ChatGPT Plugin

Admiral

Check your Google & Meta ads

Brand: Unknown

Category: Pending
Primary Subcategory: Pending

Integration details

Description

Admiral is software for the people who run Google and Meta ads. Connect it and ask about the ad account you chose, in plain language: what the campaigns cost, which keywords are wasting money, which search terms brought nothing, and how the week is trending. It can also put a suggestion into Admiral's approval queue (pause a keyword, add a negative, stop an ad), where you decide on each one. It cannot change anything in Google or Meta by itself, it cannot move a budget, and it cannot spend money. A person approves every change in Admiral. You choose the single ad account the connection may read when you authorize it, and you can disconnect it at any time under Settings.

Integration type: Plugin
Verification status: Not applicable
Platform: ChatGPT
Category: Pending
Primary Subcategory: Pending
Secondary Subcategories: None listed
Brand: Unknown
Access: Account required
First tracked: 2026-10-29
Tool count: 13
Market: US

Agent DiscoverabilityChatGPT Plugin Discovery Score

ChatGPT organic discovery is live

Your score is coming

ChatGPT now suggests Plugins on its own when they match a user's request.Your Plugin Discovery Score measures how often yours appears, and it will show here as soon as it’s ready.

ChatGPT recommends Airtable when a user asks it to update a CRM. — ChatGPT surfaces Airtable because it matches the user's request.

Primary Subcategory

Competitive lineup

No Primary Subcategory assigned yetOnce Admiral has a Primary Subcategory, the Plugins and Connectors it competes with will appear here with their scores.

Tools

13 tools agents can invoke

Account totals on two labelled bases: `window` (last 30 calendar days) and `lifetime` (provider all-time, includes deleted campaigns). `run_token` is used by Admiral's own agent runs; a personal connection is already scoped to one account.
get_account_overview
Per-asset (headline/description) impressions and clicks, with the ad group and campaign each asset belongs to. `label` is Google's own rating and is null where Google gives none: it stopped rating Search, Display and Performance Max assets. `run_token` is used by Admiral's own agent runs; a personal connection is already scoped to one account.
get_assets
Every ad by its first headline, with the ad group and campaign it belongs to. `run_token` is used by Admiral's own agent runs; a personal connection is already scoped to one account.
get_ads
Open alerts from the diagnostics engine. `run_token` is used by Admiral's own agent runs; a personal connection is already scoped to one account.
get_alerts
Campaign health scores. `run_token` is used by Admiral's own agent runs; a personal connection is already scoped to one account.
get_health
Campaigns with status, daily budget, and a `window` object holding what each one actually spent over the last 30 days with its clicks and conversions. `daily_budget` is the daily ceiling; `window.spend` is the money spent, which is the campaign's cost. Every amount is in the account's own `currency`, which each row carries; a null `currency` means the currency is unknown. `run_token` is used by Admiral's own agent runs; a personal connection is already scoped to one account.
get_campaigns
Close an open proposal that is no longer true (the ad was re-enabled, the term stopped costing money, the bid was fixed), identified by its `dedup_key`, with a one-sentence `reason`. `run_token` is used by Admiral's own agent runs; a personal connection is already scoped to one account.
resolve_proposal
Daily spend, clicks and conversions for the account, newest first, for up to 90 days. `run_token` is used by Admiral's own agent runs; a personal connection is already scoped to one account.
get_daily_history
File one proposal in the account's approval queue, where a person approves or rejects it; nothing changes in the ad account until then. `action`, when present, is {type, params} with `type` one of add_negative_keywords, set_keyword_status, set_campaign_status, pause_ad_by_resource or create_rsa. `run_token` is used by Admiral's own agent runs; a personal connection is already scoped to one account.
file_proposal
Keywords with QS, bids and metrics (top 100 by cost). `run_token` is used by Admiral's own agent runs; a personal connection is already scoped to one account.
get_keywords
Proposals waiting in the account's approval queue, each with its `dedup_key`. A proposal filed with a `dedup_key` that is already open is not added again. `run_token` is used by Admiral's own agent runs; a personal connection is already scoped to one account.
get_open_proposals
Costly search terms with zero conversions. `cost` is in the account's own `currency`, which each row carries; a null `currency` means the currency is unknown. `run_token` is used by Admiral's own agent runs; a personal connection is already scoped to one account.
get_search_terms
Metric trends vs 7-day averages. `run_token` is used by Admiral's own agent runs; a personal connection is already scoped to one account.
get_trends

FAQs

Admiral ChatGPT Plugin FAQ

How the directory, categories and Discoverability Score work.

Read the methodology

How do I improve Admiral's ChatGPT Plugin discoverability?

The levers are the listing surface agents actually read: names, descriptions, keywords, tool metadata, and registry health. Which lever matters depends on where discovery breaks, which is what continuous measurement shows.

Where is this profile measured?

This profile uses the geography attached to the latest public registry snapshot: US. Locale tags are intentionally omitted.