use it for a one-line factual question.TEAM 30 — AI Company OSTEAM 30PluginnoneAI
Check a TEAM 30 approval gateteam30 · Use this before a planned action to determine whether the user must explicitly approve it. This tool only evaluates the gate and never performs the action.TEAM 30 — AI Company OSTEAM 30PluginnoneAI
List TEAM 30 rolesteam30 · Use this when the user wants to discover TEAM 30 roles or find which specialties are available. Do not use it to perform the user's task.TEAM 30 — AI Company OSTEAM 30PluginnoneAI
Route a task to TEAM 30team30 · Use this when the user has a concrete goal and needs the best TEAM 30 role, a scope lock, approval boundaries, and the next action. This plans the route but does not execute external actions.TEAM 30 — AI Company OSTEAM 30PluginnoneAI
Compare Versionscompare · Compare the text of a CFR section at two different dates. Useful for understanding what changed in a regulatory amendment. Returns the parsed text at both dates side by side. You can then diff the paragraphs to identify specific changes. Dates must be in YYYY-MM-DD format and within the eCFR's tracking range (January 2017 to present). Both dates must not exceed the title's up_to_date_as_of value. This tool always returns the section-level XML parsed -- pass a small section_id like '15.305', not a whole part. Whole-part comparisons can exceed 100 KB per side.eCFR MCP1102toolsPluginnoneOperations
Find FAR Definitionfind · Search for a term's definition in FAR 2.101 (master definition section). FAR 2.101 contains definitions used throughout the Federal Acquisition Regulation. This tool fetches the full section and searches for paragraphs containing the term, returning matching paragraphs with surrounding context. Note: FAR 2.101 is large (~109KB XML). This tool parses the full section server-side and returns only matching paragraphs. term must be at least 3 characters. max_matches caps returned matches (default 20, max 100); common terms like 'offeror' hit many paragraphs.eCFR MCP1102toolsPluginnoneOperations
Find Recent Changesfind · Find CFR sections that have been modified since a given date. Uses the search API with last_modified_on_or_after filter to find sections amended after the specified date. Returns section identifiers, headings, and excerpts, most recently amended first. since_date must be in YYYY-MM-DD format. Results are capped at 10,000 by the API. Use title/chapter/part filters to narrow if needed. Common pattern: find FAR changes since a specific date to check for regulatory updates that might affect ongoing acquisitions.eCFR MCP1102toolsPluginnoneOperations
Get Ancestryget · Get the breadcrumb hierarchy path for a section, part, or appendix. Returns ancestors from title down to the target node: title > chapter > subchapter > part > subpart > section. Useful for understanding where a section sits in the CFR hierarchy and what regulation it belongs to. part/section/appendix accept int or string.eCFR MCP1102toolsPluginnoneOperations
Get CFR Contentget · Get the full text of a CFR section, subpart, part, or appendix. This is the primary workhorse for reading regulatory text. Returns parsed clean text by default (heading, paragraphs, citations, plus tables and editorial_notes when present). Set raw_xml=True to get the original XML instead. Specify the narrowest scope possible to keep responses manageable: - section='15.305' for a single FAR section - subpart='15.3' for a subpart - part='15' for an entire part (can be large) - chapter='1' for an entire chapter (often >1 MB, avoid) - appendix='Appendix A to Chapter 2' (with chapter='2') for a DFARS appendix Date auto-resolves to the latest available if not provided. Do NOT use today's date directly -- eCFR lags 1-2 business days and today often 404s. Title 48 = FAR/DFARS. Chapter 1 = FAR (Parts 1-99), Chapter 2 = DFARS (Parts 200-299). Other chapters = agency FAR supplements (GSAR, VAAR, HSAR, etc.). For DFARS clauses, use chapter='2' (e.g., section='252.227-7014'). part/subpart/section accept int or string. Common prefix mistakes like section='FAR 15.305' or '48 CFR 15.305' are stripped automatically, and trailing paragraph cites like section='15.305(a)(2)' resolve to the base section '15.305'.eCFR MCP1102toolsPluginnoneOperations
Get CFR Structureget · Get the hierarchical table of contents for a CFR title or subset. Returns a nested tree of titles, chapters, parts, subparts, and sections with identifiers, descriptions, and byte sizes. IMPORTANT: Does NOT support section-level filtering (returns 400). Use part or subpart, then walk the children to find sections. Common patterns: - chapter='1' for all FAR parts - chapter='2' for all DFARS parts - part='15' for FAR Part 15 structure - subpart='15.3' for just that subpart's sections part/subpart/chapter/appendix accept int or string.eCFR MCP1102toolsPluginnoneOperations
Get Correctionsget · Get editorial corrections for a CFR title. Returns a list of corrections with CFR references, corrective actions, error dates, and FR citations. Useful for checking whether a section's current text has been corrected since its last amendment. limit caps the number of corrections returned (default 50, max 1000). since_year further filters to corrections with year >= since_year. Title 48 has ~280 corrections across all years; use since_year to focus on recent ones.eCFR MCP1102toolsPluginnoneOperations
Get Latest Dateget · Get the most recent available date for a CFR title. CRITICAL: eCFR lags 1-2 business days behind the Federal Register. Using today's date on versioner endpoints causes 404 errors. Call this first to get the safe date, then pass it to other tools. Default title 48 = Federal Acquisition Regulations System (FAR, DFARS, and all agency supplements). Other common titles: 2 (Grants/Agreements), 5 (Administrative Personnel), 29 (Labor), 41 (Public Contracts). Raises ValueError for titles 1-50 that are reserved (no content).eCFR MCP1102toolsPluginnoneOperations
Get Version Historyget · Get the version history of a CFR section, subpart, or part. Returns a list of content versions with dates, amendment info, and whether each version was a substantive text change vs editorial. The 'substantive' field is key: True = the regulatory text actually changed. False = only editorial/formatting change. History goes back to January 2017 only. Pre-2017 changes are not tracked. part/subpart/section accept int or string.eCFR MCP1102toolsPluginnoneOperations
List Agencieslist · List all agencies with their CFR title and chapter references. Returns agency names, slugs, and which CFR titles/chapters they own. Useful for finding which chapter corresponds to an agency's FAR supplement. summary_only (default True) strips the `children` and most of `cfr_references` to keep the response compact (~20 KB vs ~100 KB). References owned by child agencies are merged into the parent row, so chapter lookups like DFARS (chapter 2, on a DoD child agency) still work in summary mode. Set False for the full raw payload including children.eCFR MCP1102toolsPluginnoneOperations
List Sections in Partlist · List all sections in a FAR/DFARS part with their headings. Returns a flat list of sections extracted from the structure tree. Useful for understanding the scope of a FAR part before drilling into specific sections. Default chapter='1' (FAR). Use chapter='2' for DFARS. part_number accepts int or string.eCFR MCP1102toolsPluginnoneOperations
Lookup FAR Clauselookup · Convenience tool: look up the current text of a FAR or DFARS clause. Pass a section identifier like '15.305', '52.212-4', '2.101', etc. Default chapter='1' (FAR). Use chapter='2' for DFARS (e.g., '252.227-7014'). Auto-resolves the latest available date. Returns parsed clean text with heading, paragraphs, and citations. Common FAR sections: 2.101 (Definitions), 9.104-1 (Responsibility), 15.305 (Proposal Evaluation), 19.502-2 (Small Business Set-Asides), 52.212-4 (Commercial Terms), 52.212-5 (Required Commercial Terms).eCFR MCP1102toolsPluginnoneOperations
Search CFRsearch · Full-text search across the Code of Federal Regulations. Returns matching sections with excerpts, headings, scores, and hierarchy. CRITICAL: Set current_only=True (default) to search only in-effect text. Without it, search returns ALL historical versions including superseded, so a section amended 5 times appears 5 times. Search caps at 10,000 total results. Use hierarchy filters (title, chapter, part) to narrow if you hit the cap. order controls result ordering: 'relevance' (default), 'newest_first', 'oldest_first', 'hierarchy', or 'citations'. agency_slugs filters to one or more agencies (single slug string or a list, e.g. 'defense-acquisition-regulations-system'). Use list_agencies() to find slugs. last_modified_after/before use YYYY-MM-DD format and filter by the date sections were last amended. Useful for finding recent regulatory changes. per_page accepts 1 to 5000 (default 20); paginate with page for more.eCFR MCP1102toolsPluginnoneOperations
Check emission compliance deadlinesgetemissioncompliancedeadline · Get emission compliance deadlines and status for reporting programs. Ref: https://developers.geotab.com/myGeotab/apiReference/methods/GetEmissionComplianceDeadline/MyGeotab MCPGeotabPluginrequiredOperations
Count entities by typegetcountof · Count entities by type. Faster than Get when you only need counts. Includes active and inactive. Examples: typeName='Device' | typeName='Trip',search={fromDate:'2024-01-01T00:00:00Z',toDate:'2024-01-02T00:00:00Z'}. Ref: https://developers.geotab.com/myGeotab/apiReference/methods/GetCountOf/MyGeotab MCPGeotabPluginrequiredOperations
Create a new entityadd · Create a new entity. Returns the new entity's ID. Call GetEntity first to discover required fields. Examples: typeName='Zone',entity={name:'Office',points:[{x:-79.3,y:43.6},...],groups:[{id:'GroupCompanyId'}]} | typeName='Rule',entity={name:'Speed Alert',baseType:'Custom',condition:{...}}. Ref: https://developers.geotab.com/myGeotab/apiReference/methods/Add/MyGeotab MCPGeotabPluginrequiredOperations
Decode VINs to vehicle infodecodevins · Decode VINs to extract vehicle make, model, and year. Accepts batch of 17-char VINs (auto-normalized/deduped).MyGeotab MCPGeotabPluginrequiredOperations
Delete an entityremove · Remove an entity and its associated data. Only 'id' field required in entity. Device/User/Driver use soft delete by default (recoverable); set hard_delete=True for permanent removal. Ref: https://developers.geotab.com/myGeotab/apiReference/methods/Remove/MyGeotab MCPGeotabPluginrequiredOperations
Dismiss fault recordsdismissfaults · Dismiss fault records to mark them as acknowledged. Void operation (success = no error).MyGeotab MCPGeotabPluginrequiredOperations
Download media file contentdownloadmediafile · Download file content for a MediaFile entity. Returns base64-encoded content. Ref: https://developers.geotab.com/myGeotab/apiReference/methods/DownloadMediaFile/MyGeotab MCPGeotabPluginrequiredOperations
Enroll devices for emissionsemissionenrolldevices · Register devices for Clean Truck Check emission compliance tracking. Ref: https://developers.geotab.com/myGeotab/apiReference/methods/EmissionEnrollDevices/MyGeotab MCPGeotabPluginrequiredOperations
Generate report filesendreportprocessingrequest · Queue async report file generation (Excel/PDF). Returns storage ID for polling.MyGeotab MCPGeotabPluginrequiredOperations
Generate video playback URLgetmediaurl · Generate a video playback deep-link URL from a SearchMedia result's mediaRequestId. Returns URL and embeddable iframeSrc.MyGeotab MCPGeotabPluginrequiredOperations

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.