Skip to main content
Glama
Sign In

Nexscope

by io.github.nexscope
OverviewDiscussionsAdmin

LinkedIn Ad Library Search Ads

social_linkedin_ads_search
Read-only

Searches the LinkedIn Ad Library by company name, keyword, or companyId with optional country and date filters. Custom date filtering requires both startDate and endDate. LinkedIn accepts dates from the date one year ago through yesterday. Each ad includes id, description, headline, adType, advertiser, targeting details, image or video URLs, totalImpressions, and impressionsByCountry. Date and impression fields are nullable when LinkedIn does not expose them on the public ad page. Supports pagination via paginationToken. Search results keep a consistent field set when detail hydration fails, with null or empty defaults for unavailable fields. The existing image, video, organicVideo, preRollVideo, and carouselImages fields keep their previous values. paidForBy is the public paying entity when LinkedIn shows one, without the 'Paid for by' prefix. targetingTable lists the public targeting-category flags that LinkedIn shows; it does not expand a collapsed location summary into individual locations. imageSources and thumbnailSources list the creative-image and video-poster URLs LinkedIn supplies. videoSources lists native video renditions as { src, type, bitrate }; preRollVideoSources uses the same structure but contains only pre-roll ad video. type and bitrate are null when absent; bitrate is in bits per second. Choose the lowest positive bitrate for a smaller video download, rather than assuming source order ranks quality. All four source fields are arrays and are empty when unavailable. Document-cover previews are included in imageSources where available, including search fallback results. LinkedIn may expose only one image or thumbnail resolution; URLs are signed and should not be rewritten to guess smaller sizes. Search detail hydration is best-effort, so blocked or timed-out detail fetches can leave videoSources empty even for a video ad. No extra parameter or credit charge is required. adDuration is the ad availability date-range text, not video playback duration; it is an empty string with null startDate/endDate when LinkedIn does not publish the availability block. Completed lookups cost at least 10 Nexscope credits. Actual cost depends on the operation and requested options. Repeated requests may purchase data again. LinkedIn Ad Library Search Ads API View Pricing Search the LinkedIn Ad Library with native media variants where available. LinkedIn may expose only one image or thumbnail size. 1 credit per request Searches the LinkedIn Ad Library by company name, keyword, or companyId with optional country and date filters. Custom date filtering requires both startDate and endDate. LinkedIn accepts dates from the date one year ago through yesterday. Each ad includes id, description, headline, adType, advertiser, targeting details, image or video URLs, totalImpressions, and impressionsByCountry. Date and impression fields are nullable when LinkedIn does not expose them on the public ad page. Supports pagination via paginationToken. Search results keep a consistent field set when detail hydration fails, with null or empty defaults for unavailable fields. The existing image, video, organicVideo, preRollVideo, and carouselImages fields keep their previous values. paidForBy is the public paying entity when LinkedIn shows one, without the 'Paid for by' prefix. targetingTable lists the public targeting-category flags that LinkedIn shows; it does not expand a collapsed location summary into individual locations. imageSources and thumbnailSources list the creative-image and video-poster URLs LinkedIn supplies. videoSources lists native video renditions as { src, type, bitrate }; preRollVideoSources uses the same structure but contains only pre-roll ad video. type and bitrate are null when absent; bitrate is in bits per second. Choose the lowest positive bitrate for a smaller video download, rather than assuming source order ranks quality. All four source fields are arrays and are empty when unavailable. Document-cover previews are included in imageSources where available, including search fallback results. LinkedIn may expose only one image or thumbnail resolution; URLs are signed and should not be rewritten to guess smaller sizes. Search detail hydration is best-effort, so blocked or timed-out detail fetches can leave videoSources empty even for a video ad. No extra parameter or credit charge is required. adDuration is the ad availability date-range text, not video playback duration; it is an empty string with null startDate/endDate when LinkedIn does not publish the availability block.

Input Schema

NameRequiredDescriptionDefault
companyNoThe company name to search for. 'Microsoft' for example
endDateNoEnd date in YYYY-MM-DD format. Must be used with startDate and cannot be today or a future date.
keywordNoThe keyword to search for
companyIdNoThe company id to search for
countriesNoComma separated list of countries. Example: US,CA,MX
startDateNoStart date in YYYY-MM-DD format. Must be used with endDate and cannot be earlier than the date one year ago.
paginationTokenNoPagination token to paginate through results

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

B3.4/5.0
Behavior4/5

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

Beyond the annotations (readOnlyHint, openWorldHint, destructiveHint=false), the description discloses substantive behavior: nullable date and impression fields, best-effort detail hydration that can leave videoSources empty even for a video ad, signed URLs that must not be rewritten, empty-array defaults, and paginationToken paging. The credit statements are internally inconsistent ('No extra parameter or credit charge is required' followed by 'Completed lookups cost at least 10 Nexscope credits' and '1 credit per request'), which undermines an otherwise rich disclosure.

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

Conciseness2/5

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

The text is roughly 500 words and is duplicated almost verbatim, including a pasted marketing block ('LinkedIn Ad Library Search Ads API View Pricing...'), which bloats the definition badly. Much of the length is output-field minutiae (bitrate semantics, adDuration, paidForBy prefix handling) that, while useful, is not front-loaded and buries the operational essentials.

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 no output schema, the extensive field documentation (imageSources, videoSources, targetingTable, adDuration) is legitimately needed and mostly complete. Gaps remain: no statement of result volume or rate limits, no clarification of how optional filters combine, and contradictory cost information leaves an agent unable to predict charge.

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 baseline is 3 and the schema already explains each parameter's format and date bounds. The description restates the date-pairing rule but adds no meaning about how company, companyId, and keyword interact, whether countries narrows the other keys, or what happens when no filter is supplied.

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 opening sentence gives a specific verb and resource ('Searches the LinkedIn Ad Library') plus the three search keys and optional filters, so an agent knows exactly what this does. It does not explicitly differentiate itself from plausible siblings such as social_linkedin_ad (single-ad detail) or the Facebook/TikTok ad-library search tools, leaving that distinction to be inferred.

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 constraints are stated for the date filters (startDate and endDate must be used together; dates allowed only from one year ago through yesterday), which is genuine when-to guidance. However, there is no guidance on when to choose this over social_linkedin_ad or another ad-library search, and no statement about whether company, keyword, and companyId can be combined or are mutually exclusive — all parameters are optional, so the no-argument case is undefined.

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

All Nexscope toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources