Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add mrocker/social-data-mcp --skill tiktok-transcriptsgit clone --depth 1 https://github.com/mrocker/social-data-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/mrocker/social-data-mcp/tiktok-transcripts)<a href="https://agentmods.dev/skills/mrocker/social-data-mcp/tiktok-transcripts"><img src="https://agentmods.dev/badge/skills/mrocker/social-data-mcp/tiktok-transcripts/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/mrocker/social-data-mcp/tiktok-transcripts"><img src="https://agentmods.dev/badge/skills/mrocker/social-data-mcp/tiktok-transcripts.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00064 | $0.00543 |
| Opus 5.5 | $0.00026 | $0.00217 |
| Sonnet 5.5 | $0.00013 | $0.00109 |
| Haiku 4.5 | $0.00006 | $0.00054 |
Grade A, and why
tiktok-transcripts scanned grade A with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 22d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Makes network callslowCapability
Not a fault in itself. Listed so you know the mod talks to something, and to what.
curl -s -X POST "https://api.apify.com/v2/acts/nick.cheng~tiktok-transcript-scraper/run-sync-get-dataset-items?token=$APIFY_TOKEN" \ What it actually says
TikTok transcripts
Pay-per-result Apify Actor nick.cheng/tiktok-transcript-scraper. No login, no cookies.
$0.003 per transcript delivered, same on every Apify plan; videos without captions cost nothing.
Needs APIFY_TOKEN (free account: https://console.apify.com/account/integrations).
When to use
- "What is said in these TikToks" →
videoUrls(full links,vm.tiktok.comshare links, or bare IDs) - A long list in a sheet →
listUrl(public CSV/TXT or a Google Sheet shared as "Anyone with the link")
Call it
curl -s -X POST "https://api.apify.com/v2/acts/nick.cheng~tiktok-transcript-scraper/run-sync-get-dataset-items?token=$APIFY_TOKEN" \
-H 'Content-Type: application/json' \
-d '{"videoUrls":["https://www.tiktok.com/@nasa/video/7667244788046892319"]}'
Or as an MCP tool: https://mcp.apify.com/?tools=nick.cheng/tiktok-transcript-scraper.
Output rows
itemType: "transcript"—videoId,url,authorHandle,authorNickname,description,createdAt,durationSeconds,transcriptLanguage,transcriptType(auto-generated/machine-translated),transcript(one string),subtitles[].segments({start, end, text}in seconds),inputOrdererror: true, chargedForThis: false— no captions, photo post, or deleted/private video; reason given
Limits
TikTok's own captions only — no speech recognition of its own; music-only clips and videos without
speech usually have none (no charge). TikTok's language detection is occasionally wrong — check
transcriptLanguage. No video lists per account: you supply the links. For play/like counts use
nick.cheng/tiktok-profile-stats-scraper (skill tiktok-profile-stats), which can include the transcript too.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 22d ago First seen · 40 lines · 64 tokens per session scan A ac807b01a5a7
tiktok-transcripts is a skill published in the GitHub repository mrocker/social-data-mcp (0 stars, last pushed 22d ago), licensed MIT. It adds 64 tokens to every session and 543 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 1 finding (makes network calls). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-10-18.
tiktok-transcripts compared with skills from other repositories
| Mod | Type | Stars | Last push | Licence | Scan | Tokens | Works with |
|---|---|---|---|---|---|---|---|
| tiktok-transcriptsmrocker/social-data-mcp | Skill | 0 | 22d ago | MIT | A | 64 | Claude Code, Codex |
| imagegenopenai/codex | Skill | 134k | today | Apache-2.0 | A | 113 | Codex |
| local-ai-agentsmicrosoft/ai-agents-for-beginners | Skill | 79k | 2d ago | MIT | A | 200 | Claude Code, Codex |
| playwright-climicrosoft/playwright | Skill | 100k | today | Apache-2.0 | A | 19 | Claude Code |
| browser-automationopenclaw/openclaw | Skill | 394k | today | MIT | A | 36 | Claude Code |
| systematic-debuggingobra/superpowers | Skill | 315k | 6d ago | MIT | A | 21 | Claude Code |
| next-cache-components-adoptionvercel/next.js | Skill | 143k | today | MIT | A | 95 | Claude Code |