LinkedIn Ads MCP Server

linkedin get insights

linkedin_get_insights

Read-onlyIdempotent

Run a LinkedIn Ads report grouped by one pivot to analyze performance by date range, granularity, and metrics; computes CTR, CPC, and CPM from raw data.

Instructions

Run a LinkedIn Ads report grouped by one pivot. This is the analytics finder: one pivot, any granularity, and up to 20 fields including dateRange and pivotValues. Ratios such as CTR, CPC and CPM do not exist in the API and are computed here from the raw terms.

Input Schema

Name	Required	Description
`pivot`	No	Grouping. Defaults to CAMPAIGN. One of: ACCOUNT, CAMPAIGN_GROUP, CAMPAIGN, CREATIVE, COMPANY, SHARE, CONVERSION, MEMBER_COMPANY, MEMBER_COMPANY_SIZE, MEMBER_INDUSTRY, MEMBER_SENIORITY, MEMBER_JOB_TITLE, MEMBER_JOB_FUNCTION, MEMBER_COUNTRY_V2, MEMBER_REGION_V2, MEMBER_COUNTY, SERVING_LOCATION, PLACEMENT_NAME, IMPRESSION_DEVICE_TYPE, EVENT_STAGE, CARD_INDEX, CONVERSATION_NODE, CONVERSATION_NODE_OPTION_INDEX.
`endDate`	No	Inclusive end, YYYY-MM-DD. Defaults to today.
`metrics`	No	Metric keys from linkedin://metrics. Defaults to spend, impressions, clicks and the ratios.
`sortField`	No	Native field used to order the returned rows.
`sortOrder`	No	Ascending or descending native result ordering.
`startDate`	Yes	Inclusive start, YYYY-MM-DD.
`adAccountId`	Yes	Selected LinkedIn advertising account, numeric ID. It must be listed in LINKEDIN_ADS_ACCOUNT_IDS.
`campaignIds`	No	Restrict reporting to these campaign IDs or URNs in the selected account.
`creativeIds`	No	Restrict reporting to these owned creative IDs.
`campaignType`	No	Native campaign format filter.
`timeGranularity`	No	Defaults to ALL, one row for the whole range.
`campaignGroupIds`	No	Restrict reporting to these owned campaign-group IDs.

Output Schema

Name	Required	Description	Default
`result`	Yes	Original tool result: parsed JSON when the text is JSON, otherwise the text. Provider fields depend on the selected query.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Oct 23, 2026

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/non-destructive, so the description is free to add the non-obvious behavior it does add: ratios like CTR, CPC and CPM are not returned by the API and are computed by this tool. That is genuinely useful and not derivable from annotations or schema. It still omits row limits, pagination and any cost/latency characteristics of an openWorld report call.

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 the core action before the caveat about computed ratios. Every sentence carries information, though 'any granularity, and up to 20 fields' is loose phrasing that adds little precision.

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 12 parameters, 4 enums, full schema descriptions, a complete annotation set and an output schema, the remaining burden on the description is small and mostly met: purpose, pivot model and the computed-ratio behavior are covered. The main gap is sibling disambiguation, which matters given how many report-oriented tools share this namespace.

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 coverage is 100% and every parameter carries its own description, so the schema already does the heavy lifting and a 3 is the baseline. The description adds only marginal semantic value — that ratios can appear in the metric set because they are computed, and that fields include dateRange/pivotValues — and its 'up to 20 fields' claim sits awkwardly against the schema's maxItems 40.

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 (run a LinkedIn Ads report) and pins the scope with 'grouped by one pivot'. It implicitly contrasts itself with multi-pivot/report siblings ('This is the analytics finder: one pivot'), but never names linkedin_run_statistics_report or linkedin_get_demographics, so the agent still has to guess which analytics sibling to pick.

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 implied rather than stated: 'one pivot, any granularity' hints at the single-pivot case, but there is no explicit when-to-use or when-not-to-use rule, and no alternative is named despite several overlapping siblings. Nothing tells the agent whether to reach for this or linkedin_run_statistics_report first.

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

Deploy Server