@zackbart/connecta 0.28.1 → 0.29.0

package/dist/providers/planning-center/skill.generated.js

@@ -0,0 +1,10 @@
+// Generated by scripts/generate-providers.mjs; do not edit.
+export const skill = {
+    "content": "# Planning Center usage\n\nPlanning Center Online church management — People, Services, Groups, Check-Ins, Calendar, Registrations, Giving, Publishing, Webhooks — for: \n\n## Identity first\n\n- A person id is the join key across every product: the id `search_people` returns is the `personId` for Services schedules, Groups memberships, Giving donations, and Check-Ins. Resolve ids with list tools; never guess one.\n- A person id that used to resolve and now answers `not_found` was most likely merged. Read `/people/v2/person_mergers` with `where[person_to_remove_id]` and follow `person_to_keep_id`.\n- `get_me` names the user this token acts as. Every read and write runs with that user's permissions, product by product; a `provider_permission_denied` means an administrator must grant that user access to the product or record.\n\n## Results and paging\n\n- Records keep Planning Center's own snake_case attribute names; a relationship appears as `<relationship>_id`. Pass `raw: true` for the untouched JSON:API resources and `included`.\n- Lists page by offset: `perPage` up to 100, then pass `page.nextOffset` back as `offset` while `page.hasMore` is true. `page.totalCount` answers \"how many\" without paging — request `perPage: 1`.\n- A bare date in a date filter is the organization's local day; pass a full timestamp for exact bounds. Name filters are exact; end one with `%` for a prefix match.\n- `get_plan` fetches the plan, its items, and its team in one call and sets `itemsTruncated`/`teamMembersTruncated` past 100 rows; page the rest with `pco_api_get`.\n\n## What each product lets the API write\n\n- People: full read/write. `update_person` with `status: inactive` archives reversibly; a DELETE is permanent and only reachable through `pco_api_mutate`. `run_list` can fire list automations.\n- Services: full read/write. A plan's dates come from its plan times. Scheduling needs a team.\n- Groups: memberships and group settings are writable; groups cannot be created, and events and attendance are read-only.\n- Check-Ins and Registrations: read-only. Nobody can be checked in or registered through the API.\n- Calendar: events, instances, and times are read-only; tags, resources, rooms, and folders are writable through `pco_api_mutate`.\n- Giving: the named tools only read, amounts in integer cents. Creating or editing donations, refunds, and committing a batch move money and go through `pco_api_mutate`.\n- Publishing and the `api` product (organization, OAuth applications, personal access tokens) have no named tools; use the hatches.\n\n## The hatches\n\n- `pco_api_get` reaches any GET; `pco_api_mutate` any POST, PATCH, or DELETE, always approval-gated. Paths start `/<app>/v2`, exactly as Planning Center documents them; the connector owns host, auth, content type, and the `X-PCO-API-Version` header.\n- Bodies are JSON:API documents: `{\"data\":{\"type\":\"Email\",\"attributes\":{...}}}`. `null` clears an attribute; an omitted key is left alone.\n- Each product is pinned to a reviewed API version: . Pass `version` only for an endpoint those versions lack.\n- Query parameters are name/value pairs with literal brackets: `where[status]`, `include`, `order`, `filter`, `fields[Person]`. Every list response's `meta` names the `can_query_by`, `can_order_by`, and `can_include` values for that endpoint; an unknown `where` key is ignored rather than refused.\n- File uploads go to a separate host (upload.planningcenteronline.com), which this connection does not reach.\n\n## Rate limits\n\nPlanning Center allows 100 requests per 20 seconds per user, shared by every integration running as that user. This connection admits 100 calls per 20 seconds, five at a time, per runtime — an approximation, not a guarantee. A `rate_limited` failure carries Planning Center's wait. Filter server-side and use `totalCount` rather than paging to count.\n",
+    "instructionsHeading": "Organization instructions",
+    "fragments": {
+        "guide_0": "# Planning Center usage\n\nPlanning Center Online church management — People, Services, Groups, Check-Ins, Calendar, Registrations, Giving, Publishing, Webhooks — for: ",
+        "guide_1": "\n\n## Identity first\n\n- A person id is the join key across every product: the id `search_people` returns is the `personId` for Services schedules, Groups memberships, Giving donations, and Check-Ins. Resolve ids with list tools; never guess one.\n- A person id that used to resolve and now answers `not_found` was most likely merged. Read `/people/v2/person_mergers` with `where[person_to_remove_id]` and follow `person_to_keep_id`.\n- `get_me` names the user this token acts as. Every read and write runs with that user's permissions, product by product; a `provider_permission_denied` means an administrator must grant that user access to the product or record.\n\n## Results and paging\n\n- Records keep Planning Center's own snake_case attribute names; a relationship appears as `<relationship>_id`. Pass `raw: true` for the untouched JSON:API resources and `included`.\n- Lists page by offset: `perPage` up to 100, then pass `page.nextOffset` back as `offset` while `page.hasMore` is true. `page.totalCount` answers \"how many\" without paging — request `perPage: 1`.\n- A bare date in a date filter is the organization's local day; pass a full timestamp for exact bounds. Name filters are exact; end one with `%` for a prefix match.\n- `get_plan` fetches the plan, its items, and its team in one call and sets `itemsTruncated`/`teamMembersTruncated` past 100 rows; page the rest with `pco_api_get`.\n\n## What each product lets the API write\n\n- People: full read/write. `update_person` with `status: inactive` archives reversibly; a DELETE is permanent and only reachable through `pco_api_mutate`. `run_list` can fire list automations.\n- Services: full read/write. A plan's dates come from its plan times. Scheduling needs a team.\n- Groups: memberships and group settings are writable; groups cannot be created, and events and attendance are read-only.\n- Check-Ins and Registrations: read-only. Nobody can be checked in or registered through the API.\n- Calendar: events, instances, and times are read-only; tags, resources, rooms, and folders are writable through `pco_api_mutate`.\n- Giving: the named tools only read, amounts in integer cents. Creating or editing donations, refunds, and committing a batch move money and go through `pco_api_mutate`.\n- Publishing and the `api` product (organization, OAuth applications, personal access tokens) have no named tools; use the hatches.\n\n## The hatches\n\n- `pco_api_get` reaches any GET; `pco_api_mutate` any POST, PATCH, or DELETE, always approval-gated. Paths start `/<app>/v2`, exactly as Planning Center documents them; the connector owns host, auth, content type, and the `X-PCO-API-Version` header.\n- Bodies are JSON:API documents: `{\"data\":{\"type\":\"Email\",\"attributes\":{...}}}`. `null` clears an attribute; an omitted key is left alone.\n- Each product is pinned to a reviewed API version: ",
+        "guide_2": ". Pass `version` only for an endpoint those versions lack.\n- Query parameters are name/value pairs with literal brackets: `where[status]`, `include`, `order`, `filter`, `fields[Person]`. Every list response's `meta` names the `can_query_by`, `can_order_by`, and `can_include` values for that endpoint; an unknown `where` key is ignored rather than refused.\n- File uploads go to a separate host (upload.planningcenteronline.com), which this connection does not reach.\n\n## Rate limits\n\nPlanning Center allows 100 requests per 20 seconds per user, shared by every integration running as that user. This connection admits 100 calls per 20 seconds, five at a time, per runtime — an approximation, not a guarantee. A `rate_limited` failure carries Planning Center's wait. Filter server-side and use `totalCount` rather than paging to count.\n"
+    }
+};

package/dist/providers/{revenuecat.d.ts → revenuecat/index.d.ts}

@@ -1,5 +1,5 @@
-import { type RemoteMcpAuth } from "../connectors/remote-mcp.js";
-import type { Connector, ConnectorCallAdmissionPolicy } from "../types.js";
+import { type RemoteMcpAuth } from "../../connectors/remote-mcp.js";
+import type { ConnectorCallAdmissionPolicy } from "../../types.js";
 /** RevenueCat publishes one hosted MCP endpoint, streamable HTTP. */
 export declare const REVENUECAT_MCP_ENDPOINT = "https://mcp.revenuecat.ai/mcp";
 export interface RevenueCatOptions {
@@ -43,12 +43,7 @@ export interface RevenueCatOptions {
      */
     callAdmission?: ConnectorCallAdmissionPolicy;
 }
-/**
- * One release-reviewed manifest, used both to classify a live tool and as the
- * baseline the drift check compares against, so the annotation a caller gets
- * and the verdict a check reads can never disagree. Names and verdicts only —
- * no schemas are vendored; the live `tools/list` response stays authoritative.
- */
-export declare const REVENUECAT_VETTED_CATALOG: import("../catalog-drift.js").VettedCatalog;
 /** A maintained RevenueCat hosted-MCP connection. */
-export declare function revenuecat(id: string, options: RevenueCatOptions): Connector;
+export declare const revenuecat: import("../../provider.js").ProviderFactory<RevenueCatOptions>;
+/** @deprecated Read `revenuecat.definition.classify` instead. Kept for existing imports. */
+export declare const REVENUECAT_VETTED_CATALOG: import("../../catalog-drift.js").VettedCatalog;

package/dist/providers/revenuecat/index.js

@@ -0,0 +1,557 @@
+import { skill } from "./skill.generated.js";
+import { remoteMcp, withCredentialDefaults } from "../../connectors/remote-mcp.js";
+import { reviewedCatalog } from "../../catalog-drift.js";
+import { optionsOf } from "../../config-schema.js";
+import { PROVIDER_COMMON, REMOTE_MCP_AUTH } from "../../connectors/option-shapes.js";
+import { defineProvider } from "../../provider.js";
+/** RevenueCat publishes one hosted MCP endpoint, streamable HTTP. */
+export const REVENUECAT_MCP_ENDPOINT = "https://mcp.revenuecat.ai/mcp";
+/**
+ * Reviewed in #705's provider audit against https://www.revenuecat.com/docs/tools/mcp/tools-reference.
+ * Retains the release-reviewed inventory, including names absent from today's
+ * public reference. Live annotations were not reverified without credentials.
+ * No schema digest is asserted without a captured schema to review.
+ */
+const REVENUECAT_CLASSIFICATION = {
+    tools: {
+        "get-account-billing": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat account billing information without changing vendor state.",
+        },
+        "get-app": { "verdict": "read", "reason": "Retrieves RevenueCat app information without changing vendor state." },
+        "get-project-ui-config": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat project ui config information without changing vendor state.",
+        },
+        "list-account-billing-invoices": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat account billing invoices information without changing vendor state.",
+        },
+        "list-app-public-api-keys": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat app public api keys information without changing vendor state.",
+        },
+        "list-apps": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat apps information without changing vendor state.",
+        },
+        "list-audit-logs": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat audit logs information without changing vendor state.",
+        },
+        "list-collaborators": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat collaborators information without changing vendor state.",
+        },
+        "list-projects": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat projects information without changing vendor state.",
+        },
+        "get-product": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat product information without changing vendor state.",
+        },
+        "get-product-store-state": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat product store state information without changing vendor state.",
+        },
+        "get-product-store-state-operation": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat product store state operation information without changing vendor state.",
+        },
+        "get-product-store-state-plan": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat product store state plan information without changing vendor state.",
+        },
+        "list-product-store-state-plans": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat product store state plans information without changing vendor state.",
+        },
+        "list-products": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat products information without changing vendor state.",
+        },
+        "get-entitlement": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat entitlement information without changing vendor state.",
+        },
+        "get-products-from-entitlement": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat products from entitlement information without changing vendor state.",
+        },
+        "list-entitlements": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat entitlements information without changing vendor state.",
+        },
+        "get-offering": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat offering information without changing vendor state.",
+        },
+        "get-offering-prices": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat offering prices information without changing vendor state.",
+        },
+        "list-offerings": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat offerings information without changing vendor state.",
+        },
+        "list-packages": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat packages information without changing vendor state.",
+        },
+        "get-audience": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat audience information without changing vendor state.",
+        },
+        "get-audience-filter-options": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat audience filter options information without changing vendor state.",
+        },
+        "get-targeting-rule": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat targeting rule information without changing vendor state.",
+        },
+        "list-audiences": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat audiences information without changing vendor state.",
+        },
+        "list-targeting-rules": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat targeting rules information without changing vendor state.",
+        },
+        "get-paywall": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat paywall information without changing vendor state.",
+        },
+        "list-paywalls": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat paywalls information without changing vendor state.",
+        },
+        "get-customer": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat customer information without changing vendor state.",
+        },
+        "get-customer-center-config": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat customer center config information without changing vendor state.",
+        },
+        "get-refund-request-preferences": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat refund request preferences information without changing vendor state.",
+        },
+        "get-subscription": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat subscription information without changing vendor state.",
+        },
+        "list-customer-events": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat customer events information without changing vendor state.",
+        },
+        "list-customers": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat customers information without changing vendor state.",
+        },
+        "list-purchases": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat purchases information without changing vendor state.",
+        },
+        "list-subscriptions": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat subscriptions information without changing vendor state.",
+        },
+        "list-virtual-currencies-balances": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat virtual currencies balances information without changing vendor state.",
+        },
+        "get-virtual-currency": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat virtual currency information without changing vendor state.",
+        },
+        "list-virtual-currencies": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat virtual currencies information without changing vendor state.",
+        },
+        "get-benchmarks": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat benchmarks information without changing vendor state.",
+        },
+        "get-chart-data": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat chart data information without changing vendor state.",
+        },
+        "get-chart-options-schema": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat chart options schema information without changing vendor state.",
+        },
+        "get-experiment": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat experiment information without changing vendor state.",
+        },
+        "get-experiment-results": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat experiment results information without changing vendor state.",
+        },
+        "get-overview-metrics": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat overview metrics information without changing vendor state.",
+        },
+        "get-revenue-metric": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat revenue metric information without changing vendor state.",
+        },
+        "list-experiments": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat experiments information without changing vendor state.",
+        },
+        "get-webhook-integration": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat webhook integration information without changing vendor state.",
+        },
+        "list-webhook-integrations": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat webhook integrations information without changing vendor state.",
+        },
+        "list-sdk-feature-gates": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat sdk feature gates information without changing vendor state.",
+        },
+        "list-sdk-versions": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat sdk versions information without changing vendor state.",
+        },
+        "get-paywall-ai-task": {
+            "verdict": "read",
+            "reason": "Retrieves RevenueCat paywall ai task information without changing vendor state.",
+        },
+        "create-app": {
+            "verdict": "write",
+            "reason": "create app creates or appends RevenueCat state; it has side effects.",
+        },
+        "create-project": {
+            "verdict": "write",
+            "reason": "create project creates or appends RevenueCat state; it has side effects.",
+        },
+        "update-app": { "verdict": "destructive", "reason": "update app changes existing RevenueCat state or removes it." },
+        "update-project-ui-config": {
+            "verdict": "destructive",
+            "reason": "update project ui config changes existing RevenueCat state or removes it.",
+        },
+        "validate-app-credentials": {
+            "verdict": "write",
+            "reason": "validate app credentials creates or appends RevenueCat state; it has side effects.",
+        },
+        "archive-product": {
+            "verdict": "destructive",
+            "reason": "archive product changes existing RevenueCat state or removes it.",
+        },
+        "create-product": {
+            "verdict": "write",
+            "reason": "create product creates or appends RevenueCat state; it has side effects.",
+        },
+        "create-product-prices": {
+            "verdict": "destructive",
+            "reason": "create product prices changes existing RevenueCat state or removes it.",
+        },
+        "equalize-subscription-prices": {
+            "verdict": "write",
+            "reason": "equalize subscription prices creates or appends RevenueCat state; it has side effects.",
+        },
+        "set-product-store-state": {
+            "verdict": "destructive",
+            "reason": "set product store state changes existing RevenueCat state or removes it.",
+        },
+        "submit-products-to-store": {
+            "verdict": "destructive",
+            "reason": "submit products to store changes existing RevenueCat state or removes it.",
+        },
+        "unarchive-product": {
+            "verdict": "destructive",
+            "reason": "unarchive product changes existing RevenueCat state or removes it.",
+        },
+        "update-product": {
+            "verdict": "destructive",
+            "reason": "update product changes existing RevenueCat state or removes it.",
+        },
+        "upload-product-store-state-screenshot": {
+            "verdict": "write",
+            "reason": "upload product store state screenshot creates or appends RevenueCat state; it has side effects.",
+        },
+        "create-product-store-state-plan": {
+            "verdict": "write",
+            "reason": "create product store state plan creates or appends RevenueCat state; it has side effects.",
+        },
+        "plan-product-store-state-plan": {
+            "verdict": "destructive",
+            "reason": "Advances a store-state plan workflow and can create asynchronous task state.",
+        },
+        "apply-product-store-state-plan": {
+            "verdict": "destructive",
+            "reason": "Applies a plan to store configuration and can change existing products.",
+        },
+        "update-product-store-state-plan": {
+            "verdict": "destructive",
+            "reason": "update product store state plan changes existing RevenueCat state or removes it.",
+        },
+        "discard-product-store-state-plan": {
+            "verdict": "destructive",
+            "reason": "discard product store state plan changes existing RevenueCat state or removes it.",
+        },
+        "archive-entitlement": {
+            "verdict": "destructive",
+            "reason": "archive entitlement changes existing RevenueCat state or removes it.",
+        },
+        "attach-products-to-entitlement": {
+            "verdict": "write",
+            "reason": "attach products to entitlement creates or appends RevenueCat state; it has side effects.",
+        },
+        "create-entitlement": {
+            "verdict": "write",
+            "reason": "create entitlement creates or appends RevenueCat state; it has side effects.",
+        },
+        "detach-products-from-entitlement": {
+            "verdict": "destructive",
+            "reason": "detach products from entitlement changes existing RevenueCat state or removes it.",
+        },
+        "unarchive-entitlement": {
+            "verdict": "destructive",
+            "reason": "unarchive entitlement changes existing RevenueCat state or removes it.",
+        },
+        "update-entitlement": {
+            "verdict": "destructive",
+            "reason": "update entitlement changes existing RevenueCat state or removes it.",
+        },
+        "archive-offering": {
+            "verdict": "destructive",
+            "reason": "archive offering changes existing RevenueCat state or removes it.",
+        },
+        "attach-products-to-package": {
+            "verdict": "write",
+            "reason": "attach products to package creates or appends RevenueCat state; it has side effects.",
+        },
+        "create-offering": {
+            "verdict": "write",
+            "reason": "create offering creates or appends RevenueCat state; it has side effects.",
+        },
+        "create-packages": {
+            "verdict": "write",
+            "reason": "create packages creates or appends RevenueCat state; it has side effects.",
+        },
+        "delete-package-from-offering": {
+            "verdict": "destructive",
+            "reason": "delete package from offering changes existing RevenueCat state or removes it.",
+        },
+        "detach-products-from-package": {
+            "verdict": "destructive",
+            "reason": "detach products from package changes existing RevenueCat state or removes it.",
+        },
+        "unarchive-offering": {
+            "verdict": "destructive",
+            "reason": "unarchive offering changes existing RevenueCat state or removes it.",
+        },
+        "update-offering": {
+            "verdict": "destructive",
+            "reason": "update offering changes existing RevenueCat state or removes it.",
+        },
+        "create-audience": {
+            "verdict": "write",
+            "reason": "create audience creates or appends RevenueCat state; it has side effects.",
+        },
+        "update-audience": {
+            "verdict": "destructive",
+            "reason": "update audience changes existing RevenueCat state or removes it.",
+        },
+        "create-targeting-rule": {
+            "verdict": "write",
+            "reason": "create targeting rule creates or appends RevenueCat state; it has side effects.",
+        },
+        "update-targeting-rule": {
+            "verdict": "destructive",
+            "reason": "update targeting rule changes existing RevenueCat state or removes it.",
+        },
+        "delete-targeting-rule": {
+            "verdict": "destructive",
+            "reason": "delete targeting rule changes existing RevenueCat state or removes it.",
+        },
+        "attach-offering-to-paywall": {
+            "verdict": "destructive",
+            "reason": "attach offering to paywall changes existing RevenueCat state or removes it.",
+        },
+        "detach-offering-from-paywall": {
+            "verdict": "destructive",
+            "reason": "detach offering from paywall changes existing RevenueCat state or removes it.",
+        },
+        "duplicate-paywall": {
+            "verdict": "write",
+            "reason": "duplicate paywall creates or appends RevenueCat state; it has side effects.",
+        },
+        "publish-paywall": {
+            "verdict": "destructive",
+            "reason": "publish paywall changes existing RevenueCat state or removes it.",
+        },
+        "unpublish-paywall": {
+            "verdict": "destructive",
+            "reason": "unpublish paywall changes existing RevenueCat state or removes it.",
+        },
+        "duplicate-offering": {
+            "verdict": "write",
+            "reason": "duplicate offering creates or appends RevenueCat state; it has side effects.",
+        },
+        "create-experiment": {
+            "verdict": "write",
+            "reason": "create experiment creates or appends RevenueCat state; it has side effects.",
+        },
+        "pause-experiment": {
+            "verdict": "destructive",
+            "reason": "pause experiment changes existing RevenueCat state or removes it.",
+        },
+        "resume-experiment": {
+            "verdict": "destructive",
+            "reason": "resume experiment changes existing RevenueCat state or removes it.",
+        },
+        "start-experiment": {
+            "verdict": "destructive",
+            "reason": "start experiment changes existing RevenueCat state or removes it.",
+        },
+        "stop-experiment": {
+            "verdict": "destructive",
+            "reason": "stop experiment changes existing RevenueCat state or removes it.",
+        },
+        "update-experiment": {
+            "verdict": "destructive",
+            "reason": "update experiment changes existing RevenueCat state or removes it.",
+        },
+        "assign-customer-offering": {
+            "verdict": "destructive",
+            "reason": "assign customer offering changes existing RevenueCat state or removes it.",
+        },
+        "grant-customer-entitlement": {
+            "verdict": "destructive",
+            "reason": "grant customer entitlement changes existing RevenueCat state or removes it.",
+        },
+        "archive-virtual-currency": {
+            "verdict": "destructive",
+            "reason": "archive virtual currency changes existing RevenueCat state or removes it.",
+        },
+        "create-virtual-currency": {
+            "verdict": "write",
+            "reason": "create virtual currency creates or appends RevenueCat state; it has side effects.",
+        },
+        "unarchive-virtual-currency": {
+            "verdict": "destructive",
+            "reason": "unarchive virtual currency changes existing RevenueCat state or removes it.",
+        },
+        "update-virtual-currency": {
+            "verdict": "destructive",
+            "reason": "update virtual currency changes existing RevenueCat state or removes it.",
+        },
+        "create-webhook-integration": {
+            "verdict": "destructive",
+            "reason": "Starts delivering customer events to a caller-supplied URL; omitted filters deliver every customer event in the project. Destructive by consequence even though it creates a new integration.",
+        },
+        "delete-webhook-integration": {
+            "verdict": "destructive",
+            "reason": "delete webhook integration changes existing RevenueCat state or removes it.",
+        },
+        "update-webhook-integration": {
+            "verdict": "destructive",
+            "reason": "update webhook integration changes existing RevenueCat state or removes it.",
+        },
+        "create-paywall-ai": {
+            "verdict": "write",
+            "reason": "create paywall ai creates or appends RevenueCat state; it has side effects.",
+        },
+        "edit-paywall-ai": {
+            "verdict": "destructive",
+            "reason": "edit paywall ai changes existing RevenueCat state or removes it.",
+        },
+    },
+};
+/** The catalog's summary bound; a longer declared value throws (`src/registry.ts`). */
+const SUMMARY_BUDGET = 120;
+/**
+ * Fit a purpose-bearing summary inside the catalog's bound.
+ *
+ * Stripe and Mixpanel declare static summaries because their routing fact is
+ * an enumerable variant. RevenueCat's is not: two `sk_` connectors have the
+ * same title, the same endpoint, and the same catalog, and differ only by the
+ * project the operator says each key reaches. So the summary carries that, and
+ * clipping is this function's job rather than the operator's.
+ */
+function boundedSummary(prefix, purpose) {
+    const full = `${prefix}${purpose}`;
+    if (full.length <= SUMMARY_BUDGET)
+        return full;
+    return `${full.slice(0, SUMMARY_BUDGET - 1).trimEnd()}…`;
+}
+function sharedUsageGuide() {
+    return skill.fragments.guide_0;
+}
+function oauthUsageGuide(purpose, instructions) {
+    const projectInstructions = instructions?.trim();
+    return `${skill.fragments.guide_1}${purpose}${skill.fragments.guide_2}${sharedUsageGuide()}${projectInstructions ? `\n## ${skill.instructionsHeading}\n\n${projectInstructions}\n` : ""}`;
+}
+function keyUsageGuide(purpose, instructions) {
+    const projectInstructions = instructions?.trim();
+    return `# RevenueCat usage
+
+Single-project connection: ${purpose}${skill.fragments.guide_3}${sharedUsageGuide()}${projectInstructions ? `\n## ${skill.instructionsHeading}\n\n${projectInstructions}\n` : ""}`;
+}
+/** The closed options revenuecat() accepts; see `assertKnownOptions`. */
+const REVENUECAT_OPTIONS = optionsOf()({ ...PROVIDER_COMMON, auth: REMOTE_MCP_AUTH });
+/** A maintained RevenueCat hosted-MCP connection. */
+export const revenuecat = defineProvider({
+    name: "revenuecat",
+    title: "RevenueCat",
+    kind: "mcp",
+    readme: "RevenueCat",
+    bundle: { "baselineGzip": 128548, "maxGzip": 188548 },
+    skill,
+    options: REVENUECAT_OPTIONS,
+    classify: REVENUECAT_CLASSIFICATION,
+    create: revenuecatConnector,
+});
+function revenuecatConnector(id, options, provider) {
+    const purpose = options.purpose.trim();
+    const auth = withCredentialDefaults(options.auth ?? { type: "oauth" }, {
+        credential: {
+            label: "API v2 secret key",
+            description: "A RevenueCat API v2 secret key. It reaches exactly one project, which is why two projects are two connectors; it is stored encrypted and never displayed.",
+            placeholder: "sk_…",
+        },
+    });
+    // Both static shapes reach one project. Where the key came from — the
+    // deployment file or the operator page — changes nothing an agent must know
+    // about scope, so the title, description, and guide follow the scope alone.
+    const scoped = auth.type !== "oauth";
+    const connector = remoteMcp(id, {
+        url: REVENUECAT_MCP_ENDPOINT,
+        ...provider.connectorOptions,
+        // The scope shape rides the title because browse-time discovery renders
+        // the title and the guide summary and nothing else, and reaching one
+        // project versus every project the account has is the fact an agent must
+        // not get wrong between two RevenueCat connections.
+        title: options.title ?? (scoped ? "RevenueCat (single project)" : "RevenueCat"),
+        description: scoped
+            ? `RevenueCat subscriptions and revenue (one project, static key) — ${purpose}`
+            : `RevenueCat subscriptions and revenue (every project the account can reach) — ${purpose}`,
+        auth,
+        requireHttps: true,
+        classify: provider.classify,
+        usageGuide: {
+            content: scoped ? keyUsageGuide(purpose, options.instructions) : oauthUsageGuide(purpose, options.instructions),
+            // Explicit rather than derived, and purpose-bearing rather than static:
+            // the derived summary would cut the scoping sentence mid-clause at 120
+            // characters, and two static summaries would leave two `sk_` connectors
+            // indistinguishable in the one field search returns (P3).
+            summary: scoped
+                ? boundedSummary("One project only: ", purpose)
+                : boundedSummary("All account projects; list-projects first: ", purpose),
+            // Not `required`. RevenueCat's own schemas describe each call; the guide
+            // carries the project-resolution sequence, which is worth reading before
+            // a run rather than before every call.
+        },
+    });
+    return connector;
+}
+/** @deprecated Read `revenuecat.definition.classify` instead. Kept for existing imports. */
+export const REVENUECAT_VETTED_CATALOG = reviewedCatalog(revenuecat.definition.classify, 'defineProvider("revenuecat")');

package/dist/providers/revenuecat/skill.generated.js

@@ -0,0 +1,11 @@
+// Generated by scripts/generate-providers.mjs; do not edit.
+export const skill = {
+    "content": "\n- Inspect result framing before accessing fields. A text result is not automatically an object; parse it only if the returned text is valid JSON. Do not iterate fields that the response does not contain.\n- Resolve ids before acting; never guess one. `list-projects` yields the `project_id` every project-scoped call takes. `list-apps`, `list-products`, `list-entitlements`, `list-offerings`, `list-paywalls`, `list-audiences`, and `list-customers` yield the ids their `get-`, `update-`, `archive-`, and `delete-` counterparts expect. A plausible-looking id belongs to another project or to nobody.\n- Customers are addressed by the app user id your SDK set, not by an internal key. Find one with `list-customers` before `get-customer`, and carry the id it returned unchanged.\n- Customer and subscription objects are large, and a customer's history is larger. Page with the cursor the list returned rather than raising the page size, and reduce inside `execute_code` — select the fields the question needs and return those, not the whole object.\n- Whether a customer should have access is `gives_access` on each subscription from `list-subscriptions`, which RevenueCat calls the authoritative flag. `status` and `expires_date` describe the store-side state and disagree with it during grace periods, billing retries, and promotional grants — answer access questions from `gives_access` and say which subscription it came from.\n- `get-chart-data` is the metrics path: read `get-chart-options-schema` for the chart you want before calling it, rather than guessing an option name. `get-overview-metrics` and `get-revenue-metric` answer the summary questions in one call.\n- `create-paywall-ai` and `edit-paywall-ai` are asynchronous. Poll the task id they return with `get-paywall-ai-task` rather than assuming the work finished when the call returned.\n- Store changes ride the plan workflow, not the deprecated direct tools: `create-product-store-state-plan`, then `plan-product-store-state-plan`, then `apply-product-store-state-plan`. Every step past the create is asynchronous — read the plan back with `get-product-store-state-plan` between steps instead of assuming the last one finished.\n- This connection's tool list is not a fixed set. RevenueCat gates parts of its MCP catalog by plan, platform, and beta enrollment — paywall AI editing, benchmarks, experiments, virtual currencies, and the account-billing tools are the usual absentees — so search this connector for what it actually exposes rather than assuming a documented tool is here.\n- `render-paywall-screenshot` is unclassified on purpose because RevenueCat's reference gives it no access column. An explicit, uncontradicted live read annotation qualifies it as a read; otherwise it fails closed as a write. The public reference alone cannot establish that rendering has no side effects.\n- RevenueCat meters API v2 per minute and per domain, and the domains differ: 480 requests per minute for customer information and virtual currencies, 60 for project configuration and audiences, 25 for charts and metrics. It answers a breach with `429`, a `Retry-After` header, and a `backoff_ms` field. Back off on that rather than retrying immediately, and expect chart sweeps to hit the ceiling long before customer reads do.\n- Treat every create, update, archive, unarchive, attach, detach, delete, publish, unpublish, grant, assign, and submit operation as a write. For guest calls, classification, and routing, fetch `skills({ name: \"usage\" })`.\n- An `auth_required` failure means this connector's RevenueCat authorization is missing or expired: run `authorize_connector` for this connector id, then retry the same call unchanged. A rejected argument, a permission gap, or a plan restriction comes back in RevenueCat's own words instead — read it rather than re-authorizing.\n# RevenueCat usage\n\nAccount-scoped connection: this OAuth session reaches every RevenueCat project the account can see. Connector purpose: \n\nCall `list-projects` first and carry the exact `project_id` it returned into every project-scoped call. Connecta does not pick a project, and the connector id, title, and purpose are routing hints rather than proof of which project a call will land in. If more than one project fits the request, stop and ask; never guess a `project_id`.\n. RevenueCat secret API keys are project-wide, so this key reaches exactly one project and nothing outside it. A second project is a second connector with its own key and its own id — never a `project_id` argument pointed somewhere else.\n\nConfirm the project on first use: `list-projects` returns the one project this key can see, and its `project_id` is the one every project-scoped call takes. An empty or unexpected result means wrong connector, not missing data.\n\nA RevenueCat secret key is issued read-only or write-enabled, and connecta cannot tell which this one is. It does not filter writes for a read-only key: every write is offered, reaches RevenueCat, and fails there in RevenueCat's own words. Read that refusal as \"this key cannot write\" rather than as a bad argument, and route the write to a connector configured with a write-enabled key.\n",
+    "instructionsHeading": "Project instructions",
+    "fragments": {
+        "guide_0": "\n- Inspect result framing before accessing fields. A text result is not automatically an object; parse it only if the returned text is valid JSON. Do not iterate fields that the response does not contain.\n- Resolve ids before acting; never guess one. `list-projects` yields the `project_id` every project-scoped call takes. `list-apps`, `list-products`, `list-entitlements`, `list-offerings`, `list-paywalls`, `list-audiences`, and `list-customers` yield the ids their `get-`, `update-`, `archive-`, and `delete-` counterparts expect. A plausible-looking id belongs to another project or to nobody.\n- Customers are addressed by the app user id your SDK set, not by an internal key. Find one with `list-customers` before `get-customer`, and carry the id it returned unchanged.\n- Customer and subscription objects are large, and a customer's history is larger. Page with the cursor the list returned rather than raising the page size, and reduce inside `execute_code` — select the fields the question needs and return those, not the whole object.\n- Whether a customer should have access is `gives_access` on each subscription from `list-subscriptions`, which RevenueCat calls the authoritative flag. `status` and `expires_date` describe the store-side state and disagree with it during grace periods, billing retries, and promotional grants — answer access questions from `gives_access` and say which subscription it came from.\n- `get-chart-data` is the metrics path: read `get-chart-options-schema` for the chart you want before calling it, rather than guessing an option name. `get-overview-metrics` and `get-revenue-metric` answer the summary questions in one call.\n- `create-paywall-ai` and `edit-paywall-ai` are asynchronous. Poll the task id they return with `get-paywall-ai-task` rather than assuming the work finished when the call returned.\n- Store changes ride the plan workflow, not the deprecated direct tools: `create-product-store-state-plan`, then `plan-product-store-state-plan`, then `apply-product-store-state-plan`. Every step past the create is asynchronous — read the plan back with `get-product-store-state-plan` between steps instead of assuming the last one finished.\n- This connection's tool list is not a fixed set. RevenueCat gates parts of its MCP catalog by plan, platform, and beta enrollment — paywall AI editing, benchmarks, experiments, virtual currencies, and the account-billing tools are the usual absentees — so search this connector for what it actually exposes rather than assuming a documented tool is here.\n- `render-paywall-screenshot` is unclassified on purpose because RevenueCat's reference gives it no access column. An explicit, uncontradicted live read annotation qualifies it as a read; otherwise it fails closed as a write. The public reference alone cannot establish that rendering has no side effects.\n- RevenueCat meters API v2 per minute and per domain, and the domains differ: 480 requests per minute for customer information and virtual currencies, 60 for project configuration and audiences, 25 for charts and metrics. It answers a breach with `429`, a `Retry-After` header, and a `backoff_ms` field. Back off on that rather than retrying immediately, and expect chart sweeps to hit the ceiling long before customer reads do.\n- Treat every create, update, archive, unarchive, attach, detach, delete, publish, unpublish, grant, assign, and submit operation as a write. For guest calls, classification, and routing, fetch `skills({ name: \"usage\" })`.\n- An `auth_required` failure means this connector's RevenueCat authorization is missing or expired: run `authorize_connector` for this connector id, then retry the same call unchanged. A rejected argument, a permission gap, or a plan restriction comes back in RevenueCat's own words instead — read it rather than re-authorizing.\n",
+        "guide_1": "# RevenueCat usage\n\nAccount-scoped connection: this OAuth session reaches every RevenueCat project the account can see. Connector purpose: ",
+        "guide_2": "\n\nCall `list-projects` first and carry the exact `project_id` it returned into every project-scoped call. Connecta does not pick a project, and the connector id, title, and purpose are routing hints rather than proof of which project a call will land in. If more than one project fits the request, stop and ask; never guess a `project_id`.\n",
+        "guide_3": ". RevenueCat secret API keys are project-wide, so this key reaches exactly one project and nothing outside it. A second project is a second connector with its own key and its own id — never a `project_id` argument pointed somewhere else.\n\nConfirm the project on first use: `list-projects` returns the one project this key can see, and its `project_id` is the one every project-scoped call takes. An empty or unexpected result means wrong connector, not missing data.\n\nA RevenueCat secret key is issued read-only or write-enabled, and connecta cannot tell which this one is. It does not filter writes for a read-only key: every write is offered, reaches RevenueCat, and fails there in RevenueCat's own words. Read that refusal as \"this key cannot write\" rather than as a bad argument, and route the write to a connector configured with a write-enabled key.\n"
+    }
+};