Skip to main content
Glama
thenavidm

ScrapeCreators MCP Server

by thenavidm
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Search

facebook_ad_library_search_post

Search Facebook's Ad Library by keyword to retrieve matching ads. Filter by language, country, status, or media type for targeted ad research.

Instructions

Searches the Meta Ad Library by keyword and returns matching ads. Supports filtering by language with a 2-letter code such as EN or ES. Each result includes ad_archive_id, page_name, is_active, publisher_platform, and a snapshot with body text, images, videos, and cta_text. Both GET and POST are supported. Use GET for normal requests. If the cursor becomes too large after extensive pagination, use POST and send the same parameters in the JSON body. Potentially consumes paid API credits; requires confirm=true. Read-like POST requests do not publish to social platforms.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
trimNoSet to true for a trimmed down version of the response
queryNoKeyword to search for
cursorNoCursor to paginate through results
statusNoStatus of the ad. Defaults to ACTIVE.
accountNoNamed private ScrapeCreators account; selects credentials, not a remote account ID.
ad_typeNoSearch for all ads or only political and issue ads
confirmNoMust be true for the specific approved credit-consuming research call.
countryNoThis can only be one country. It has to be the 2 letter code for the country. It defaults to ALL.
payloadNoComplete JSON request body instead of body flags. Preserves current endpoint fields and values.
sort_byNoSort by impressions (high to low), or Most Recent (relevancy_monthly_grouped). Defaults to impressions.
end_dateNoImpressions end date. Needs to be in YYYY-MM-DD format.
languageNoLanguage to filter ads on. Needs to be a 2 letter language code, such as EN, ES, or FR.
media_typeNoMedia type of the ad. Defaults to ALL. Meme just means the ad has text and an image. No clue why they call it meme.
start_dateNoImpressions start date. Needs to be in YYYY-MM-DD format.
search_typeNoIf you want to search by exact phrase or not
payload_fileNoRegular local JSON body file, at most 5 MB. Cannot be mixed with body flags or payload.

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?

Adds real context beyond the annotations: it warns that the call 'Potentially consumes paid API credits; requires confirm=true' and explicitly resolves the apparent read/write ambiguity by noting 'Read-like POST requests do not publish to social platforms.' This usefully explains why readOnlyHint=false on a de-facto read operation. It does not describe rate limits or pagination semantics beyond the cursor hint.

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 pagination strategy, then the credit/confirm caveat. Sentences are tight and each carries useful information, though the language-filter sentence restates schema content and could be dropped.

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?

With no output schema, the description compensates by enumerating returned fields (ad_archive_id, page_name, is_active, publisher_platform, snapshot with body/images/videos/cta_text), and it covers the credit cost and confirm requirement. For a 16-parameter tool, it stops short of explaining the payload vs. payload_file vs. body-flag interaction, which an agent would need to choose correctly.

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 each of the 16 parameters is already documented in the schema, including defaults, enums, and the language 2-letter-code format. The description's mention of language filtering and result fields is largely duplicative, so baseline 3 is appropriate.

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: 'Searches the Meta Ad Library by keyword and returns matching ads.' It also explains the GET/POST distinction, which is effectively the differentiator from the sibling facebook_ad_library_search, though it never names that sibling explicitly. Clear purpose, near-miss on explicit sibling differentiation.

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?

Gives concrete routing guidance: 'Use GET for normal requests. If the cursor becomes too large after extensive pagination, use POST and send the same parameters in the JSON body' and notes confirm=true is required. It omits when NOT to use this tool (e.g. preferring the company-ads or ad-details siblings for those use cases).

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