Skip to main content
Glama
thenavidm

ScrapeCreators MCP Server

by thenavidm
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Video Info

tiktok_video_info

Fetch detailed metadata, engagement stats, video URLs, author and music info for a TikTok video by URL, and optionally its transcript/captions.

Instructions

Fetches detailed data for a single TikTok video by URL, including its metadata, engagement stats, and optionally its transcript/captions. Returns aweme_detail with desc (caption), statistics (play_count, digg_count/likes, comment_count, share_count, collect_count), video URLs, author info, and music info; also returns transcript in WEBVTT format if get_transcript=true. For no-watermark video URLs, use aweme_detail.video.download_no_watermark_addr.url_list[0] when it exists. If it is missing and aweme_detail.video.has_watermark is false, use aweme_detail.video.play_addr.url_list[0] instead. If has_watermark is true and download_no_watermark_addr is missing, TikTok did not return a no-watermark URL for that video. Potentially consumes paid API credits; requires confirm=true. Read-like POST requests do not publish to social platforms.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
urlYesTikTok video URL
trimNoSet to true to get a trimmed response
regionNoRegion of the proxy. Sometimes you'll need to specify the region if you're not getting a response. Commonly for videos from the Phillipines, in which case you'd use 'PH'. Use 2 letter country codes like US, GB, FR, etc
accountNoNamed private ScrapeCreators account; selects credentials, not a remote account ID.
confirmNoMust be true for the specific approved credit-consuming research call.
cache_max_ageNoIf we have a response in the cache that is this many days old or newer, return the cached response (0 credits, with "cached": true and a "cached_at" timestamp). Otherwise, scrape a live result (1 credit). [See the Caching page for details.](https://docs.scrapecreators.com/caching)
download_mediaNoSet to true to download the video/images and get back permanent Supabase URLs. Costs 10 credits if media is found, 1 credit otherwise.
get_transcriptNoGet transcript of the video

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.0.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations declare readOnlyHint=false, which the description usefully explains away ('Read-like POST requests do not publish to social platforms'), and it adds cost/credit and confirm=true requirements not present in annotations. Does not mention rate limits or failure behavior, so it stops short of a 5.

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?

Front-loads purpose, then outputs, then cost/confirm caveats. The multi-sentence no-watermark fallback logic is verbose but each branch is actionable; no sentence is pure filler, though the URL-selection paragraph could be tightened.

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?

There is no output schema, and the description compensates by naming the returned fields (desc, statistics, video, author, music, transcript in WEBVTT), plus cost and confirm requirements. Only error/edge behavior and caching semantics (left to the schema) are unaddressed.

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%, so all eight parameters are already documented in the schema. The description only echoes get_transcript behavior and otherwise describes outputs, not input semantics, so the baseline 3 is appropriate.

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: 'Fetches detailed data for a single TikTok video by URL.' The single-video/by-URL scoping distinguishes it from profile-level siblings (tiktok_profile, tiktok_profile_videos) and from transcript-only tools (tiktok_transcript), and the return contents are enumerated concretely.

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?

Gives operational conditions (paid credits, requires confirm=true) and explains when to prefer the no-watermark vs play_addr URL, but never routes the agent between sibling tools or states when this tool is the wrong choice versus e.g. tiktok_transcript. Usage is implied rather than framed as alternatives.

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

Deploy Server

Other Tools