Skip to main content
Glama
Crawlora-org

Crawlora MCP

Official

datasets_creators_search

Find TikTok creators by niche, followers, verified status, and engagement. Use filters and qualified engagement sorting to identify active influencers and retrieve contact emails for outreach.

Instructions

Search the TikTok creators dataset. Searches TikTok creators stored in a search index (one document per creator), with follower counts, verified status, niche, and engagement. Deleted and private accounts are excluded by default; set include_inactive=true to include them for historical lookups. Sort enum: followers_desc, engagement_desc, engagement_qualified_desc, likes_desc, relevance. Coverage note: followers_desc, likes_desc, and relevance are backed by profile fields present across the full dataset; the post-level engagement metrics (engagement_rate, avg_views, and the nested post_stats object) and the engagement_desc/engagement_qualified_desc sorts are currently populated for a growing subset of creators, prioritizing the highest-reach accounts. Creators without these metrics are still returned but sort last under engagement_desc and omit those fields; engagement_qualified_desc excludes them outright (they cannot clear its floors). engagement_desc ranks by raw engagement_rate with no eligibility floor — it surfaces a real stale-record + ratio-by-design trap: an account whose last real post was years ago can still carry an unrealistic rate computed from a handful of old posts. engagement_qualified_desc is the same metric restricted to creators with a recent post (last_post_at within 90 days), a minimum reach (avg_views >= 10000) and sample size (post_stats.sampled_posts >= 10), and a sanity ceiling (engagement_rate <= 50%) — use this, not the raw sort, for a "best engagement" leaderboard. Sound fields: post_stats.top_sounds holds only a creator's FIVE most-used sounds from the sampled posts, ranked by use count with ties broken by lowest music_id, so it is a top-5 view and not the creator's full sound list; post_stats.distinct_sounds gives the true number of different sounds the sample used. Use each sound's original boolean to tell TikTok-generated original audio from catalogue tracks - do NOT infer it from the title, because TikTok localizes the original-audio label (sonido original, som original, оригинальный звук, and at least fifteen more), so a title match silently reclassifies original audio as named tracks.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
qNoFull-text query over handle, nickname and bio, max 256 characters
pageNoPage number, defaults to 1
sortNoSort enum: followers_desc, engagement_desc, engagement_qualified_desc, likes_desc, relevance. engagement_desc ranks by raw post-level engagement rate, currently populated for a subset of creators (highest-reach first); creators without it sort last. engagement_qualified_desc is the same metric restricted to creators with a recent post (<=90d), a minimum reach (avg_views>=10000) and sample size (>=10 posts), and a sanity ceiling (<=50%) -- use this, not the raw sort, for a 'best engagement' leaderboard
nicheNoExact content-niche filter, max 128 characters
handleNoExact handle lookup (case-insensitive), e.g. khaby.lame; returns the single creator with that exact @handle
countryNoExact creator country/region filter, max 128 characters
verifiedNoFilter by verified badge; true keeps only verified creators
has_emailNoFilter by contact-email presence; true keeps only creators with an email
page_sizeNoPage size, defaults to 20 and maxes at 100; page * page_size must be <= 10000
include_emailNoReturn the stored contact email instead of a blanked value. Off by default for everyone, and honoured only for entitled (non-Free) API keys
min_followersNoMinimum follower count
include_inactiveNoInclude deleted/private accounts; defaults to false (only live accounts returned)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv1.17.5
    • changedInput schema / properties / sort / description
      Previous value: -"Sort enum: followers_desc, engagement_desc, likes_desc, relevance. engagement_desc ranks by post-level engagement rate, currently populated for a subset of creators (highest-reach first); creators without it sort last"New value: +"Sort enum: followers_desc, engagement_desc, engagement_qualified_desc, likes_desc, relevance. engagement_desc ranks by raw post-level engagement rate, currently populated for a subset of creators (highest-reach first); creators without it sort last. engagement_qualified_desc is the same metric restricted to creators with a recent post (<=90d), a minimum reach (avg_views>=10000) and sample size (>=10 posts), and a sanity ceiling (<=50%) -- use this, not the raw sort, for a 'best engagement' leaderboard"
    • addedInput schema / properties / sort / enum
      Added value: +[
      +  "followers_desc",
      +  "engagement_desc",
      +  "engagement_qualified_desc",
      +  "likes_desc",
      +  "relevance"
      +]
  2. Changed1 schema field changedv1.16.2
    • addedInput schema / properties / include_email
      Added value: +{
      +  "description": "Return the stored contact email instead of a blanked value. Off by default for everyone, and honoured only for entitled (non-Free) API keys",
      +  "type": "boolean"
      +}
  3. Addedv1.2.0

TDQS

A4.6/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and delivers exceptionally. It discloses default exclusions (deleted/private), coverage caveats (engagement metrics for a subset), the stale-record trap with raw `engagement_rate`, the top-5 limitation of `post_stats.top_sounds`, and the localization issue with original-audio labels. This goes far beyond a basic behavioral statement.

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

Conciseness5/5

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

The description is long, but every sentence contributes unique, non-redundant information. It is front-loaded with the core purpose, then systematically covers inactive handling, sort semantics, coverage notes, and sound-field caveats. There is no filler or repetition.

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?

The description is remarkably complete for a 12-parameter search tool with no output schema. It explains behavioral quirks, field-population gaps, and parameter interactions. The only notable absence is an explicit description of the response structure (e.g., fields like `id`, `username`, `engagement_rate`), though many are implied by the prose. This is a minor gap given the depth provided.

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

Parameters4/5

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

Schema description coverage is 100%, so baseline is 3. The description adds meaningful semantic depth beyond the schema, especially for `sort` (explaining floors, eligibility, and the rationale for each option) and `include_inactive` (historical lookup context). It also clarifies the meaning of output-related fields like `post_stats.distinct_sounds`, enriching parameter understanding.

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?

The description opens with a specific verb and resource: 'Search the TikTok creators dataset.' It enumerates the data points returned (follower counts, verified status, niche, engagement) and clarifies the document granularity (one per creator). This clearly distinguishes it from other TikTok endpoints and from other creator-focused tools.

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

Usage Guidelines4/5

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

Provides explicit within-tool guidance: when to use `include_inactive`, and a direct recommendation to use `engagement_qualified_desc` over `engagement_desc` for a 'best engagement' leaderboard. It does not name any alternative tools (e.g., tiktok_profile), so it lacks explicit cross-tool comparisons, but the guidance given is actionable and specific.

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