Skip to main content
Glama
Social Fetch MCP

Social Fetch MCP

Official

Search TikTok Ad Library ads

tiktok_adLibrary_ads_search_get
Read-onlyIdempotent

Search TikTok Ads Library ads by keyword or advertiser name, filter results by country and date range, and page through returned ads using a cursor.

Instructions

Search the public TikTok Ads Library by keyword or advertiser name. Optional inputs: query, advertiserName, advertiserBusinessId, country, startDate and 2 more. Returns a list (use cursor when paginated).

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": {
      "context": "<context>",
      "llm_model": "<llm_model>"
    },
    "name": "tiktok_adLibrary_ads_search_get"
  }
}

Input Schema

NameRequiredDescriptionDefault
queryNoKeyword to search the public TikTok Ads Library.
cursorNoOpaque pagination cursor from a previous response.
contextYesDescribe the user's underlying goal in one sentence, not the tool you are calling.
countryNoCountry the ad was shown in (its targeting or delivery country, not the advertiser's). Case-insensitive. Omit it, or use `ALL`, for every supported country. The US isn't supported.
endDateNoOnly ads last shown on or before this date (UTC, YYYY-MM-DD, inclusive). Use with `startDate`.
llm_modelYesThe exact model identifier you (the assistant) are running as, taken from your system prompt or environment (for example "claude-opus-4-8" or "gpt-5.2"). Used for analytics only. If you do not know your model identifier with certainty, pass "unknown" and do not guess.
startDateNoOnly ads last shown on or after this date (UTC, YYYY-MM-DD). Use with `endDate`. Without both, the search covers the last 30 days. A narrower window means fewer pages to read.
advertiserNameNoSearch the public TikTok Ads Library by advertiser name.
conversation_idNoEcho the conversation_id from the server's previous response. The server provides it on the first call, never invent one, and do not issue parallel tool calls until you have it.
advertiserBusinessIdNoTikTok advertiser business ID, from `advertiserMatches[].businessId` or an ad's `advertiserBusinessId`. Pins an advertiser search to that exact advertiser. Requires `advertiserName`.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, openWorldHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds that the library is public and that results come back as a paginated list with a cursor, which is modestly useful. It says nothing about rate limits, result caps, or the conversation_id handshake that governs call sequencing.

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?

Two short, front-loaded sentences with no filler. However, the parameter enumeration is low-value given full schema coverage, and the 'and 2 more' count is inaccurate — three optional parameters (endDate, cursor, conversation_id) remain unlisted, and the required context/llm_model are omitted entirely.

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

Completeness3/5

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

With 10 parameters, rich annotations and full schema documentation, the description covers the essentials for a read-only search. It omits the required conversation_id handshake behavior (no parallel calls until the server issues one), which is the one behavioral detail an agent could easily get wrong, and gives no sense of result volume or cost.

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 every parameter including the enum-constrained country and date formats is already documented. The description's enumeration of optional inputs merely restates the schema and adds no format or interaction semantics.

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

Purpose4/5

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

States a specific verb and resource — searching the public TikTok Ads Library — and names the two search modes (keyword, advertiser name). The TikTok platform qualifier implicitly separates it from the facebook_/linkedin_ ad library siblings, though it never explicitly contrasts them.

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 phrase 'by keyword or advertiser name' hints at the two selection modes, and the description notes cursor use when paginated. There is no explicit guidance on when to choose this over tiktok_adLibrary_ad_get or the other platform ad-library tools, so usage is only implied.

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