Skip to main content
Glama

tiktok_search_users

Find TikTok creators by keyword — distinct authors ranking for the query, id + secUid, per-counter isApproximate flags, cursor pagination. Costs 1 credit. Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "q": "<q>"
    },
    "name": "tiktok_search_users"
  }
}

Input Schema

NameRequiredDescriptionDefault
qYesSearch query matched against usernames, display names and bios (min 2 characters).
cacheNoSet true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh.
limitNoMax items to return (default 20, max 100). Flat 1 credit per call.
cursorNoPagination cursor. Omit (or pass 0) for the first page; then pass the nextCursor value from the previous response verbatim — it carries the search session, not just an offset. A null nextCursor means the end of the results.
fieldsNoOptional comma-separated keys to keep on each result row (or on the object for single-item tools), e.g. id,url,publishedAt,engagement. Pagination keys are always kept. Does not change the price.
compactNoDefault true here: drop signed media URLs (video, image, avatar links and their expiry stamps) to keep the response small. Ids, permalinks, dates, text and metrics stay. On Threads, Facebook, Meta Ad Library and TikTok Shop tools request timings are dropped too. Pass false for the full body.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / compact / description
      Previous value: -"Default true here: drop signed media URLs (video, image, avatar links and their expiry stamps) to keep the response small. Ids, permalinks, dates, text and metrics stay. Pass false for the full body."New value: +"Default true here: drop signed media URLs (video, image, avatar links and their expiry stamps) to keep the response small. Ids, permalinks, dates, text and metrics stay. On Threads, Facebook, Meta Ad Library and TikTok Shop tools request timings are dropped too. Pass false for the full body."
  2. Changed2 schema fields changed
    • addedInput schema / properties / compact
      Added value: +{
      +  "default": true,
      +  "description": "Default true here: drop signed media URLs (video, image, avatar links and their expiry stamps) to keep the response small. Ids, permalinks, dates, text and metrics stay. Pass false for the full body.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / fields
      Added value: +{
      +  "description": "Optional comma-separated keys to keep on each result row (or on the object for single-item tools), e.g. id,url,publishedAt,engagement. Pagination keys are always kept. Does not change the price.",
      +  "type": "string"
      +}
  3. Changed1 schema field changed
    • removedInput schema / properties / fallback
      Removed value: -{
      -  "description": "Deprecated — no effect, removed on 2026-12-17. Sending it adds an X-Captapi-Warning response header. When native search is unavailable the response is an empty degraded page (0 credits).",
      -  "type": "boolean"
      -}
  4. Changed1 schema field changed
    • changedInput schema / properties / fallback / description
      Previous value: -"Opt into the slower fallback path when native search is unavailable (~2 min, capped at 100 s, degraded-empty on timeout). Default false — return an empty degraded page (0 credits) instead."New value: +"Deprecated — no effect, removed on 2026-12-17. Sending it adds an X-Captapi-Warning response header. When native search is unavailable the response is an empty degraded page (0 credits)."
  5. Changed1 schema field changed
    • changedInput schema / properties / fallback / description
      Previous value: -"Opt into the scraper actor when native search is unavailable (~2 min, capped at 100 s, degraded-empty on timeout). Default false — return an empty degraded page (0 credits) instead."New value: +"Opt into the slower fallback path when native search is unavailable (~2 min, capped at 100 s, degraded-empty on timeout). Default false — return an empty degraded page (0 credits) instead."
  6. Changed1 schema field changed
    • changedInput schema / properties / cache / description
      Previous value: -"Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. Envelope includes cached + cachedAt on hits."New value: +"Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh."
  7. Changed7 schema fields changed
    • changedInput schema / properties / cache / description
      Previous value: -"Set true to serve from the 24h response cache. Default false — always fetch fresh data."New value: +"Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. Envelope includes cached + cachedAt on hits."
    • changedInput schema / properties / cursor / description
      Previous value: -"Pagination offset. Leave at 0 for the first page; then pass the nextCursor value from the previous response. A null nextCursor means the end."New value: +"Pagination cursor. Omit (or pass 0) for the first page; then pass the nextCursor value from the previous response verbatim — it carries the search session, not just an offset. A null nextCursor means the end of the results."
    • removedInput schema / properties / cursor / minimum
      Removed value: -1
    • changedInput schema / properties / cursor / type
      Previous value: -"integer"New value: +"string"
    • addedInput schema / properties / fallback
      Added value: +{
      +  "description": "Opt into the scraper actor when native search is unavailable (~2 min, capped at 100 s, degraded-empty on timeout). Default false — return an empty degraded page (0 credits) instead.",
      +  "type": "boolean"
      +}
    • changedInput schema / properties / limit / description
      Previous value: -"Max items to return. Default 20, max 100. Billed per result."New value: +"Max items to return (default 20, max 100). Flat 1 credit per call."
    • changedInput schema / properties / q / description
      Previous value: -"Search query matched against usernames, display names and bios."New value: +"Search query matched against usernames, display names and bios (min 2 characters)."
  8. Changed1 schema field changed
    • changedInput schema / properties / limit / description
      Previous value: -"Max items to return. Default 20, max 100. Flat 1 credit on the native path."New value: +"Max items to return. Default 20, max 100. Billed per result."
  9. Changed1 schema field changed
    • changedInput schema / properties / limit / description
      Previous value: -"Max items to return. Default 20, max 100. Billed per result."New value: +"Max items to return. Default 20, max 100. Flat 1 credit on the native path."
  10. Added

TDQS

A3.9/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the 1-credit cost, that empty results and failures are never charged, the 24h cache behavior and default freshness, approximate counters via isApproximate flags, and session-bound cursor pagination. It stops short of describing result ordering or any rate limits.

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?

A single dense paragraph that front-loads purpose before cost and caching rules; every clause carries information, though the telegraphic em-dash style is slightly harder to scan than separate sentences.

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 6-parameter, no-annotation, no-output-schema search tool, the description covers cost model, caching, pagination semantics and result composition well. Minor gaps remain on result ordering and whether searches draw on a specific index, but nothing critical to calling it correctly is missing.

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 the schema already explains q, cache, limit, cursor, fields and compact. The description only restates the cache default and notes cursor pagination exists, adding no new syntax or format detail beyond the structured fields.

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 ('Find TikTok creators by keyword') plus the exact result shape ('distinct authors ranking for the query, id + secUid'), which separates it from hashtag-, suggestion- and ad-library-oriented siblings without needing their schemas.

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?

Offers one concrete usage decision — pass cache=true for a free cache hit versus leaving the default fresh fetch — but gives no guidance on when to choose this tool over tiktok_search_by_hashtag or tiktok_top_search, and no stated preconditions for the query.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.