mcp-scraper 0.25.0 → 0.26.1

package/dist/{site-extract-repository-2QQSL2QC.js → site-extract-repository-O36SIFI2.js}

@@ -10,8 +10,8 @@ import {
   saveExtractPages,
   setExtractJobTotal,
   settleExtractJob
-} from "./chunk-PNBYYAEK.js";
-import "./chunk-JHI373VB.js";
+} from "./chunk-3ZZOLQ6A.js";
+import "./chunk-4767BA2O.js";
 import "./chunk-M2S27J6Z.js";
 import "./chunk-ICT7DDHL.js";
 export {
@@ -27,4 +27,4 @@ export {
   setExtractJobTotal,
   settleExtractJob
 };
-//# sourceMappingURL=site-extract-repository-2QQSL2QC.js.map
+//# sourceMappingURL=site-extract-repository-O36SIFI2.js.map

package/dist/{worker-RV2TYXE3.js → worker-E3KHQH2F.js}

@@ -16,7 +16,7 @@ import "./chunk-XGIPATLV.js";
 import {
   MC_COSTS,
   serpActualCostMc
-} from "./chunk-JHI373VB.js";
+} from "./chunk-4767BA2O.js";
 import "./chunk-M2S27J6Z.js";
 import {
   claimPendingJob,
@@ -139,4 +139,4 @@ export {
   startWorker,
   tickOnce
 };
-//# sourceMappingURL=worker-RV2TYXE3.js.map
+//# sourceMappingURL=worker-E3KHQH2F.js.map

package/docs/mcp-tool-manifest.generated.json

@@ -1,12 +1,12 @@
 {
-  "generatedAt": "2026-07-16T22:35:30.875Z",
+  "generatedAt": "2026-07-17T00:51:33.183Z",
   "generatedFrom": "dist/bin/mcp-stdio-server.js",
   "serverInfo": {
     "name": "mcp-scraper",
-    "version": "0.25.0"
+    "version": "0.26.1"
   },
   "counts": {
-    "unified_stdio": 162
+    "unified_stdio": 163
   },
   "surfaces": {
     "unified_stdio": [
@@ -156,6 +156,7 @@
       "table-list",
       "table-query",
       "temporal-recall",
+      "test_service_connection",
       "trustpilot_reviews",
       "upsert-memory-tag",
       "validate-memory-write",
@@ -10835,7 +10836,7 @@
     {
       "name": "list_service_connections",
       "title": "List Connected Services",
-      "description": "List every third-party service connection this MCP Scraper account has authorized, including Resend, GitHub, Google Analytics, Google Search Console, YouTube, Facebook Pages, LinkedIn, X, Meta Marketing, Slack, Gmail, Calendar, Google Drive, Zoom, Xero, and others. Returns the tenant-scoped connectionId, credential transport, exact live readTools and gated actionTools, permission-aware toolCapabilities with missing OAuth-grant or provider-app-feature blockers, permanently blocked administrative tools, and schema-discovery metadata. Get a connectionId and exact tool name here before calling describe_service_connection_tool, read_service_connection, or call_service_connection_action. Nango OAuth and official remote MCP connections use the same provider-neutral bridges; mutations still require the account action switch and an exact allowed action. A scheduled Search Console connection_sync creates a typed tenant-owned performance table; after it runs, use the returned tableName with table-describe and table-query instead of repeatedly calling Google for historical filtering.",
+      "description": "List every third-party service connection this MCP Scraper account has authorized, including Resend, GitHub, Google Analytics, Google Search Console, YouTube, Facebook Pages, LinkedIn, X, Meta Marketing, Slack, Gmail, Calendar, Google Drive, Zoom, Xero, and others. Returns the tenant-scoped connectionId; verified providerAccountEmail/providerAccountName identity when the provider exposes it; credential transport; exact live readTools and gated actionTools; permission-aware toolCapabilities with missing OAuth-grant or provider-app-feature blockers; permanently blocked administrative tools; and schema-discovery metadata. The provider identity is distinct from the MCP Scraper login: use it to choose the intended account before any read, export, schedule binding, or gated action. Get a connectionId and exact tool name here before calling describe_service_connection_tool, read_service_connection, or call_service_connection_action. Nango OAuth and official remote MCP connections use the same provider-neutral bridges; mutations still require the account action switch and an exact allowed action. A scheduled Search Console connection_sync creates a typed tenant-owned performance table; after it runs, use the returned tableName with table-describe and table-query instead of repeatedly calling Google for historical filtering.",
       "inputSchema": {
         "type": "object",
         "properties": {},
@@ -10862,11 +10863,63 @@
                   ]
                 },
                 "label": {
-                  "type": "string"
+                  "type": "string",
+                  "description": "Best verified provider-side account label. This is never derived from the MCP Scraper login email."
+                },
+                "providerAccountId": {
+                  "type": [
+                    "string",
+                    "null"
+                  ],
+                  "description": "Provider-side account or principal identifier when safely discoverable. This is not the MCP Scraper user id."
+                },
+                "providerAccountEmail": {
+                  "type": [
+                    "string",
+                    "null"
+                  ],
+                  "description": "Actual provider-side email for the authorized account when the provider exposes and verifies it. Null for organization-only accounts or unavailable identity scopes."
+                },
+                "providerAccountName": {
+                  "type": [
+                    "string",
+                    "null"
+                  ],
+                  "description": "Actual provider-side person, workspace, channel, or organization name when available."
+                },
+                "providerIdentityStatus": {
+                  "type": "string",
+                  "enum": [
+                    "pending",
+                    "verified",
+                    "unavailable"
+                  ],
+                  "description": "Whether provider-side account identity discovery is pending, verified, or unavailable under the current OAuth grant. Reconnect when unavailable after identity scopes were added."
                 },
                 "status": {
                   "type": "string"
                 },
+                "lifecycleStatus": {
+                  "type": "string",
+                  "enum": [
+                    "pending",
+                    "connected",
+                    "needs_reauth",
+                    "disconnecting",
+                    "disconnected"
+                  ],
+                  "description": "Credential lifecycle. This is separate from current provider availability."
+                },
+                "operationalStatus": {
+                  "type": "string",
+                  "enum": [
+                    "unknown",
+                    "available",
+                    "degraded",
+                    "unavailable"
+                  ],
+                  "description": "Last observed provider transport availability. Unavailable does not imply reconnect is required."
+                },
                 "reconnectRequired": {
                   "type": "boolean"
                 },
@@ -11031,6 +11084,36 @@
                   ],
                   "description": "Opaque revision of the resolved live tool catalog, when available. It changes when provider tools or policy change."
                 },
+                "lastCheckedAt": {
+                  "type": [
+                    "string",
+                    "null"
+                  ]
+                },
+                "lastSuccessfulCallAt": {
+                  "type": [
+                    "string",
+                    "null"
+                  ]
+                },
+                "lastFailureAt": {
+                  "type": [
+                    "string",
+                    "null"
+                  ]
+                },
+                "lastFailureCode": {
+                  "type": [
+                    "string",
+                    "null"
+                  ]
+                },
+                "lastFailureRetryable": {
+                  "type": [
+                    "boolean",
+                    "null"
+                  ]
+                },
                 "vaultName": {
                   "type": [
                     "string",
@@ -11050,6 +11133,10 @@
                 "connectionId",
                 "providerConfigKey",
                 "label",
+                "providerAccountId",
+                "providerAccountEmail",
+                "providerAccountName",
+                "providerIdentityStatus",
                 "status",
                 "transport",
                 "actionsEnabled",
@@ -18450,6 +18537,78 @@
         "taskSupport": "forbidden"
       }
     },
+    {
+      "name": "test_service_connection",
+      "title": "Test Connected Service",
+      "description": "Test the current provider transport for one tenant-owned connection without changing its OAuth lifecycle. Call this when a connected account appears unavailable before recommending reconnect. Reconnect is appropriate only when reconnectRequired is true.",
+      "inputSchema": {
+        "type": "object",
+        "properties": {
+          "connectionId": {
+            "type": "string",
+            "minLength": 1,
+            "description": "A tenant-owned connectionId from list_service_connections."
+          },
+          "providerConfigKey": {
+            "type": "string",
+            "minLength": 1,
+            "description": "Optional provider hint from list_service_connections."
+          }
+        },
+        "required": [
+          "connectionId"
+        ],
+        "additionalProperties": false,
+        "$schema": "http://json-schema.org/draft-07/schema#"
+      },
+      "outputSchema": {
+        "type": "object",
+        "properties": {
+          "ok": {
+            "type": "boolean"
+          },
+          "operationalStatus": {
+            "type": "string",
+            "enum": [
+              "available",
+              "unavailable"
+            ]
+          },
+          "checkedAt": {
+            "type": "string"
+          },
+          "toolCount": {
+            "type": "integer",
+            "minimum": 0
+          },
+          "code": {
+            "type": "string"
+          },
+          "error": {
+            "type": [
+              "string",
+              "null"
+            ]
+          }
+        },
+        "required": [
+          "ok",
+          "error"
+        ],
+        "additionalProperties": false,
+        "$schema": "http://json-schema.org/draft-07/schema#"
+      },
+      "annotations": {
+        "title": "Test Connected Service",
+        "readOnlyHint": true,
+        "destructiveHint": false,
+        "idempotentHint": true,
+        "openWorldHint": true
+      },
+      "execution": {
+        "taskSupport": "forbidden"
+      }
+    },
     {
       "name": "trustpilot_reviews",
       "title": "Trustpilot Review Harvest",