Skip to main content
Glama
zrk-scrapers-mcp

zrk-scrapers-mcp

by Zrk1212

TikTok Transcript Scraper

get_tiktok_transcripts

Fetch transcripts from TikTok video URLs or profile handles, using native captions first and AI speech-to-text when captions are missing. Returns timestamped segments, language, views and likes.

Instructions

Get transcripts of TikTok videos from video URLs or profile handles. Uses TikTok's own captions first and AI speech-to-text only when captions are missing. Returns transcript text, timestamped segments, language, views and likes. Priced per transcript. Runs the Apify actor zrk1212/tiktok-transcript-scraper on your Apify account.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "get_tiktok_transcripts"
  }
}

Input Schema

NameRequiredDescriptionDefault
maxItemsNoMost result rows to return in this response (default 50). The run may produce more; page with get_run_results.
profilesNoTikTok handles (without @) to pull recent videos from.
waitSecsNoSeconds to wait for the run to finish (default 120). If it is still running, use get_run_results later.
videoUrlsNoTikTok video URLs.
aiFallbackNoUse AI transcription when captions are missing (default true, billed per minute).
extraInputNoAny other input field of the Apify actor zrk1212/tiktok-transcript-scraper, passed through as-is. See https://apify.com/zrk1212/tiktok-transcript-scraper/input-schema
maxChargeUsdNoHard spending cap for this run in USD (default 1). Apify stops charging when it is reached.
preferredLanguageNoPreferred caption language code, e.g. 'en'.
maxVideosPerProfileNoRecent videos per profile (default 4).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.9/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations already declare this is a non-read-only, open-world, non-idempotent run, so the description's additions are what count: it discloses the caption-first fallback logic, per-transcript billing, the concrete cost model, and the underlying Apify actor. It does not explain the wait/polling semantics, which is the main remaining behavioral gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Five sentences, front-loaded with purpose and input modes, then behavior, then pricing. Slight redundancy between 'Priced per transcript' and the actor/billing sentence, but nothing is wasted.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 9-parameter, open-world, paid scraping tool with no output schema, the description covers inputs, cost, fallback strategy, and even names the returned fields. The missing piece is guidance on the asynchronous run/wait pattern the schema parameters imply.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and every parameter is documented inline, so the baseline is 3. The description only restates the two input modes and the preferred-language/caption behavior, adding no syntax or format detail beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Get transcripts of TikTok videos') plus both accepted input modes (video URLs or profile handles). The sibling tools listed are all unrelated domains, so no explicit differentiation is needed for an agent to pick this one.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage by naming the two input routes and flagging per-transcript pricing, which helps an agent decide whether to spend money. However, it gives no explicit when-to-use/when-not guidance, and it never points to get_run_results for the async follow-up that the schema relies on.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.