Skip to main content
Glama
hashcott

Meta Ads MCP Server

by hashcott

Get Meta Ad Insights

meta_ads_get_ad_insights
Read-onlyIdempotent

Retrieve performance metrics like impressions, clicks, conversions for a specified Meta ad. Supports custom date ranges and breakdowns by age, gender, and platform.

Instructions

Retrieve detailed performance insights for a specific Meta ad.

Fetches performance metrics for an individual ad, such as impressions, clicks, conversions, video views, etc.

Args:

  • ad_id (string): Ad ID, e.g., '6123456789012'

  • fields (string[]): Metrics to retrieve. Common: ad_name, adset_name, campaign_name, impressions, clicks, spend, ctr, cpc, cpm, reach, frequency, actions, conversions, cost_per_action_type, inline_link_clicks, video_p25_watched_actions

  • date_preset (string): Relative time range preset (default: last_30d)

  • time_range (object): Custom range {'since':'YYYY-MM-DD','until':'YYYY-MM-DD'}

  • level (string): Aggregation level, should be 'ad' (default: ad)

  • breakdowns (string[]): Segment by: age, gender, country, publisher_platform, impression_device, platform_position, device_platform, etc.

  • See full parameter list in inputSchema

Returns: Object with:

  • data (array): List of insight records with requested metrics

  • paging (object): Pagination cursors. Use meta_ads_fetch_pagination_url with paging.next to get more results

Pagination note: When response contains paging.next, use meta_ads_fetch_pagination_url to retrieve additional pages automatically.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
fieldsNoMetrics and dimensions to retrieve. Common examples: impressions, reach, clicks, spend, ctr, cpc, cpm, cpp, frequency, actions, conversions, cost_per_action_type, date_start, date_stop
date_presetNoPredefined relative time range. Options: today, yesterday, this_month, last_month, this_quarter, maximum, last_3d, last_7d, last_14d, last_28d, last_30d, last_90d, last_week_mon_sun, last_week_sun_sat, last_quarter, last_year, this_week_mon_today, this_week_sun_today, this_year. Default: last_30d. Ignored if time_range, time_ranges, since, or until is providedlast_30d
time_rangeNoSpecific time range {'since':'YYYY-MM-DD','until':'YYYY-MM-DD'}. Overrides date_preset
time_rangesNoArray of time range objects for period comparison. Overrides time_range and date_preset
time_incrementNoTime breakdown granularity: integer 1-90 (days per point), 'monthly', or 'all_days' (single summary). Default: all_daysall_days
levelNoLevel of aggregation: account, campaign, adset, or ad
action_attribution_windowsNoAttribution windows for actions. Examples: 1d_view, 7d_view, 28d_view, 1d_click, 7d_click, 28d_click, dda, default
action_breakdownsNoSegments the actions results. Examples: action_device, action_type, conversion_destination, action_destination. Default: [action_type]
action_report_timeNoWhen actions are counted: impression (time of ad impression), conversion (time of conversion), mixed. Default: mixed
breakdownsNoSegment results by dimensions. Examples: age, gender, country, region, dma, impression_device, publisher_platform, platform_position, device_platform
default_summaryNoIf true, include an additional summary row in the response. Default: false
use_account_attribution_settingNoIf true, use the attribution settings defined at the ad account level. Default: false
use_unified_attribution_settingNoIf true, use unified attribution settings defined at the ad set level. Recommended for consistency with Ads Manager. Default: true
filteringNoList of filter objects. Each has 'field', 'operator', and 'value'. Example: [{field: 'spend', operator: 'GREATER_THAN', value: 50}]
sortNoSort field and direction. Format: {field}_ascending or {field}_descending. Example: impressions_descending
sinceNoStart timestamp for time-based pagination (Unix or strtotime). Only used when time_range and time_ranges are not set
untilNoEnd timestamp for time-based pagination (Unix or strtotime). Only used when time_range and time_ranges are not set
localeNoLocale for text responses (e.g., en_US). Controls language and formatting
limitNoMaximum number of results to return per page (1-100, default: 25)
afterNoCursor for the next page of results, from response.paging.cursors.after
beforeNoCursor for the previous page of results, from response.paging.cursors.before
offsetNoAlternative pagination: number of results to skip
ad_idYesAd ID, e.g., '6123456789012'
Behavior4/5

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

Annotations already indicate read-only and idempotent. The description adds pagination details, return structure, and how to request fields. No contradictions. It provides significant behavioral context beyond annotations.

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

Conciseness5/5

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

Description is well-organized with clear sections (purpose, args, returns, pagination note). Each sentence is informative and necessary. No fluff, achieves conciseness without sacrificing completeness.

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

Completeness5/5

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

For a complex tool with 23 parameters, the description covers key aspects: how to use date presets vs custom range, pagination, and return format. It references a sibling tool for pagination. No output schema, but description compensates adequately.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. Description adds value by listing common fields, breakdowns, and examples (e.g., 'comma-separated list e.g. impressions, clicks'). Clearly explains key parameters like date_preset and time_range.

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

Purpose5/5

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

The description clearly states it retrieves performance insights for a specific Meta ad. It distinguishes from sibling tools that operate at different levels (e.g., adaccount, adset) by specifying 'ad' level and naming the tool accordingly.

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?

The description provides clear context: it fetches metrics for an individual ad and mentions pagination using a sibling tool. It defaults to last_30d and 'ad' level, indicating typical use. Lacks explicit when-not-to-use, but sufficient guidance.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/hashcott/meta-ads-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server