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
- Get a report by idatlas · Fetches one report, including its result once status is "completed" and a shareable publicUrl. Free. Reports are created through the REST API, not from this connector; use atlas_list_reports to find an id, then this to read the result.RED Atlas APIRED Atlas
PluginrequiredData & Analytics - Get a single recordatlas · Fetches one record by id for an entity type in a market. Costs credits for the fields returned; use `fields` to limit them. Includes the canonical `atlasUrl` app link for listings/parcels/properties.RED Atlas APIRED AtlasPluginrequiredData & Analytics
- List available entities for a marketatlas · Lists the entity types (properties, listings, parcels, …) available in a market and their endpoints. Free. Start here when unsure what data a market has.RED Atlas APIRED AtlasPluginrequiredData & Analytics
- List reportsatlas · Lists the account’s generated reports (all plans). Free.RED Atlas APIRED AtlasPluginrequiredData & Analytics
- Location market profileatlas · Full market profile for ONE location (city, neighborhood or sub-neighborhood): sale and lease medians with monthly series, inventory, days on market, yield, demographics, quality-of-life scores, nearby POIs and local news — in a single call. Resolve the locationId with atlas_lookup_location first. EVERY metric is an envelope: { value, unit, yoy, vsParent, series, availability, caveats }. Read `availability` before quoting a number — "unavailable" means we genuinely cannot compute it (listed with the reason in meta.notAvailable), and "partial" means the value is real but the caveats change how it should be read (e.g. deed_lag_truncated_12mo, mixed_census_vintages, current_value_only). Never present a metric without its caveats, and never fill an unavailable metric from another source.RED Atlas APIRED AtlasPluginrequiredData & Analytics
- Market report for one asset classatlas · Profiles ONE asset class (office, retail/business, warehouse, residential, ...) in a single call: for-sale and for-rent aggregates, a building-class (A/B/C) breakdown, the top municipalities by asking value, month-over-month velocity, AND the total stock of that use — property count plus built area — which yields `shareOfStockListed`, the percent of the stock currently on the market. Use this instead of chaining atlas_get_stats + atlas_top_by + atlas_velocity by hand. COST: this runs ~7 metered queries and is billed as such (reported in meta.creditCost) — it saves round-trips, not credits. Outlier-flagged placeholder prices are excluded from every money figure, and the area sum drops impossible outliers (see inventory.excludedByAreaCap — quote it with the total). Read meta.notAvailable before reporting anything it lists as missing, and never estimate those.RED Atlas APIRED AtlasPluginrequiredData & Analytics
- Market velocity (new records per period + trend)atlas · How fast a market is moving: the count of new records in the current period vs the previous equal-length period, with the absolute and percent change. E.g. new listings or permits this month vs last month. Charges a fixed credit cost (meta.creditCost). Entities without a usable date field return an error — pass `dateField` to override the default.RED Atlas APIRED AtlasPluginrequiredData & Analytics
- Multi-entity text searchatlas · Free-text search across entity types in a market (addresses, names, places). Charges credits per call. Returns grouped hits per entity bucket; follow up with atlas_get_record for full details. On a lower plan, find records with atlas_query_data + an `address.like` filter instead.RED Atlas APIRED AtlasPluginrequiredData & Analytics
- One-call market summaryatlas · Profiles a market in a single call: the aggregated stats block (counts, price/area aggregates, percentiles and derived metrics like median price per m²), a count-per-month trend for the last year, and — when `groupBy` is set — a ranked breakdown by that dimension. Use this instead of chaining atlas_get_stats + atlas_top_by when you want an overview. Billed as one aggregator call (meta.creditCost), the trend/breakdown add no extra cost.RED Atlas APIRED AtlasPluginrequiredData & Analytics
- Parcel contacts already in Atlas (premium)atlas · Contacts Atlas ALREADY HOLDS for a parcel, harvested from listings, permits and other internal sources — no external vendor is called and nothing new is looked up. Each row carries its provenance (source, typePerson, permitId, genericListingId): a broker, a contractor or a permit applicant is an ASSOCIATION with the parcel, NOT the owner and NOT a party to any sale — never present one as buyer, seller or owner. For who OWNS it (Puerto Rico) query the `owners` entity; for a fresh skip-trace of the owner/occupant use atlas_enrich_contacts; for who bought or sold, read the deed parties in transactions.scripturesJson. Premium: charges credits per call (meta.creditCost); an empty result costs nothing.RED Atlas APIRED AtlasPluginrequiredData & Analytics
- Plan catalog and the credit price of everythingatlas · The published plan ladder plus the credit price of every billable thing. FREE. Plans are the RED Atlas platform tiers with their monthly price, included tokens (1 token = 1 report or document) and included seats. Credit costs are per record by entity, per aggregation, per add-on field, per contacts call, per enrichment and per report — that half is what a data call actually spends. Use it to price a piece of work before running it, to explain a bill, and to compare plans. This is the CATALOG, not the caller: for what THIS account is on and how much of it is left, read atlas_my_plan — an account's API call allowance comes from its API package and is reported there, not here.RED Atlas APIRED AtlasPluginrequiredData & Analytics
- Query recordsatlas · Lists records of an entity type in a market with pagination, filters, sorting and field projection. Costs credits per record returned — keep `limit` small and use `fields` to request only what you need. Each record includes a server-built `atlasUrl` (canonical app link) for listings/parcels/properties — link to that, never to a record's source `url`. Response envelope: { data, meta (creditCost), rateLimit (limit/remaining/reset) }.RED Atlas APIRED AtlasPluginrequiredData & Analytics
- Rank/count records by a dimensionatlas · Terms aggregation: the top values of `groupBy` (e.g. propertyType, status, cityId) with their record counts and an optional sub-metric. One call replaces paging + manual counting. Charges a fixed credit cost (meta.creditCost).RED Atlas APIRED AtlasPluginrequiredData & Analytics
- Read the API documentationatlas · Reads the official RED Atlas API docs. Without a topic it returns the section index; with a topic (e.g. "filtering", "credits", "rate limits", "avm") it returns the matching sections. Free. Prefer this over guessing parameters.RED Atlas APIRED AtlasPluginrequiredData & Analytics
- Resolve location idsatlas · Translates human location names into the stable ids (regionId, cityId, neighborhoodId, …) that atlas_query_data filters expect, and returns boundary polygons. Free (0 credits). kind-specific parameters: cities accepts regionId; neighborhoods accepts cityId; sub-neighborhoods requires neighborhoodIds; zip-codes requires zipCode; buildings requires name and accepts cityId/neighborhoodId. Set includeGeometry to get GeoJSON boundary polygons for markets, regions, cities, neighborhoods, sub-neighborhoods and zip-codes — polygons are large, so keep `size` small and raise `simplify` (degrees; higher = coarser) if the result is truncated. sectors/sub-sectors/micro-sectors are a shared property-USE classification (e.g. "Office"), NOT geographic areas — name lookups with no polygon; sub-sectors accepts sectorId and micro-sectors accepts subsectorId to scope to a parent.RED Atlas APIRED AtlasPluginrequiredData & Analytics
- This account: plan, what it includes, credits leftatlas · The CALLING account's own plan and BOTH of its monthly ceilings, because both gate every data call: `calls` (1 per request, from the account's API package) and `credits` (per record/aggregation, from the organization pool or the account's own allowance). Also the credits burned per calendar month over the last 6. FREE — costs nothing. Use it for "how much have I got left", "what am I paying for", "is this on my plan", and — with atlas_pricing — for "should I move plan", where the monthly burn is the number to size against, not the current period, which is a partial month. QUOTE THE CEILING THAT BINDS: an account can be far from its call limit and out of credits, or the reverse, so name which one is close before advising anything. `unlimited: true` on either means there is no allowance to spend down — `remaining` is then null because there is no ceiling, NOT because the balance is zero. It cannot change the plan or buy credits — follow `manageBillingUrl` for that.RED Atlas APIRED AtlasPluginrequiredData & Analytics
- Audit a marketplace statementaudit · Use this when the user supplies one redacted CSV or TSV marketplace statement with explicit fee and funding columns. Detect marketplace and money columns, remove exact duplicates only when transaction identity supports it, calculate observed cost and payout variance, and return evidence-backed operator actions. For DoorDash, do not use Financial Simplified Transactions because Customer discounts does not identify who funded them; request Detailed Transactions or Payout Summary instead. For PDF, screenshot, or spreadsheet evidence, extract structured totals first and use reconcile_marketplace_payout. Do not use credentials or scrape a marketplace.Never86'd Marketplace AuditNever86'dPluginnoneFinance
- Compare marketplace channelscompare · Use this when the user supplies two to six marketplace channel summaries for the same date range and identical restaurant scope. Compare eligible sales, true marketplace cost, all-in take rate, supported addressable leak, and payout variance. Do not use for month-to-month analysis; return a blocker rather than declaring a winner when scopes differ.Never86'd Marketplace AuditNever86'dPluginnoneFinance
- Compare marketplace statement periodscompare · Use this when the user supplies two to twenty-four finalized, non-overlapping monthly statement summaries from the same marketplace and identical restaurant scope. Return chronological true-cost and take-rate trends, disclosure warnings, and evidence gaps without claiming causation or recovered cash. Do not use for cross-channel ranking or mismatched scopes.Never86'd Marketplace AuditNever86'dPluginnoneFinance
- Inspect Toast Order Detailsinspect · Use this when the user supplies a redacted Toast OrderDetails.csv plus the exact location, business date, IANA timezone, and business-day cutoff. Classify a marketplace row only when at least two channel signals agree; quarantine incomplete, conflicting, out-of-scope, or wrong-location rows. Return POS Amount evidence, not gross sales, marketplace fees, or payout proof. Do not use if Tab Names, guest data, credentials, or payment-card fields remain.Never86'd Marketplace AuditNever86'dPluginnoneFinance
- Inspect a PDQ Z-reportinspect · Use this when the user supplies one redacted daily PDQ Z-report as a native-text PDF or plain-text export. Extract daily aggregate POS evidence only. Never attribute PDQ Delivery to DoorDash, Uber Eats, or Grubhub, and never treat it as marketplace fee or payout proof. Do not use for image-only PDFs, credentials, guest data, or multi-day order matching.Never86'd Marketplace AuditNever86'dPluginnoneFinance
- Reconcile a marketplace payoutreconcile · Use this when ChatGPT has already extracted one marketplace statement scope from a redacted PDF, screenshot, spreadsheet, or typed evidence. Calculate true marketplace cost and reconcile expected payout. Include filename/page provenance, omit unreadable lines, and use zero only when the source explicitly shows zero or a disclosed bundled fee. Do not use credentials or invent missing values.Never86'd Marketplace AuditNever86'dPluginnoneFinance
- Render a Never86'd evidence cardrender · Use this only after a Never86'd inspection, audit, reconciliation, or comparison tool returns a completed report. Pass that exact report without recalculating, summarizing, adding, or altering any value. Do not use with hand-authored or unrelated financial data.Never86'd Marketplace AuditNever86'dPluginnoneFinance
- Add Identity to Watch Listadd · Add an identity to the company Person-of-Interest watch list, or update its entry if it is already listed (idempotent). Pick a reason (new_hire, pip, final_warning, investigation, offboarding, other), optionally attach a note, and set the on-expiry action (auto_remove or keep_until_reviewed). Entries expire after a fixed 90 days. Requires an Admin role (HR/Legal/User/IT cannot call). Resolve an email to a UUID with get_identity_uuid first.Above SecurityAbove SecurityPluginrequiredSecurity
- Deep Investigative Searchsearch · Deep escalation search for broad investigative questions the direct entity tools cannot answer. Use this ONLY when the focused tools (get_identity_*, get_incident*, get_device/list_devices, get_applications/get_extensions, get_alerts, get_insights, list_high_risk_identities, query_audit_logs) genuinely cannot answer — questions that require searching and correlating raw user activity and events across the tenant (e.g. "has anyone exfiltrated data to personal cloud storage in the last month?", "which users accessed competitor sites and also touched sensitive files?"). This is the slow, heavyweight path: it triggers a background investigation that searches and correlates raw events end-to-end. Results are NOT returned inline by this tool. Calling it signals that you want to escalate; the deeper search runs in the background and its answer is delivered to this thread when ready. Do NOT call it for a question a direct tool can answer, and do NOT expect data back in the same turn. Disambiguation from global_search: use global_search for a FAST cross-entity lookup of already-known objects (find a specific identity, incident, device, or application by name/identifier); use search_discovery for a SLOW deep search that explores and correlates raw activity to answer an open-ended investigative question.Above SecurityAbove SecurityPluginrequiredSecurity
- Find Identity by Emailget · Resolve an email to its monitored identity, returning the identity's UUID, name, email, risk score, and type — or a not-found error if the email is not a monitored identity in this tenant. Returns no overview, incidents, devices, or observations.Above SecurityAbove SecurityPluginrequiredSecurity
- Get Device Detailsget · Get one device by UUID. Returns name, email, status, last-seen, created plus the linked identity (name, email, risk score) when associated.Above SecurityAbove SecurityPluginrequiredSecurity
- Get Executive Reportget · Get the latest executive report or a specific one by UUIDAbove SecurityAbove SecurityPluginrequiredSecurity
- Get Identity 360 Overviewget · Get an identity's Identity 360 overview: risk score, risk tier, free-text observations, risk categories, linked devices, and incident COUNTS ONLY (total / open / critical). Does NOT return individual incident titles, descriptions, severities, or remediation steps.Above SecurityAbove SecurityPluginrequiredSecurity
- Get Identity Activityget · Return recent event activity (chronological, newest first) for ONE identity by UUID. Returns paginated events with type/url/path/text/timestamp/important fields. Safe for HR/Legal roles (Identity-360 scope).Above SecurityAbove SecurityPluginrequiredSecurity
- Get Identity Risk Scoreget · Get one identity's current risk score (numeric), risk tier, and last-updated timestamp. Returns no incident, device, or observation data.Above SecurityAbove SecurityPluginrequiredSecurity
- Get Incident Detailsget · Get the full detail of ONE incident by UUID: severity, status, verdict, type, the involved identity, executive summary, behavioral analysis, risk assessment, metrics, matrix tags, and an activity timeline. This is the authoritative source for what a specific incident involved.Above SecurityAbove SecurityPluginrequiredSecurity
- Get Incident Timelineget · Return the chronological activity timeline for ONE incident by UUID. Includes events, actions, status transitions. Cheaper than refetching the full incident.Above SecurityAbove SecurityPluginrequiredSecurity
- Global Searchglobal · Search across identities, incidents, applications, and browser extensions in this tenant. Returns sectioned results — each section has hits with name/uuid/score. Use when you have a name/email/incident-ID substring but not a UUID. Minimum 3 characters required (canonical incident IDs like 'INC-42' bypass the length check).Above SecurityAbove SecurityPluginrequiredSecurity
- List Browser Extensionsget · List browser extensionsAbove SecurityAbove SecurityPluginrequiredSecurity
- List Deviceslist · List devices in this tenant (UUID, name, email, status, last-seen, created). Supports substring search across name/email/UUID, sort by createdAt|name|lastActivityAt, paginate. Use get_device for the per-device detail (incl. linked identity).Above SecurityAbove SecurityPluginrequiredSecurity
- List High-Risk Identitieslist · List identities at HIGH or CRITICAL risk (UUID, name, email, risk score), optionally filtered by severity and limit. A tenant-wide ranked view of the riskiest identities.Above SecurityAbove SecurityPluginrequiredSecurity
- List Identitieslist · List identities in this tenant with full filters (substring search across name/email/UUID, minimum risk score, sort, paginate). For 'just the risky ones' use list_high_risk_identities instead — this is the full browse.Above SecurityAbove SecurityPluginrequiredSecurity
- List Incident Evidenceget · List all evidence items (screenshots, app context, uploaded files) attached to ONE incident by UUID. Each item includes its public download URL (presigned, time-limited).Above SecurityAbove SecurityPluginrequiredSecurity
- List Incidentsget · List incidents in this tenant (optionally filtered by severity, status, verdict, or type), returning each incident's summary fields (UUID, external id, severity, status, verdict, type, and the involved identity). Use get_incident for one incident's full detail.Above SecurityAbove SecurityPluginrequiredSecurity
- List Investigation Insightsget · List investigation insights and reports (optionally filtered by identity email, report type, year, or week number), returning report records and summaries. Does not return raw incident detail.Above SecurityAbove SecurityPluginrequiredSecurity
- List Monitored Applicationsget · List monitored applications (shadow IT)Above SecurityAbove SecurityPluginrequiredSecurity
- Query Audit Logsquery · Query the company's portal audit log (who did what, when, from where). Admin/SystemAdmin only — non-admin keys will be rejected at the route layer with 403. Filters by action, date range, portal user, and limit (max 200).Above SecurityAbove SecurityPluginrequiredSecurity
- Remove Identity from Watch Listremove · Remove an identity from the company Person-of-Interest watch list. Returns a clear 'not_on_watch_list' result (not an error) when the identity was not flagged, so it is safe to call unconditionally. Requires an Admin role (HR/Legal/User/IT cannot call). Resolve an email to a UUID with get_identity_uuid first.Above SecurityAbove SecurityPluginrequiredSecurity
- Set Incident Resolution Notesset · Set the resolution notes on an incident (free-form text, max 4000 chars). Note: this REPLACES the current notes — to extend existing notes, the caller is responsible for fetching them first via get_incident and concatenating. Requires non-restricted role.Above SecurityAbove SecurityPluginrequiredSecurity
- Set Incident Verdictupdate · Set an incident's verdict (Pending, Confirmed, FalsePositive, NeedsReview, Benign). Use this to record analyst judgement on whether an incident is a true positive or false positive. 'Benign' marks real, correctly-detected activity that is not concerning/acceptable — unlike FalsePositive it does not feed the false-positive training pipeline. Requires non-restricted role.Above SecurityAbove SecurityPluginrequiredSecurity
- Update Incident Statusupdate · Update an incident's status (Open, InProgress, Resolved, Dismissed, AutoResolved). Use this to triage incidents. The Hidden state cannot be set here — use the False Positive flow in the portal instead. Requires non-restricted role (HR/Legal cannot call).Above SecurityAbove SecurityPluginrequiredSecurity
- agentic_searchagenticAnakinAnakin
ConnectorrequiredData & Analytics - ai_visibility_searchaiAnakinAnakinConnectorrequiredData & Analytics
- ai_visibility_sourcesaiAnakinAnakinConnectorrequiredData & Analytics
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.