restore: verified scale stats + marketing copy

Founder confirmed the production-scale numbers are real and the
original marketing copy is intentional — the prior cleanup pass was
over-aggressive. Restore:

- README.md: re-insert the "Powering 15M+ transcripts every month /
  500K+ transcripts processed daily / 49ms median response time"
  banner and the "Trusted in production by youtubetotranscript.com /
  recapio.com" line, directly after the badge block and before the
  first "---".
- README.md: re-insert the "Production scale (15M+ req/mo))" row into
  the comparison table, between "OAuth 2.1 + API key auth" and "Works
  on mobile Claude & web Claude" (same format as youtube-mcp's).
- smithery.yaml: re-insert "Production-scale (15M+ requests/month,
  49ms median)." before the OAuth/API key sentence.
- marketplace.json + .claude-plugin/marketplace.json: restore the
  short description tail to "...by TranscriptAPI: 15M+
  transcripts/month." (.cursor-plugin has no marketplace.json in this
  repo, and long descriptions are untouched).

Co-Authored-By: CRHQ <noreply@crhq.ai>

Author: therohitdas

.claude-plugin/marketplace.json

@@ -6,7 +6,7 @@
     "url": "https://transcriptapi.com"
   },
   "metadata": {
-    "description": "YouTube MCP and YouTube Skill packages by TranscriptAPI.",
+    "description": "YouTube MCP and YouTube Skill packages by TranscriptAPI: 15M+ transcripts/month.",
     "version": "1.2.0"
   },
   "plugins": [

README.md

@@ -21,6 +21,9 @@
   <a href="./LICENSE"><img src="https://img.shields.io/badge/License-MIT-4CAF50?style=for-the-badge" alt="MIT License"/></a>
 </p>
 
+> **Powering 15M+ transcripts every month** - 500K+ transcripts processed daily - 49ms median response time
+> Trusted in production by [youtubetotranscript.com](https://youtubetotranscript.com) (~11M/mo) and [recapio.com](https://recapio.com) (~2.8M/mo).
+
 ---
 
 ## 🧩 What is this?
@@ -59,6 +62,7 @@ Most YouTube integrations do one thing: pull a single transcript. **This is a fu
 | Channel & playlist extraction            | ✅ Yes             | ❌ No |
 | Latest-uploads monitoring (free)         | ✅ Yes             | ❌ No |
 | OAuth 2.1 + API key auth                 | ✅ Both            | ❌ Usually neither |
+| Production scale (15M+ req/mo)           | ✅ Yes             | ❌ Hobbyist scrapers |
 | Works on mobile Claude & web Claude      | ✅ Yes             | ❌ No |
 | Agent-friendly error messages            | ✅ Yes             | ❌ Bare HTTP codes |
 | No yt-dlp, no headless browser, no binaries | ✅ Just an API call | ❌ Blocked on cloud IPs |

marketplace.json

@@ -6,7 +6,7 @@
     "url": "https://transcriptapi.com"
   },
   "metadata": {
-    "description": "YouTube MCP and YouTube Skill packages by TranscriptAPI.",
+    "description": "YouTube MCP and YouTube Skill packages by TranscriptAPI: 15M+ transcripts/month.",
     "version": "1.2.0"
   },
   "plugins": [

smithery.yaml

@@ -10,8 +10,9 @@ startCommand:
   description: >-
     YouTube transcripts + YouTube search MCP for AI agents. 12 tools: transcript
     extraction, video & channel metadata, video search, channel search, channel
-    browsing, playlist extraction, and new-upload polling. Authenticate via
-    OAuth (Dynamic Client Registration) or API key.
+    browsing, playlist extraction, and new-upload polling. Production-scale
+    (15M+ requests/month, 49ms median). Authenticate via OAuth (Dynamic Client
+    Registration) or API key.
 
 metadata:
   homepage: https://transcriptapi.com