mcp-scraper 0.12.0 → 0.14.0

package/README.md

@@ -88,7 +88,7 @@ Build the branded one-click bundle:
 npm run build:mcpb
 ```
 
-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` (`0.12.0`, SHA-256 `2a0dfdc53e93d48588ef672c6daf0ec0e6194b3f938add02b106bf5e86c20ef3`). 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.
+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` (`0.14.0`, SHA-256 `01b37c065b803a19ac824b82058b311b115e272d9be01d870094737c74b58753`). 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.
 
 The MCPB install exposes every tool — web-intelligence plus all `browser_*` tools — through the one `mcp-scraper` server.
 
@@ -174,6 +174,17 @@ env = { MCP_SCRAPER_API_KEY = "sk_live_your_key" }
 - `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.
 - `credits_info`
 
+### Connected-account tools
+
+- `list_service_connections` — list this caller's tenant-owned OAuth connections and the exact live read/action tools available on each account. Connections are never shared between customers.
+- `export_connected_service_data` — fetch a bounded Gmail, Google Calendar, or Zoom time range in one MCP call. The server handles provider pagination, Gmail hydration, normalization, and continuation. Small exports return inline; larger exports become private JSONL retained for seven days with a 15-minute signed URL. Attachments remain metadata-only and oversized individual bodies/transcripts are truncated with warnings.
+- `renew_connected_data_download` — issue a fresh 15-minute signed URL for an unexpired private export artifact without pulling the provider again.
+- `read_service_connection` — run one small live read by exact allowlisted name. Do not loop it over a time range; use `export_connected_service_data` for email, calendar, recording, or transcript collections.
+- `call_service_connection_action` — run one exact mutation only after the account action switch is enabled. GitHub, Gmail, Calendar, Slack, Zoom, Facebook, Google Analytics, X, and YouTube actions remain provider-policy and tenant gated.
+- `set_scheduled_action_connections` — bind exact tenant connections and exact tool grants to one scheduled action. Deterministic connection syncs are model-free and one schedule occurrence counts as one metered event even when provider pagination spans many pages.
+
+GitHub uses the same provider-neutral read/action bridges: 27 reads cover repository discovery, issues, pull requests, commits, releases, and workflows; 20 mutations remain gated. Private-repository and workflow access requires reconnecting the OAuth account after the expanded scope set is deployed.
+
 ### Browser-agent tools
 
 - `browser_open` — open a direct/no-proxy hosted browser session. Pass a saved profile name to load an authenticated session. Returns a human `watch_url`.
@@ -207,7 +218,7 @@ The `mcp-scraper` server (and the MCPB bundle, which runs it) exposes both secti
 
 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.
 
-The canonical tool inventory is generated at `docs/mcp-tool-manifest.generated.json`. Both the `mcp-scraper` stdio server and the hosted endpoint at `https://mcpscraper.dev/mcp` expose the same 153 tools: 68 scraper, browser, workflow, billing, and connected-service tools plus 85 durable-memory tools. Release verification compares the exact local and remote tool-name sets, not only the count.
+The canonical tool inventory is generated at `docs/mcp-tool-manifest.generated.json`. Both the `mcp-scraper` stdio server and the hosted endpoint at `https://mcpscraper.dev/mcp` expose the same 155 tools: 70 scraper, browser, workflow, billing, and connected-service tools plus 85 durable-memory tools. Release verification compares the exact local and remote tool-name sets, not only the count.
 
 ## Resources