Skip to main content
Glama
Social Fetch MCP

Social Fetch MCP

Official

Search LinkedIn Ad Library ads

linkedin_adLibrary_ads_search_list
Read-onlyIdempotent

Search LinkedIn Ad Library ads by company, keyword, or company ID, with optional country and date filters. Use pagination cursors to retrieve additional ad results.

Instructions

Search LinkedIn Ad Library ads by company, keyword, or company id. Optional inputs: company, keyword, companyId, countries, startDate and 2 more. Returns a list (use cursor when paginated). countries is one comma-separated string, e.g. "US,CA", not an array.

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": "linkedin_adLibrary_ads_search_list"
  }
}

Input Schema

NameRequiredDescriptionDefault
cursorNoOpaque pagination cursor from a previous response.
companyNoCompany name to search for in the LinkedIn Ad Library.
contextYesDescribe the user's underlying goal in one sentence, not the tool you are calling.
endDateNoOptional end date filter in YYYY-MM-DD format.
keywordNoKeyword or phrase to search for in LinkedIn Ad Library ads.
companyIdNoLinkedIn company id to search for in the Ad Library.
countriesNoOptional comma-separated list of country codes (for example US,CA,MX).
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.
startDateNoOptional start date filter in YYYY-MM-DD format.
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.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, openWorld and non-destructive, so the safety profile is covered. The description adds genuine behavior beyond that: it returns a list, a cursor is used when the result is paginated, and countries must be passed as one comma-separated string rather than an array — the last point being a common calling mistake.

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?

Three short sentences, front-loaded with purpose and followed by input notes and the return shape; nothing is padded. The vague 'and 2 more' enumeration slightly undercuts an otherwise tight structure.

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 10-parameter read-only search tool with no output schema, the description covers purpose, filter inputs, pagination behavior and return type. An agent could call it correctly, with the only gap being no guidance on how the filters combine or whether one is required.

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 is already documented, including the countries comma-separated format and the YYYY-MM-DD date patterns. The description's parameter content largely restates the schema, and its 'and 2 more' phrasing is uninformative; baseline 3 applies.

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?

The description gives a specific verb and resource ('Search LinkedIn Ad Library ads') and names the three primary search modes (company, keyword, company id). It is clearly distinguishable from the facebook/tiktok equivalents by platform plus its 'search_list' scope, though it never contrasts with the single-record sibling linkedin_adLibrary_ad_get.

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?

Usage is only implied: the phrase 'by company, keyword, or company id' suggests at least one filter should be supplied, and the cursor note implies follow-up calls for pagination. There is no explicit statement of when to choose this over linkedin_adLibrary_ad_get or the other platform Ad Library tools, and no prerequisites or exclusions.

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