mcp-scraper 0.2.13 → 0.2.15

package/README.md

@@ -34,6 +34,15 @@ npx -y -p mcp-scraper@latest mcp-scraper-cli agent install codex
 npx -y -p mcp-scraper@latest mcp-scraper-cli agent prompt agent-packet
 ```
 
+Check usage and upgrade concurrency from a normal terminal:
+
+```bash
+MCP_SCRAPER_API_KEY=sk_live_your_key npx -y -p mcp-scraper@latest mcp-scraper-cli billing concurrency info
+MCP_SCRAPER_API_KEY=sk_live_your_key npx -y -p mcp-scraper@latest mcp-scraper-cli billing concurrency checkout
+```
+
+Each account has 1 base concurrent operation. Extra concurrency slots are `$5/month` per slot. If an MCP tool hits `concurrency_limit_exceeded`, the error includes `active`, `limit`, `upgrade_url`, and the `mcp-scraper-cli billing concurrency checkout` command so the AI can explain the next step without guessing.
+
 Run local workflow reports:
 
 ```bash
@@ -146,6 +155,7 @@ env = { MCP_SCRAPER_API_KEY = "sk_live_your_key" }
 - `facebook_ad_search`
 - `facebook_page_intel`
 - `facebook_ad_transcribe`
+- `facebook_video_transcribe` — transcribe an organic Facebook reel, video, watch, or share URL. The tool renders the page, extracts the best public Facebook CDN MP4 URL, then returns transcript text, timestamped chunks, and the extracted MP4 URL for follow-up download.
 - `maps_search` — search Google Maps for multiple business/profile candidates. Use for GMB/GBP prospect lists, competitors, categories, and anything needing more than the Google 3-pack. In default `proxyMode: "location"`, retryable failures rotate to a new residential proxy and new browser session for up to 5 attempts. `maxResults` defaults to 10 and is capped at 50.
 - `maps_place_intel` — hydrate one known/named Google Maps business with profile details and optional reviews. Use after `maps_search` when a selected candidate needs full details.
 - `directory_workflow` — build city-by-city directory/prospecting datasets from Census place selection plus Google Maps searches. Use it for requests like "all cities over 100k population in Tennessee, then get 20 roofers from Maps." In default `proxyMode: "location"`, each city search rotates retryable failures to a new residential proxy and new browser session for up to 5 attempts. The saved CSV includes `source_location`, `result_position`, `business_name`, `review_stars`, `review_count`, `category`, `address`, `phone`, `hours_status`, `website_url`, `directions_url`, `place_url`, `cid`, `cid_decimal`, Census population, and ZIP groups.
@@ -180,9 +190,9 @@ For Google Maps tools (`maps_search` and `directory_workflow`), keep `proxyMode`
 
 The MCPB bundle and `mcp-scraper-combined` expose both sections through one local MCP server. The split `mcp-scraper` entrypoint exposes only the web-intelligence tools, and the split `browser-agent` entrypoint exposes only the browser-agent tools.
 
-Chaining and planning tools (`maps_search`, `directory_workflow`, `rank_tracker_blueprint`, `map_site_urls`, `youtube_harvest`, `facebook_ad_search`, `facebook_page_intel`) advertise an `outputSchema` and return `structuredContent` with the IDs, URLs, CSV paths, or blueprint fields needed by the next step. All tools carry MCP annotations (`readOnlyHint: true`; live-web tools use `openWorldHint: true`, while local planning and credit tools are closed-world/idempotent).
+Chaining and planning tools (`maps_search`, `directory_workflow`, `rank_tracker_blueprint`, `map_site_urls`, `youtube_harvest`, `facebook_ad_search`, `facebook_page_intel`, `facebook_video_transcribe`) advertise an `outputSchema` and return `structuredContent` with the IDs, URLs, CSV paths, transcripts, or blueprint fields needed by the next step. All tools carry MCP annotations (`readOnlyHint: true`; live-web tools use `openWorldHint: true`, while local planning and credit tools are closed-world/idempotent).
 
-The hosted MCP endpoint at `https://mcpscraper.dev/mcp` exposes the 15 web-intelligence tools plus `capture_serp_snapshot` and `capture_serp_page_snapshots` (17 total). Browser-agent tools are local stdio tools backed by the REST API under `https://mcpscraper.dev/agent/*`.
+The hosted MCP endpoint at `https://mcpscraper.dev/mcp` exposes the 16 web-intelligence tools plus `capture_serp_snapshot` and `capture_serp_page_snapshots` (18 total). Browser-agent tools are local stdio tools backed by the REST API under `https://mcpscraper.dev/agent/*`.
 
 ## Resources