mcp-scraper 0.38.2 → 0.40.1
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +5 -2
- package/package.json +5 -6
- package/dist/bin/api-server.cjs +0 -58752
- package/dist/bin/api-server.cjs.map +0 -1
- package/dist/bin/api-server.d.cts +0 -1
- package/dist/bin/api-server.d.ts +0 -1
- package/dist/bin/api-server.js +0 -38
- package/dist/bin/api-server.js.map +0 -1
- package/dist/bin/mcp-scraper-cli.cjs +0 -2671
- package/dist/bin/mcp-scraper-cli.cjs.map +0 -1
- package/dist/bin/mcp-scraper-cli.d.cts +0 -1
- package/dist/bin/mcp-scraper-cli.d.ts +0 -1
- package/dist/bin/mcp-scraper-cli.js +0 -742
- package/dist/bin/mcp-scraper-cli.js.map +0 -1
- package/dist/bin/mcp-scraper-install.cjs +0 -129
- package/dist/bin/mcp-scraper-install.cjs.map +0 -1
- package/dist/bin/mcp-scraper-install.d.cts +0 -1
- package/dist/bin/mcp-scraper-install.d.ts +0 -1
- package/dist/bin/mcp-scraper-install.js +0 -27
- package/dist/bin/mcp-scraper-install.js.map +0 -1
- package/dist/bin/mcp-stdio-server.cjs +0 -12264
- package/dist/bin/mcp-stdio-server.cjs.map +0 -1
- package/dist/bin/mcp-stdio-server.d.cts +0 -1
- package/dist/bin/mcp-stdio-server.d.ts +0 -1
- package/dist/bin/mcp-stdio-server.js +0 -135
- package/dist/bin/mcp-stdio-server.js.map +0 -1
- package/dist/bin/paa-harvest.cjs +0 -3808
- package/dist/bin/paa-harvest.cjs.map +0 -1
- package/dist/bin/paa-harvest.d.cts +0 -1
- package/dist/bin/paa-harvest.d.ts +0 -1
- package/dist/bin/paa-harvest.js +0 -44
- package/dist/bin/paa-harvest.js.map +0 -1
- package/dist/chunk-345BQXZH.js +0 -712
- package/dist/chunk-345BQXZH.js.map +0 -1
- package/dist/chunk-44HZLHDV.js +0 -52
- package/dist/chunk-44HZLHDV.js.map +0 -1
- package/dist/chunk-AZRPG43B.js +0 -617
- package/dist/chunk-AZRPG43B.js.map +0 -1
- package/dist/chunk-CB5C3BPB.js +0 -135
- package/dist/chunk-CB5C3BPB.js.map +0 -1
- package/dist/chunk-EGJKUB4Q.js +0 -276
- package/dist/chunk-EGJKUB4Q.js.map +0 -1
- package/dist/chunk-FQI5PFE7.js +0 -1866
- package/dist/chunk-FQI5PFE7.js.map +0 -1
- package/dist/chunk-FRYT3ID4.js +0 -684
- package/dist/chunk-FRYT3ID4.js.map +0 -1
- package/dist/chunk-G3P3ZDB4.js +0 -69
- package/dist/chunk-G3P3ZDB4.js.map +0 -1
- package/dist/chunk-K443GQY5.js +0 -24
- package/dist/chunk-K443GQY5.js.map +0 -1
- package/dist/chunk-N7KUTTCC.js +0 -3007
- package/dist/chunk-N7KUTTCC.js.map +0 -1
- package/dist/chunk-NGM237OO.js +0 -3410
- package/dist/chunk-NGM237OO.js.map +0 -1
- package/dist/chunk-NKCCGADE.js +0 -11285
- package/dist/chunk-NKCCGADE.js.map +0 -1
- package/dist/chunk-NNW3O6ZD.js +0 -108
- package/dist/chunk-NNW3O6ZD.js.map +0 -1
- package/dist/chunk-QZXKQB7Y.js +0 -414
- package/dist/chunk-QZXKQB7Y.js.map +0 -1
- package/dist/chunk-SFRMFGQ6.js +0 -158
- package/dist/chunk-SFRMFGQ6.js.map +0 -1
- package/dist/chunk-YCI2PNCS.js +0 -499
- package/dist/chunk-YCI2PNCS.js.map +0 -1
- package/dist/chunk-YODBNTTN.js +0 -7
- package/dist/chunk-YODBNTTN.js.map +0 -1
- package/dist/db-C5KVCOYT.js +0 -239
- package/dist/db-C5KVCOYT.js.map +0 -1
- package/dist/extract-bundle-KUBX6N6Z.js +0 -568
- package/dist/extract-bundle-KUBX6N6Z.js.map +0 -1
- package/dist/index.cjs +0 -4160
- package/dist/index.cjs.map +0 -1
- package/dist/index.d.cts +0 -413
- package/dist/index.d.ts +0 -413
- package/dist/index.js +0 -338
- package/dist/index.js.map +0 -1
- package/dist/location-data-repository-TTWF3OTM.js +0 -35
- package/dist/location-data-repository-TTWF3OTM.js.map +0 -1
- package/dist/server-5EX6XBIA.js +0 -33596
- package/dist/server-5EX6XBIA.js.map +0 -1
- package/dist/site-extract-repository-XSPJTCIL.js +0 -62
- package/dist/site-extract-repository-XSPJTCIL.js.map +0 -1
- package/dist/worker-XCPU4YSN.js +0 -142
- package/dist/worker-XCPU4YSN.js.map +0 -1
- package/docs/adr/0001-in-page-graphql-interception-for-anti-bot-scraping.md +0 -58
- package/docs/adr/0002-hybrid-smart-rag-vault-retrieval.md +0 -62
- package/docs/adr/0003-waive-unrecoverable-scheduled-model-cost.md +0 -22
- package/docs/adr/README.md +0 -13
- package/docs/final-tooling-spec.md +0 -206
- package/docs/hosted-location-data.md +0 -108
- package/docs/kernel-proxy-future-enhancements.md +0 -80
- package/docs/mcp-tool-craft-lint.generated.md +0 -183
- package/docs/mcp-tool-design-guide.md +0 -225
- package/docs/mcp-tool-manifest.generated.json +0 -22871
- package/docs/mcp-tool-quality-spec.md +0 -240
- package/docs/oauth-legal-review.md +0 -38
- package/docs/seo-crawl-report-spec.md +0 -287
- package/docs/specs/api-forge-spec.md +0 -234
- package/docs/specs/connected-services-control-plane-decoupling-spec.md +0 -1044
- package/docs/specs/deferred-work-spec.md +0 -86
- package/docs/specs/google-drive-bulk-access-and-mcp-schema-passthrough-spec.md +0 -1689
- package/docs/specs/kernel-stealth-captcha-test-matrix.md +0 -278
- package/docs/specs/main-mcp-integration-ownership-spec.md +0 -1164
- package/docs/specs/mcp-tool-definition-quality-audit-spec.md +0 -1602
- package/docs/specs/meta-ad-creative-media-resolution-spec.md +0 -31
- package/docs/specs/multimodal-image-memory-architecture-spec.md +0 -1022
- package/docs/specs/oauth-mcp-spec.md +0 -213
- package/docs/specs/query-fanout-transport-contract-fix.md +0 -45
- package/docs/specs/relationship-workspace-ai-behavior-plan.md +0 -26
- package/docs/specs/unified-credit-and-scheduled-execution-billing-spec.md +0 -995
- package/docs/tool-catalog-spec.md +0 -388
package/README.md
CHANGED
|
@@ -90,7 +90,7 @@ Build the branded one-click bundle:
|
|
|
90
90
|
npm run build:mcpb
|
|
91
91
|
```
|
|
92
92
|
|
|
93
|
-
The generated bundle is written to `build/mcpb/mcp-scraper-<version>.mcpb` and copied to `public/downloads/` for the hosted download. The current public bundle is `https://mcpscraper.dev/downloads/mcp-scraper.mcpb` (`0.
|
|
93
|
+
The generated bundle is written to `build/mcpb/mcp-scraper-<version>.mcpb` and copied to `public/downloads/` for the hosted download. The current public bundle is `https://mcpscraper.dev/downloads/mcp-scraper.mcpb` (`0.40.1`, SHA-256 `bf7727b9308e473633f0165562538c9de38640b184d8f1882f275704bb970476`). Install it by opening or dragging it into Claude Desktop. Claude displays the `MCP Scraper` install card, icon, and API-key configuration field from the bundle manifest.
|
|
94
94
|
|
|
95
95
|
The MCPB install exposes every tool — web-intelligence plus all `browser_*` tools — through the one `mcp-scraper` server.
|
|
96
96
|
|
|
@@ -175,6 +175,9 @@ env = { MCP_SCRAPER_API_KEY = "sk_live_your_key" }
|
|
|
175
175
|
- `workflow_run` — run hosted workflows such as `agent-packet`, `local-competitive-audit`, `map-comparison`, `serp-comparison`, `paa-expansion-brief`, and `ai-overview-language`; returns run metadata, summary, and artifact IDs.
|
|
176
176
|
- `workflow_status` — reopen a workflow run and list its current status and artifacts.
|
|
177
177
|
- `workflow_artifact_read` — pull generated workflow artifacts such as `evidence.json`, CSVs, Markdown briefs, and reports back into MCP context.
|
|
178
|
+
- `editorial_reading_room_guide` — load the reusable editorial workflow, content contract, or compact example before turning dense supplied material into a reading surface.
|
|
179
|
+
- `create_editorial_reading_room` — render fully authored, source-grounded articles into one self-contained mobile-first HTML reading room with contents, hamburger navigation, search, jump links, progress, text sizing, evening mode, and visible provenance. Hosted clients receive a private seven-day artifact; local stdio clients receive an openable file under the MCP Scraper output directory.
|
|
180
|
+
- `renew_editorial_reading_room_download` — issue a fresh signed URL for an unexpired private reading-room artifact.
|
|
178
181
|
- `rank_tracker_workflow` — generate a database schema, cron/heartbeat plan, ingestion workflow, metrics list, and implementation prompt for building rank trackers. It has modes for Maps rankings via `directory_workflow`/`maps_search`, organic rankings via `search_serp`, AI Overview citation tracking, and PAA source presence tracking. This planning tool does not spend credits.
|
|
179
182
|
- `credits_info`
|
|
180
183
|
|
|
@@ -229,7 +232,7 @@ The `mcp-scraper` server (and the MCPB bundle, which runs it) exposes both secti
|
|
|
229
232
|
|
|
230
233
|
All MCP tools expose output schemas and return `structuredContent` with the IDs, URLs, CSV paths, transcripts, browser session handles, replay paths, artifacts, recipe fields, or blueprint fields needed by the next step. Browser Agent tools keep a JSON text block for older clients, but structured data is the primary contract. All tools carry MCP annotations; file-writing tools such as replay downloads and annotations state their filesystem side effects.
|
|
231
234
|
|
|
232
|
-
The canonical tool inventory is generated at `docs/mcp-tool-manifest.generated.json`. The unified server exposes
|
|
235
|
+
The canonical tool inventory is generated at `docs/mcp-tool-manifest.generated.json`. The unified server exposes 175 tools: 85 scraper, browser, workflow, billing, and connected-service tools plus 90 durable-memory tools. Release verification compares the exact local and hosted tool-name sets, not only the count.
|
|
233
236
|
|
|
234
237
|
For contract parity, stdio and MCPB memory calls invoke the matching public tool on the hosted MCP Scraper `/mcp` endpoint. The hosted aggregate runtime owns MCP Scraper-specific billing, scheduling, credential, and in-process cutover policy; its internal `/memory/mcp-call` bridge is a fallback to the standalone memory service, not the public stdio execution path. Direct `mcp-memory` OAuth and stdio clients continue to use `memory.mcpscraper.dev` and must be verified as a separate dependent release surface.
|
|
235
238
|
|
package/package.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
|
1
1
|
{
|
|
2
2
|
"name": "mcp-scraper",
|
|
3
|
-
"version": "0.
|
|
3
|
+
"version": "0.40.1",
|
|
4
4
|
"description": "MCP server for MCP Scraper web intelligence tools",
|
|
5
5
|
"type": "module",
|
|
6
6
|
"main": "./dist/index.cjs",
|
|
@@ -24,14 +24,10 @@
|
|
|
24
24
|
},
|
|
25
25
|
"files": [
|
|
26
26
|
"dist",
|
|
27
|
-
"docs/*.md",
|
|
28
|
-
"docs/*.json",
|
|
29
|
-
"docs/adr/*.md",
|
|
30
|
-
"docs/specs/*.md",
|
|
31
27
|
"README.md"
|
|
32
28
|
],
|
|
33
29
|
"scripts": {
|
|
34
|
-
"build": "tsup
|
|
30
|
+
"build": "tsup",
|
|
35
31
|
"build:og-pages": "node scripts/build-og-pages.mjs",
|
|
36
32
|
"build:md": "node scripts/build-md-mirror.mjs",
|
|
37
33
|
"build:mcpb": "npm run build && node scripts/build-mcpb.mjs",
|
|
@@ -63,6 +59,8 @@
|
|
|
63
59
|
"email:inbound:setup": "node --import tsx scripts/email/setup-resend-inbound.ts",
|
|
64
60
|
"email:audience": "node scripts/run-ts-sandbox-safe.mjs scripts/email/sync-resend-audience.ts",
|
|
65
61
|
"email:drafts": "node scripts/run-ts-sandbox-safe.mjs scripts/email/create-resend-drafts.ts",
|
|
62
|
+
"email:workshop-reminders": "node --import tsx scripts/email/refresh-workshop-reminders.ts",
|
|
63
|
+
"email:workshop-reminders:apply": "node --import tsx scripts/email/refresh-workshop-reminders.ts --apply",
|
|
66
64
|
"billing:preview-credit-lot-repair": "node --import tsx scripts/billing/preview-credit-lot-repair.ts",
|
|
67
65
|
"billing:apply-credit-lot-repair": "node --import tsx scripts/billing/apply-credit-lot-repair.ts"
|
|
68
66
|
},
|
|
@@ -82,6 +80,7 @@
|
|
|
82
80
|
"inngest": "^4.4.0",
|
|
83
81
|
"ipaddr.js": "^1.9.1",
|
|
84
82
|
"jose": "^6.2.3",
|
|
83
|
+
"marked": "^18.0.7",
|
|
85
84
|
"mcpscraper-memory-tools": "^1.10.1",
|
|
86
85
|
"p-limit": "^7.3.0",
|
|
87
86
|
"papaparse": "^5.4.0",
|