Meta Ads MCP Server
Integrates with Facebook Pages and the Facebook Ads API to manage pages, ad campaigns, ad sets, ads, and more through the same Meta Graph API.
Provides tools to manage Meta advertising accounts, campaigns, ad sets, ads, creatives, media, insights, targeting catalog, budget schedules, and activity logs via the Meta Graph API v22.0.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Meta Ads MCP Server show me my campaign insights for last month"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Meta Ads MCP Server
Disclaimer: This is an unofficial third-party tool and is not associated with, endorsed by, or affiliated with Meta in any way. This project is maintained independently and uses Meta's public APIs in accordance with their Terms of Service. Meta, Facebook, Instagram, and other Meta brand names are trademarks of their respective owners.
Table of Contents
Related MCP server: ArmaVita Meta Ads MCP
Features
Category | What it does |
Accounts | List ad accounts, get account details |
Campaigns | Get / list / create / update / pause / resume / delete |
Ad Sets | Get / list / batch-fetch / create / update / pause / resume / delete |
Ads | Get / list / create / update / pause / resume / delete |
Creatives | Get / list, create + update, compute image crops |
Media | List ad images, upload images, lookup by hash, get ad previews and videos |
Insights | Performance analytics at account, campaign, ad set, and ad level |
Targeting | Search interests / behaviors / demographics / geo, audience size estimation |
Pages | List Facebook Pages reachable from the token, search by name |
Budget Schedules | Schedule temporary budget bumps over a time window |
Activities | Change history log for ad accounts and ad sets |
Pagination | Utility tool to fetch subsequent pages of results |
All mutation tools (create / update / delete / pause / resume / upload / budget schedule) are off by default and only register when you opt in — see Enabling Write Tools.
Requirements
Node.js >= 18
A Meta User Access Token with the right permissions for what you plan to do — see below.
Installation
# From npm
npx meta-ads-mcp-server --access-token YOUR_META_ACCESS_TOKEN
# From source
git clone https://github.com/hashcott/meta-ads-mcp.git
cd meta-ads-mcp
npm install
npm run build
node dist/index.js --access-token YOUR_META_ACCESS_TOKENObtaining a Meta Access Token
This server uses the Meta Marketing API. You need an access token attached to a Meta App that has the right permissions.
Quick option — Graph API Explorer (read-only experiments)
Open the Graph API Explorer.
Pick your Meta App from the top-right dropdown (create one at developers.facebook.com/apps if you don't have any — choose type "Business").
Click Generate Access Token, then under Permissions add at minimum:
ads_read— for all the read tools.ads_management— required for any write tool (create / update / delete / pause / resume / upload / budget schedule).business_management— recommended if you operate via Business Manager.pages_show_list,pages_read_engagement— required for the Pages tools.
Copy the generated token. This is a short-lived token (~1 hour) — fine for testing.
Production option — long-lived User token
Short-lived tokens from the Explorer expire in about an hour. Exchange yours for a 60-day token:
curl -G "https://graph.facebook.com/v22.0/oauth/access_token" \
--data-urlencode "grant_type=fb_exchange_token" \
--data-urlencode "client_id=YOUR_APP_ID" \
--data-urlencode "client_secret=YOUR_APP_SECRET" \
--data-urlencode "fb_exchange_token=YOUR_SHORT_LIVED_TOKEN"Response contains "access_token": "..." — that token is valid for ~60 days. Refresh it the same way before it expires, or build a full OAuth flow if you need permanent access.
Production option — System User token (recommended for servers)
For unattended production use (no expiry), generate a System User token in Business Manager:
Go to Business Manager → Business Settings → Users → System Users.
Create a system user (or use an existing one), assign the relevant ad account, and grant
ads_read/ads_management.Click Generate New Token → pick your Meta App → select the same permissions → Never for expiration.
System User tokens don't expire and are ideal for backend deployments.
Verifying your token
curl "https://graph.facebook.com/v22.0/me?access_token=YOUR_TOKEN"Should return your user/system-user object. If it returns an error, double-check the permissions and that the token isn't expired.
Authentication
Pass your Meta access token using either method:
CLI argument (recommended for Cursor / Claude Desktop):
node dist/index.js --access-token YOUR_META_ACCESS_TOKENEnvironment variable:
export META_ADS_ACCESS_TOKEN=YOUR_META_ACCESS_TOKEN
node dist/index.jsThe token is held only in memory of the running process — it is never written to disk by this server.
Enabling Write Tools
By default the server registers only the 35 read tools — create / update / delete / pause / resume / upload / budget-schedule tools are not exposed. This is intentional: a mistakenly-issued meta_ads_delete_campaign can permanently remove campaigns and their ads.
To opt in, set:
META_ADS_ENABLE_WRITE_TOOLS=trueAccepted truthy values: true, 1, yes, on (case-insensitive). Anything else (or unset) keeps writes off.
When enabled, the server logs a one-line warning to stderr at startup:
[meta-ads-mcp] WARNING: META_ADS_ENABLE_WRITE_TOOLS is on — create/update/delete/pause/resume tools are EXPOSED. These can permanently delete campaigns/ad sets/ads or change live delivery.Your access token also needs the ads_management permission for the writes to succeed.
Example Cursor / Claude Desktop configuration with writes enabled:
{
"mcpServers": {
"meta-ads": {
"command": "npx",
"args": ["-y", "meta-ads-mcp-server"],
"env": {
"META_ADS_ACCESS_TOKEN": "YOUR_META_ACCESS_TOKEN",
"META_ADS_ENABLE_WRITE_TOOLS": "true"
}
}
}
}Transport Modes
Mode | Use case | How to enable |
| Cursor, Claude Desktop, local tools | No configuration needed |
| Claude.ai remote connectors, multi-client setups | Set |
Cursor / Claude Desktop Setup
Add one of the following to your MCP client configuration file:
Via npx (recommended — no local install required):
{
"mcpServers": {
"meta-ads": {
"command": "npx",
"args": ["-y", "meta-ads-mcp-server", "--access-token", "YOUR_META_ACCESS_TOKEN"]
}
}
}Via local build:
{
"mcpServers": {
"meta-ads": {
"command": "node",
"args": ["/path/to/meta-ads-mcp/dist/index.js", "--access-token", "YOUR_META_ACCESS_TOKEN"]
}
}
}Via environment variable (and opt-in writes):
{
"mcpServers": {
"meta-ads": {
"command": "npx",
"args": ["-y", "meta-ads-mcp-server"],
"env": {
"META_ADS_ACCESS_TOKEN": "YOUR_META_ACCESS_TOKEN",
"META_ADS_ENABLE_WRITE_TOOLS": "true"
}
}
}
}Remote HTTP Server
Run as a persistent HTTP server for use with Claude.ai custom connectors or any remote MCP client.
# Start on default port 3000
TRANSPORT=http META_ADS_ACCESS_TOKEN=YOUR_TOKEN node dist/index.js
# Start on a custom port, writes enabled
TRANSPORT=http \
META_ADS_ACCESS_TOKEN=YOUR_TOKEN \
META_ADS_ENABLE_WRITE_TOOLS=true \
PORT=8080 \
node dist/index.jsEndpoints:
POST /mcp— MCP protocol endpointGET /health— Health check ({"status":"ok"})
Adding to Claude.ai
Go to Settings → Connectors → Add custom connector
Enter your server URL:
https://your-domain.com/mcpClick Add
Local testing with ngrok
# Terminal 1 — start the server
TRANSPORT=http META_ADS_ACCESS_TOKEN=YOUR_TOKEN PORT=8080 node dist/index.js
# Terminal 2 — expose publicly
ngrok http 8080Use the generated HTTPS URL (e.g. https://xxxx.ngrok-free.app/mcp) as your connector URL.
Deploying to cloud platforms
Set the following environment variables on your hosting provider (Railway, Render, Fly.io, etc.):
Variable | Value |
|
|
| Your Meta access token |
|
|
| Assigned automatically by the platform |
Available Tools
Legend: 🔍 read • ✏️ write (gated by META_ADS_ENABLE_WRITE_TOOLS) • 🛠️ pure utility (no API call).
Accounts
Tool | Type | Description |
| 🔍 | List all ad accounts accessible with your token |
| 🔍 | Get detailed information for a specific ad account |
Campaigns
Tool | Type | Description |
| 🔍 | Fetch a specific campaign by its ID |
| 🔍 | List campaigns within an ad account, with filters and pagination |
| ✏️ | Create a new ODAX campaign (CBO or ABO) |
| ✏️ | Update name/status/budget/bid; supports CBO → ABO migration via |
| ✏️ | Permanently delete a campaign and its ad sets/ads |
| ✏️ | Convenience: set status to |
| ✏️ | Convenience: set status to |
meta_ads_create_campaign inputs:
act_id(string) — Ad account ID, formatact_XXXXXXXXX.name(string) — Campaign name.objective(enum) — ODAX outcome-based objective:OUTCOME_AWARENESS,OUTCOME_TRAFFIC,OUTCOME_ENGAGEMENT,OUTCOME_LEADS,OUTCOME_SALES,OUTCOME_APP_PROMOTION.Legacy objectives (
BRAND_AWARENESS,LINK_CLICKS,CONVERSIONS,APP_INSTALLS, …) are not accepted by Meta v22+ and will return HTTP 400.
status(defaultPAUSED),special_ad_categories(default[])daily_budget/lifetime_budget(cents) — omit both whenuse_adset_level_budgets=true.bid_strategy—LOWEST_COST_WITHOUT_CAP(default),LOWEST_COST_WITH_BID_CAP,COST_CAP,LOWEST_COST_WITH_MIN_ROAS. Bid-cap strategies requirebid_amounton every child ad set.bid_cap,spend_cap,campaign_budget_optimization,use_adset_level_budgets,ab_test_control_setups,buying_type.
{
"act_id": "act_123456789012345",
"name": "2026 - Spring Sale - Awareness",
"objective": "OUTCOME_AWARENESS",
"special_ad_categories": [],
"status": "PAUSED",
"bid_strategy": "LOWEST_COST_WITHOUT_CAP",
"daily_budget": 10000
}Ad Sets
Tool | Type | Description |
| 🔍 | Fetch a single ad set by its ID |
| 🔍 | Batch fetch multiple ad sets |
| 🔍 | List ad sets in an ad account |
| 🔍 | List ad sets within a campaign |
| ✏️ | Create a new ad set under a campaign |
| ✏️ | Update an ad set's fields (note: |
| ✏️ | Permanently delete an ad set |
| ✏️ | Set status to |
| ✏️ | Set status to |
meta_ads_create_adset highlights:
Required:
act_id,campaign_id,name,optimization_goal,billing_event.targeting(object) — full targeting spec; remembertargeting_automation.advantage_audiencedefaults to0on Meta v24+ — set it explicitly if you want Advantage+ Audience.bid_amount— required forLOWEST_COST_WITH_BID_CAP/COST_CAP.bid_constraints— required forLOWEST_COST_WITH_MIN_ROAS, e.g.,{"roas_average_floor": 20000}for a 2.0× ROAS floor.dsa_beneficiary/dsa_payor— required for EU-targeted ad sets.promoted_object— required forAPP_INSTALLS.frequency_control_specs— MUST be set at creation; Meta makes it immutable afterward.regional_regulated_categories/regional_regulation_identities— Taiwan / Australia / Singapore / India regulated verticals.
Ads
Tool | Type | Description |
| 🔍 | Fetch a single ad by ID |
| 🔍 | List ads in an ad account |
| 🔍 | List ads within a campaign |
| 🔍 | List ads within an ad set |
| ✏️ | Create a new ad referencing an existing creative |
| ✏️ | Update name / status / bid / tracking specs / creative reference |
| ✏️ | Permanently delete an ad |
| ✏️ | Set status to |
| ✏️ | Set status to |
ℹ️ Swapping
creative_idon a FLEX ad can fail witherror_subcode 3858355if the new creative'sasset_feed_specimages don't match itsobject_story_spec. In that case, create a new ad with the new creative and pause the old one (you lose social proof but the ad runs).
Creatives
Tool | Type | Description |
| 🔍 | Fetch one creative |
| 🔍 | List creatives attached to an ad |
| 🔍 | List creatives in an ad account |
| 🛠️ | Compute centered crop boxes for the 6 Meta-accepted aspect ratios (no API call) |
| ✏️ | Create a creative — 3 simple modes plus full |
| ✏️ | Update |
meta_ads_create_ad_creative — three common modes:
Promote an existing post: pass only
object_story_idin the form{page_id}_{post_id}.Single-image link ad:
page_id+image_hash+link_url+message+ optionalheadline,description,call_to_action_type.Single-video ad:
page_id+video_id+link_url+message+ optionalheadline,call_to_action_type,thumbnail_url.
For advanced layouts (FLEX/DOF, Placement Asset Customization, Dynamic Creative, multi-headline, lead-gen forms, branded content, image crops), pass a fully composed object_story_spec and/or asset_feed_spec — those take precedence over the simple-mode auto-construction.
Media
Tool | Type | Description |
| 🔍 | List image assets in an ad account |
| 🔍 | Single-image lookup by hash (URL + dimensions) |
| 🔍 | Generate rendered previews of an ad across placements |
| 🔍 | Video details (source URL, thumbnails, length) by |
| ✏️ | Upload an image to an account's ad images library and get back its |
meta_ads_upload_ad_image accepts exactly one of:
file— a data URL (data:image/png;base64,iVBORw0KG...) or a raw base64 string.image_url— a public URL; the server downloads the bytes and uploads them.
Returns the image_hash you then pass to meta_ads_create_ad_creative.
Insights
Tool | Type | Description |
| 🔍 | Performance metrics at the account level |
| 🔍 | Performance metrics for a specific campaign |
| 🔍 | Performance metrics for a specific ad set |
| 🔍 | Performance metrics for a specific ad |
All four accept the same option surface: fields, date_preset, time_range, time_ranges, time_increment, level, action_attribution_windows, action_breakdowns, breakdowns, filtering, sort, pagination, and locale.
Time-range precedence: time_ranges > time_range > since/until > date_preset.
Targeting Catalog
Tool | Type | Description |
| 🔍 | Search Meta's interest catalog by keyword |
| 🔍 | Get related interests from a seed list |
| 🔍 | List available behavior targeting options |
| 🔍 | List demographic options (demographics / life_events / industries / income / family_statuses / user_device / user_os) |
| 🔍 | Search countries / regions / cities / zips / geo_markets / electoral_districts |
| 🔍 | Estimate reach for a targeting spec via |
Pages
Tool | Type | Description |
| 🔍 | List Facebook Pages reachable from the access token ( |
| 🔍 | Substring filter over the token's pages (client-side — Meta does not expose a server-side name filter) |
The returned page_id values are the ones you pass to meta_ads_create_ad_creative.
Budget Schedules
Tool | Type | Description |
| ✏️ | Schedule a temporary budget bump for a campaign over a Unix-timestamp window |
Inputs:
campaign_id(string)budget_value(int, positive)budget_value_type—ABSOLUTE(cents in account currency) orMULTIPLIER(e.g.,2doubles the budget)time_start,time_end(Unix timestamps in seconds) —time_end > time_start
Activities
Tool | Type | Description |
| 🔍 | Retrieve the change history log for an ad account |
| 🔍 | Retrieve the change history log for an ad set |
Pagination tool
Tool | Type | Description |
| 🛠️ | Follow |
End-to-End: Create an Ad from Scratch
A typical "build a new ad" workflow uses tools across several categories. With META_ADS_ENABLE_WRITE_TOOLS=true:
1. meta_ads_list_ad_accounts → pick an act_id
2. meta_ads_get_account_pages → pick a page_id
3. meta_ads_search_geo_locations(q="Vietnam") → grab the country/region keys
4. meta_ads_search_interests(q="cooking") → grab interest IDs
5. meta_ads_estimate_audience_size(act_id, targeting) → sanity-check reach
6. meta_ads_upload_ad_image(act_id, image_url) → returns image_hash
7. meta_ads_create_campaign(act_id, ...) → returns campaign_id
8. meta_ads_create_adset(act_id, campaign_id, targeting, ...) → returns adset_id
9. meta_ads_create_ad_creative(act_id, page_id, image_hash, link_url, message, ...) → returns creative_id
10. meta_ads_create_ad(act_id, name, adset_id, creative_id, status="PAUSED") → returns ad_id
11. (Optional) meta_ads_get_ad_previews(ad_id, ...) → render placements before going live
12. meta_ads_resume_ad(ad_id) → flip to ACTIVE when readyAll steps that mutate state default to status: "PAUSED" so nothing goes live until you explicitly call a resume tool.
Pagination
Many list tools return paginated results. When a response contains a paging.next URL, use meta_ads_fetch_pagination_url to retrieve subsequent pages:
1. Call meta_ads_get_campaigns_by_adaccount → receive first page
2. Check if response.paging.next exists
3. Call meta_ads_fetch_pagination_url(url=response.paging.next) → receive next page
4. Repeat until paging.next is absentDevelopment
npm run dev # Watch mode — auto-recompile on change
npm run build # Compile TypeScript to dist/
npm run clean # Remove dist/
npm run clean && npm run build # Full rebuild from scratchQuick smoke test:
# Default (read-only)
META_ADS_ACCESS_TOKEN=dummy node dist/index.js
# → "Meta Ads MCP server running via stdio"
# With writes enabled
META_ADS_ACCESS_TOKEN=dummy META_ADS_ENABLE_WRITE_TOOLS=true node dist/index.js
# → WARNING line + "Meta Ads MCP server running via stdio"Project Structure
meta-ads-mcp/
├── src/
│ ├── index.ts # Entry point, server setup, transport selection, write-tools warning
│ ├── constants.ts # API version, base URLs, isWriteToolsEnabled() flag
│ ├── types.ts # Shared TypeScript interfaces
│ ├── services/
│ │ └── graph-api.ts # HTTP client (GET/POST/DELETE), auth, error handling, param builders
│ ├── schemas/
│ │ ├── common.ts # Shared Zod schemas (pagination, date ranges, filters)
│ │ └── insights.ts # Insights-specific Zod schemas
│ └── tools/
│ ├── accounts.ts # Account tools
│ ├── insights.ts # Insights tools (account/campaign/adset/ad level)
│ ├── campaigns.ts # Campaign read + write/lifecycle tools
│ ├── adsets.ts # Ad set read + write/lifecycle tools
│ ├── ads.ts # Ad read + write/lifecycle tools
│ ├── creatives.ts # Creative read tools, image crops utility, create/update creative
│ ├── media.ts # Image list / upload / hash lookup / video / preview
│ ├── activities.ts # Activity log tools
│ ├── pagination.ts # Pagination utility tool
│ ├── targeting.ts # Interest/behavior/demographic/geo search + audience-size estimate
│ ├── pages.ts # Facebook Pages list and name search
│ └── budget-schedules.ts # Campaign budget schedule create
├── dist/ # Compiled JavaScript output (generated)
├── package.json
└── tsconfig.jsonLicense
Available Tools
35 toolsmeta_ads_compute_image_cropsCompute Meta Ad Image CropsARead-onlyIdempotent
Compute image_crops coordinates for a source image. For each requested key, returns the largest centered region that fits the source while matching that key's aspect ratio (equivalent to Meta's "Original" crop — no content cut beyond the ratio).
Valid keys (Meta accepts only these 6): 100x100 — 1:1 square (Feed, Marketplace) 100x72 — ~1.39:1 horizontal (Marketplace) 400x500 — 4:5 portrait (Feed mobile, Stories fallback) 400x150 — ~2.67:1 banner (Audience Network) 600x360 — ~1.67:1 horizontal (Right column) 90x160 — 9:16 portrait (Stories)
Pass the returned image_crops dict to meta_ads_create_ad_creative.
Inputs: image_width (required), image_height (required), crop_keys.
meta_ads_estimate_audience_sizeEstimate Meta Ad Audience SizeARead-onlyIdempotent
Estimate audience size for a targeting spec using Meta's delivery_estimate / reachestimate endpoints.
Args:
act_id (string): Ad account ID prefixed with 'act_'.
targeting (object): Full targeting spec (geo_locations, age_min, age_max, interests, flexible_spec, etc.).
optimization_goal (string, optional): Default 'REACH'. Other common values: LINK_CLICKS, LANDING_PAGE_VIEWS, OFFSITE_CONVERSIONS, IMPRESSIONS.
Returns: Estimated audience size bounds plus the raw API response.
Inputs: act_id (required), targeting (required), optimization_goal.
meta_ads_fetch_pagination_urlFetch Meta Ads Pagination URLARead-onlyIdempotent
Fetch the next or previous page of results from a Meta Graph API pagination URL.
Use this tool whenever a Meta Ads tool response contains a paging.next or paging.previous URL. The pagination URL already includes the access token and all necessary parameters.
Args:
url (string): The complete pagination URL from response.paging.next or response.paging.previous
Returns: The next/previous page of results in the same format as the original response.
Examples:
Use when: response.paging.next exists after calling meta_ads_get_adaccount_insights
Use when: response.paging.next exists after calling meta_ads_get_campaigns_by_adaccount
Use when: "Get all pages of results automatically"
Note: The pagination URL already contains the access token — do NOT add or modify it.
Inputs: url (required).
meta_ads_get_account_pagesGet Meta Account PagesARead-onlyIdempotent
List Facebook Pages reachable from the access token's user. These are the candidate page_id values for create_ad_creative.
Args:
act_id (string, optional): Reserved for parity with the Python reference; Meta returns pages bound to the user/token, not the ad account, so this is currently unused.
Returns: { data: [{ id, name, username, category, fan_count, link, verification_status, picture }] }
Inputs: act_id.
meta_ads_get_activities_by_adaccountGet Meta Ad Account Activity LogARead-onlyIdempotent
Retrieve the change history (activity log) for a Meta ad account.
Returns key updates to the account and associated ad objects, including status changes, budget updates, targeting changes, and more. By default returns one week of data.
Args:
act_id (string): Ad account ID prefixed with 'act_', e.g., 'act_1234567890'
fields (string[]): Fields to retrieve. Available: actor_id, actor_name, application_id, application_name, changed_data, date_time_in_timezone, event_time, event_type, extra_data, object_id, object_name, object_type, translated_event_type
limit (number): Maximum activities per page
after / before (string): Pagination cursors
time_range (object): Custom range {'since':'YYYY-MM-DD','until':'YYYY-MM-DD'}. Overrides since/until
since (string): Start date in YYYY-MM-DD format (ignored if time_range is set)
until (string): End date in YYYY-MM-DD format (ignored if time_range is set)
Returns: Object with data (activity array) and paging. Each activity record contains who made the change, what was changed, when, and the specific details.
actor_name (string): Name of the user who made the change
object_type (string): Type of object: AD, ADSET, CAMPAIGN, ACCOUNT, IMAGE, REPORT, etc.
translated_event_type (string): Human-readable description, e.g., 'ad created', 'campaign budget updated'
event_time (string): Timestamp of the event
changed_data (string): JSON detailing what changed
Use meta_ads_fetch_pagination_url with paging.next to retrieve additional pages.
Examples:
Use when: "Show me all changes made to my ad account in the last week"
Use when: "Who changed the budget on this account in January 2024?"
Inputs: act_id (required), fields, time_range, since, +5 more.
meta_ads_get_activities_by_adsetGet Meta Ad Set Activity LogARead-onlyIdempotent
Retrieve the change history (activity log) for a specific Meta ad set.
Returns updates to the ad set including status changes, budget updates, targeting changes, and more. By default returns one week of data.
Args:
adset_id (string): Ad set ID, e.g., '23843211234567'
fields (string[]): Fields to retrieve. Available: actor_id, actor_name, application_id, application_name, changed_data, date_time_in_timezone, event_time, event_type, extra_data, object_id, object_name, object_type, translated_event_type
limit (number): Maximum activities per page
after / before (string): Pagination cursors
time_range (object): Custom range {'since':'YYYY-MM-DD','until':'YYYY-MM-DD'}. Overrides since/until
since (string): Start date in YYYY-MM-DD format (ignored if time_range is set)
until (string): End date in YYYY-MM-DD format (ignored if time_range is set)
Returns: Object with data (activity array) and paging. Each activity record contains who made the change, what was changed, when, and the specific details.
actor_name (string): Name of the user who made the change
object_type (string): Type of object: AD, ADSET, CAMPAIGN, ACCOUNT, IMAGE, REPORT, etc.
translated_event_type (string): Human-readable description, e.g., 'ad created', 'campaign budget updated'
event_time (string): Timestamp of the event
changed_data (string): JSON detailing what changed
Use meta_ads_fetch_pagination_url with paging.next to retrieve additional pages.
Examples:
Use when: "What changes were made to ad set 23843211234567 this month?"
Use when: "Show me the targeting change history for this ad set"
Inputs: adset_id (required), fields, time_range, since, +5 more.
meta_ads_get_ad_account_detailsGet Meta Ad Account DetailsARead-onlyIdempotent
Get detailed information about a specific Meta ad account.
Args:
act_id (string): The ad account ID prefixed with 'act_', e.g., 'act_1234567890'
fields (string[]): Optional. Fields to retrieve. If omitted, defaults to: name, business_name, age, account_status, balance, amount_spent, attribution_spec, account_id, business, business_city, brand_safety_content_filter_levels, currency, created_time, id.
Returns: Object with the requested ad account fields. Key fields:
id (string): Ad account ID
name (string): Account display name
account_status (number): Status code (1=ACTIVE, 2=DISABLED, 3=UNSETTLED, etc.)
currency (string): Account currency code (e.g., 'USD')
balance (string): Current account balance
amount_spent (string): Total lifetime spend
Examples:
Use when: "Get details for ad account act_123456"
Use when: "What is the currency and balance of my ad account?"
Inputs: act_id (required), fields.
meta_ads_get_adaccount_insightsGet Meta Ad Account InsightsBRead-onlyIdempotent
Retrieve performance insights for a Meta ad account.
Fetches metrics like impressions, reach, clicks, spend, conversions, and more for an entire ad account. Supports time range definitions, demographic breakdowns, and attribution settings.
Args:
act_id (string): Ad account ID prefixed with 'act_', e.g., 'act_1234567890'
fields (string[]): Metrics to retrieve. Common: impressions, reach, clicks, spend, ctr, cpc, cpm, cpp, frequency, actions, conversions, cost_per_action_type
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: account, campaign, adset, ad (default: account)
breakdowns (string[]): Segment by: age, gender, country, impression_device, publisher_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.
Inputs: act_id (required), fields, date_preset, time_range, +19 more.
meta_ads_get_ad_by_idGet Meta Ad by IDARead-onlyIdempotent
Retrieve detailed information about a specific Meta ad.
Args:
ad_id (string): Ad ID, e.g., '23843211234567'
fields (string[]): Fields per ad. Common: id, name, account_id, adset_id, campaign_id, status, effective_status, configured_status, creative, bid_amount, bid_type, created_time, updated_time, targeting, conversion_specs, recommendations, preview_shareable_link
Returns: Object with the requested ad fields.
Examples:
Use when: "Get details for ad 23843211234567"
Use when: "What creative and status does this ad have?"
Inputs: ad_id (required), fields.
meta_ads_get_ad_creative_by_idGet Meta Ad Creative by IDARead-onlyIdempotent
Retrieve detailed information about a specific Meta ad creative.
Args:
creative_id (string): Ad creative ID, e.g., '23842312323312'
fields (string[]): Fields to retrieve. Available: id, name, account_id, actor_id, adlabels, asset_feed_spec, authorization_category, body, call_to_action_type, effective_authorization_category, effective_instagram_media_id, effective_object_story_id, image_hash, image_url, instagram_permalink_url, instagram_story_id, instagram_user_id, link_url, object_id, object_story_id, object_story_spec, object_type, object_url, platform_customizations, product_set_id, status, template_url, thumbnail_url, title, url_tags, use_page_actor_override, video_id
thumbnail_width (number): Width of the thumbnail image in pixels (default: 64)
thumbnail_height (number): Height of the thumbnail image in pixels (default: 64)
Returns: Object with the requested creative fields.
Examples:
Use when: "Get the body text, title, and image URL for creative 23842312323312"
Use when: "What is the call-to-action type and status of this creative?"
Use when: "Get a larger thumbnail (300x200) for this creative"
Inputs: creative_id (required), fields, thumbnail_width, thumbnail_height.
meta_ads_get_adcreatives_by_adaccountGet Meta Ad Creatives by Ad AccountARead-onlyIdempotent
Retrieve all ad creatives belonging to a specific Meta ad account.
Useful for auditing all creative assets, finding creatives by status, or reviewing creative content across the account.
Args:
act_id (string): Ad account ID prefixed with 'act_', e.g., 'act_1234567890'
fields (string[]): Fields to retrieve. Available: id, name, account_id, actor_id, adlabels, asset_feed_spec, authorization_category, body, call_to_action_type, effective_authorization_category, effective_instagram_media_id, effective_object_story_id, image_hash, image_url, instagram_permalink_url, instagram_story_id, instagram_user_id, link_url, object_id, object_story_id, object_story_spec, object_type, object_url, platform_customizations, product_set_id, status, template_url, thumbnail_url, title, url_tags, use_page_actor_override, video_id
effective_status (string[]): Filter by status: ACTIVE, DELETED, IN_PROCESS, WITH_ISSUES
filtering (object[]): Additional filter objects with field, operator, value
limit (number): Results per page (1-100, default: 25)
after / before (string): Pagination cursors
Returns: Object with data (creative array) and paging. Use meta_ads_fetch_pagination_url with paging.next for more results.
Examples:
Use when: "List all active creatives in my ad account"
Use when: "Show all creatives with issues in act_123456"
Inputs: act_id (required), fields, effective_status, filtering, +4 more.
meta_ads_get_ad_creatives_by_ad_idGet Meta Ad Creatives by Ad IDARead-onlyIdempotent
Retrieve the ad creatives associated with a specific Meta ad.
Args:
ad_id (string): Ad ID to retrieve creatives for, e.g., '23843211234567'
fields (string[]): Fields to retrieve. Available: id, name, account_id, actor_id, adlabels, asset_feed_spec, authorization_category, body, call_to_action_type, effective_authorization_category, effective_instagram_media_id, effective_object_story_id, image_hash, image_url, instagram_permalink_url, instagram_story_id, instagram_user_id, link_url, object_id, object_story_id, object_story_spec, object_type, object_url, platform_customizations, product_set_id, status, template_url, thumbnail_url, title, url_tags, use_page_actor_override, video_id
limit (number): Maximum creatives per page (default: 25)
after / before (string): Pagination cursors from response.paging.cursors
date_format (string): Date format: 'U' for Unix timestamp, 'Y-m-d H:i:s' for MySQL datetime
Returns: Object with data (creative array) and paging. Use meta_ads_fetch_pagination_url with paging.next for more results.
Examples:
Use when: "What creatives are used by ad 23843211234567?"
Use when: "Get the image URLs and titles for all creatives on this ad"
Inputs: ad_id (required), fields, date_format, limit, +3 more.
meta_ads_get_ad_imagesGet Meta Ad ImagesARead-onlyIdempotent
Retrieve ad images belonging to a Meta ad account.
Useful for auditing image assets, finding images by hash or name, and checking image dimensions and status.
Args:
act_id (string): Ad account ID prefixed with 'act_', e.g., 'act_1234567890'
fields (string[]): Fields to retrieve. Available: id, account_id, created_time, creatives, hash, height, is_associated_creatives_in_adgroups, name, original_height, original_width, permalink_url, status, updated_time, url, url_128, width
hashes (string[]): Filter by specific image hashes
name (string): Filter images by name (partial match)
minwidth (number): Minimum image width in pixels
minheight (number): Minimum image height in pixels
limit (number): Results per page (1-100, default: 25)
after / before (string): Pagination cursors
Returns: Object with data (image array) and paging. Each image contains URL, dimensions, hash, and status. Use meta_ads_fetch_pagination_url with paging.next for more results.
Examples:
Use when: "List all images in my ad account"
Use when: "Find images with hashes abc123 and def456"
Use when: "Show images wider than 1000px"
Inputs: act_id (required), fields, hashes, name, +6 more.
meta_ads_get_ad_insightsGet Meta Ad InsightsARead-onlyIdempotent
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.
Inputs: ad_id (required), fields, date_preset, time_range, +19 more.
meta_ads_get_ad_previewsGet Meta Ad PreviewsARead-onlyIdempotent
Generate preview links or embed HTML for a Meta ad in various ad formats and placements.
Allows you to see how an ad looks across different placements (Facebook feed, Instagram, Stories, etc.) before or after publishing.
Args:
ad_id (string): Ad ID to preview, e.g., '23843211234567'
ad_format (string): Preview format. Options: DESKTOP_FEED_STANDARD, MOBILE_FEED_STANDARD, MOBILE_FEED_BASIC, MOBILE_INTERSTITIAL, MOBILE_BANNER, MOBILE_MEDIUM_RECTANGLE, MOBILE_FULLWIDTH, RIGHT_COLUMN_STANDARD, INSTAGRAM_STANDARD, INSTAGRAM_STORY, AUDIENCE_NETWORK_OUTSTREAM_VIDEO, AUDIENCE_NETWORK_INSTREAM_VIDEO, FACEBOOK_STORY_MOBILE, MESSENGER_MOBILE_INBOX_MEDIA, SUGGESTED_VIDEO_MOBILE, WATCH_FEED_MOBILE, FACEBOOK_REELS_MOBILE, INSTAGRAM_REELS
locale (string): Locale for the preview, e.g., 'en_US'
start_date (string): Preview start date for scheduled ads (UNIX timestamp)
end_date (string): Preview end date for scheduled ads (UNIX timestamp)
Returns: Object with data array. Each item contains:
body (string): HTML iframe embed code for the preview
encoded_creative_id (string): Encoded creative ID
Examples:
Use when: "Show me how ad 23843211234567 looks on Instagram"
Use when: "Preview this ad in desktop feed format"
Use when: "Generate previews for all placements of this ad"
Inputs: ad_id (required), ad_format, locale, start_date, +1 more.
meta_ads_get_ads_by_adaccountGet Meta Ads by Ad AccountARead-onlyIdempotent
Retrieve all ads from a specific Meta ad account with filtering and pagination.
Args:
act_id (string): Ad account ID prefixed with 'act_', e.g., 'act_1234567890'
fields (string[]): Fields per ad. Common: id, name, account_id, adset_id, campaign_id, status, effective_status, configured_status, creative, bid_amount, bid_type, created_time, updated_time, targeting, conversion_specs, recommendations, preview_shareable_link
effective_status (string[]): Filter by status: ACTIVE, PAUSED, DELETED, PENDING_REVIEW, DISAPPROVED, PREAPPROVED, PENDING_BILLING_INFO, CAMPAIGN_PAUSED, ARCHIVED, ADSET_PAUSED, IN_PROCESS, WITH_ISSUES
filtering (object[]): Additional filter objects with field, operator, value
limit (number): Results per page (1-100, default: 25)
after / before (string): Pagination cursors
date_preset / time_range: Date filter
updated_since (number): Unix timestamp — return ads updated since this time
Returns: Object with data (ad array) and paging. Use meta_ads_fetch_pagination_url with paging.next for more results.
Inputs: act_id (required), fields, filtering, date_preset, +7 more.
meta_ads_get_ads_by_adsetGet Meta Ads by Ad SetARead-onlyIdempotent
Retrieve all ads belonging to a specific Meta ad set with filtering and pagination.
Args:
adset_id (string): Ad set ID, e.g., '23843211234567'
fields (string[]): Fields per ad. Common: id, name, account_id, adset_id, campaign_id, status, effective_status, configured_status, creative, bid_amount, bid_type, created_time, updated_time, targeting, conversion_specs, recommendations, preview_shareable_link
effective_status (string[]): Filter by status: ACTIVE, PAUSED, DELETED, PENDING_REVIEW, DISAPPROVED, PREAPPROVED, PENDING_BILLING_INFO, CAMPAIGN_PAUSED, ARCHIVED, IN_PROCESS, WITH_ISSUES
filtering (object[]): Filter objects. Operators: EQUAL, NOT_EQUAL, GREATER_THAN, GREATER_THAN_OR_EQUAL, LESS_THAN, LESS_THAN_OR_EQUAL, IN_RANGE, NOT_IN_RANGE, CONTAIN, NOT_CONTAIN, IN, NOT_IN, EMPTY, NOT_EMPTY
limit (number): Results per page (1-100, default: 25, max: 100)
after / before (string): Pagination cursors
date_format (string): Date format for response
Returns: Object with data (ad array) and paging. Use meta_ads_fetch_pagination_url with paging.next for more results.
Inputs: adset_id (required), fields, filtering, effective_status, +5 more.
meta_ads_get_ads_by_campaignGet Meta Ads by CampaignARead-onlyIdempotent
Retrieve all ads belonging to a specific Meta campaign with filtering and pagination.
Args:
campaign_id (string): Campaign ID, e.g., '23843xxxxx'
fields (string[]): Fields per ad. Common: id, name, account_id, adset_id, campaign_id, status, effective_status, configured_status, creative, bid_amount, bid_type, created_time, updated_time, targeting, conversion_specs, recommendations, preview_shareable_link
effective_status (string[]): Filter by status: ACTIVE, PAUSED, DELETED, PENDING_REVIEW, DISAPPROVED, PREAPPROVED, PENDING_BILLING_INFO, ADSET_PAUSED, ARCHIVED, IN_PROCESS, WITH_ISSUES
filtering (object[]): Additional filter objects with field, operator, value
limit (number): Results per page (1-100, default: 25)
after / before (string): Pagination cursors
Returns: Object with data (ad array) and paging. Use meta_ads_fetch_pagination_url with paging.next for more results.
Inputs: campaign_id (required), fields, filtering, effective_status, +4 more.
meta_ads_get_adset_by_idGet Meta Ad Set by IDARead-onlyIdempotent
Retrieve detailed information about a specific Meta ad set.
Args:
adset_id (string): Ad set ID, e.g., '23843211234567'
fields (string[]): Fields per ad set. Common: id, name, account_id, campaign_id, status, effective_status, daily_budget, lifetime_budget, budget_remaining, bid_amount, bid_strategy, billing_event, optimization_goal, targeting, start_time, end_time, created_time, updated_time, pacing_type, destination_type
Returns: Object with the requested ad set fields.
Examples:
Use when: "Get the targeting and budget for ad set 23843211234567"
Use when: "What is the optimization goal and status of this ad set?"
Inputs: adset_id (required), fields.
meta_ads_get_adset_insightsGet Meta Ad Set InsightsARead-onlyIdempotent
Retrieve performance insights for a specific Meta ad set.
Provides advertising statistics for an ad set, useful for analyzing performance across its child ads.
Args:
adset_id (string): Ad set ID, e.g., '6123456789012'
fields (string[]): Metrics to retrieve. Common: adset_name, campaign_name, impressions, clicks, spend, ctr, reach, actions, cpc, cpm, cpp, cost_per_action_type
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: adset, ad (default: adset)
breakdowns (string[]): Segment by: age, gender, country, publisher_platform, impression_device, platform_position, 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.
Inputs: adset_id (required), fields, date_preset, time_range, +19 more.
meta_ads_get_adsets_by_adaccountGet Meta Ad Sets by Ad AccountARead-onlyIdempotent
Retrieve all ad sets from a specific Meta ad account with filtering and pagination.
Args:
act_id (string): Ad account ID prefixed with 'act_', e.g., 'act_1234567890'
fields (string[]): Fields per ad set. Common: id, name, account_id, campaign_id, status, effective_status, daily_budget, lifetime_budget, budget_remaining, bid_amount, bid_strategy, billing_event, optimization_goal, targeting, start_time, end_time, created_time, updated_time, pacing_type, destination_type
effective_status (string[]): Filter by status: ACTIVE, PAUSED, DELETED, PENDING_REVIEW, DISAPPROVED, PREAPPROVED, PENDING_BILLING_INFO, CAMPAIGN_PAUSED, ARCHIVED, WITH_ISSUES
filtering (object[]): Additional filter objects, e.g., [{field: 'daily_budget', operator: 'GREATER_THAN', value: 1000}]
limit (number): Results per page (1-100, default: 25)
after / before (string): Pagination cursors
date_preset / time_range: Date filter
updated_since (number): Unix timestamp — return ad sets updated since this time
date_format (string): Date format for response
Returns: Object with data (ad set array) and paging. Use meta_ads_fetch_pagination_url with paging.next for more results.
Inputs: act_id (required), fields, filtering, date_preset, +8 more.
meta_ads_get_adsets_by_campaignGet Meta Ad Sets by CampaignARead-onlyIdempotent
Retrieve all ad sets belonging to a specific Meta campaign with filtering and pagination.
Args:
campaign_id (string): Campaign ID, e.g., '23843xxxxx'
fields (string[]): Fields per ad set. Common: id, name, account_id, campaign_id, status, effective_status, daily_budget, lifetime_budget, budget_remaining, bid_amount, bid_strategy, billing_event, optimization_goal, targeting, start_time, end_time, created_time, updated_time, pacing_type, destination_type
effective_status (string[]): Filter by status: ACTIVE, PAUSED, DELETED, PENDING_REVIEW, DISAPPROVED, PREAPPROVED, PENDING_BILLING_INFO, ARCHIVED, WITH_ISSUES
filtering (object[]): Additional filter objects, e.g., [{field: 'optimization_goal', operator: 'IN', value: ['OFFSITE_CONVERSIONS', 'VALUE']}]
limit (number): Results per page (1-100, default: 25)
after / before (string): Pagination cursors
date_format (string): Date format for response
Returns: Object with data (ad set array) and paging. Use meta_ads_fetch_pagination_url with paging.next for more results.
Inputs: campaign_id (required), fields, filtering, effective_status, +5 more.
meta_ads_get_adsets_by_idsGet Multiple Meta Ad Sets by IDsARead-onlyIdempotent
Retrieve information for multiple Meta ad sets in a single API call (batch lookup).
Efficient when you need data for several ad sets at once.
Args:
adset_ids (string[]): List of ad set IDs to retrieve, e.g., ['23843211234567', '23843211234568']
fields (string[]): Fields per ad set. Common: id, name, account_id, campaign_id, status, effective_status, daily_budget, lifetime_budget, budget_remaining, bid_amount, bid_strategy, billing_event, optimization_goal, targeting, start_time, end_time, created_time, updated_time, pacing_type, destination_type
date_format (string): Date format: 'U' for Unix timestamp, 'Y-m-d H:i:s' for MySQL datetime
Returns: Object where keys are ad set IDs and values are the corresponding ad set details.
Examples:
Use when: "Get details for ad sets 23843211234567, 23843211234568, and 23843211234569"
Inputs: adset_ids (required), fields, date_format.
meta_ads_get_ad_videoGet Meta Ad VideoARead-onlyIdempotent
Get video details (source URL, thumbnail, title, duration) for a Meta ad video. Provide either ad_id (server resolves the video_id from the ad's creative) or video_id directly. Pass act_id when available — the /act_X/advideos edge avoids permission errors (#10 / #33) that hit the bare /{video_id} node for BM-shared or page-owned videos.
Inputs: ad_id, video_id, act_id.
meta_ads_get_campaign_by_idGet Meta Campaign by IDARead-onlyIdempotent
Retrieve detailed information about a specific Meta ad campaign.
Args:
campaign_id (string): Campaign ID, e.g., '23843xxxxx'
fields (string[]): Fields to retrieve. Available: id, name, account_id, objective, status, effective_status, configured_status, daily_budget, lifetime_budget, budget_remaining, spend_cap, bid_strategy, buying_type, created_time, updated_time, start_time, stop_time, special_ad_categories, pacing_type, promoted_object, issues_info, recommendations
date_format (string): Date format: 'U' for Unix timestamp, 'Y-m-d H:i:s' for MySQL datetime, default: ISO 8601
Returns: Object with the requested campaign fields.
Examples:
Use when: "Get details for campaign 23843xxxxx"
Use when: "What is the objective and status of my campaign?"
Inputs: campaign_id (required), fields, date_format.
meta_ads_get_campaign_insightsGet Meta Campaign InsightsARead-onlyIdempotent
Retrieve performance insights for a specific Meta ad campaign.
Fetches advertising statistics for a campaign, allowing analysis of metrics like impressions, clicks, conversions, spend, etc.
Args:
campaign_id (string): Campaign ID, e.g., '23843xxxxx'
fields (string[]): Metrics to retrieve. Common: campaign_name, impressions, clicks, spend, ctr, reach, actions, objective, cpc, cpm, date_start, date_stop
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: campaign, adset, ad (default: campaign)
breakdowns (string[]): Segment by: age, gender, country, publisher_platform, impression_device, 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.
Inputs: campaign_id (required), fields, date_preset, time_range, +19 more.
meta_ads_get_campaigns_by_adaccountGet Meta Campaigns by Ad AccountARead-onlyIdempotent
Retrieve all campaigns from a specific Meta ad account with filtering and pagination.
Args:
act_id (string): Ad account ID prefixed with 'act_', e.g., 'act_1234567890'
fields (string[]): Fields per campaign. Common: id, name, objective, effective_status, created_time, daily_budget, lifetime_budget, budget_remaining
effective_status (string[]): Filter by status: ACTIVE, PAUSED, DELETED, PENDING_REVIEW, DISAPPROVED, PREAPPROVED, PENDING_BILLING_INFO, ARCHIVED, WITH_ISSUES
objective (string[]): Filter by objective: APP_INSTALLS, BRAND_AWARENESS, CONVERSIONS, EVENT_RESPONSES, LEAD_GENERATION, LINK_CLICKS, MESSAGES, PAGE_LIKES, POST_ENGAGEMENT, PRODUCT_CATALOG_SALES, REACH, VIDEO_VIEWS
filtering (object[]): Additional filter objects with field, operator, value
limit (number): Results per page (1-100, default: 25)
after / before (string): Pagination cursors
date_preset / time_range: Date filter for campaigns
updated_since (number): Return campaigns updated since this Unix timestamp
is_completed (boolean): True = only completed, False = only active, null = both
special_ad_categories (string[]): Filter by: EMPLOYMENT, HOUSING, CREDIT, ISSUES_ELECTIONS_POLITICS, NONE
include_drafts (boolean): Include draft campaigns if true
date_format (string): Date format for response
Returns: Object with data (campaign array) and paging. Use meta_ads_fetch_pagination_url with paging.next for more results.
Inputs: act_id (required), fields, filtering, date_preset, +13 more.
meta_ads_get_image_by_hashGet Meta Ad Image by HashARead-onlyIdempotent
Look up a single image in an ad account's image library by hash. Returns the CDN url, dimensions, name, and status — useful when you only have the hash (e.g., from upload_ad_image or a creative's object_story_spec.link_data.image_hash) and need the URL.
Inputs: act_id (required), image_hash (required).
meta_ads_get_interest_suggestionsGet Meta Ad Interest SuggestionsARead-onlyIdempotent
Given a seed list of interest names, return related/suggested interests.
Args:
interest_list (string[]): Seed interest names, e.g., ["Basketball", "Soccer"]
limit (number, optional): Max suggestions (default 25)
Inputs: interest_list (required), limit.
meta_ads_list_ad_accountsList Meta Ad AccountsARead-onlyIdempotent
List all ad accounts associated with the authenticated Facebook user.
Returns account names and IDs. When the response contains a paging.next URL, use meta_ads_fetch_pagination_url to retrieve additional pages.
Returns: Object with adaccounts.data array, each containing:
id (string): Ad account ID prefixed with 'act_' (e.g., 'act_1234567890')
name (string): Display name of the ad account
Examples:
Use when: "Show me all my ad accounts"
Use when: "What ad accounts do I have access to?"
Inputs: no named parameters.
meta_ads_search_behaviorsSearch Meta Ad BehaviorsARead-onlyIdempotent
List available behavior targeting options.
Args:
limit (number, optional): Max results (default 50)
Inputs: limit.
meta_ads_search_demographicsSearch Meta Ad DemographicsARead-onlyIdempotent
List demographic targeting options. Pass demographic_class to scope the results (default: 'demographics'). Other valid classes: 'life_events', 'industries', 'income', 'family_statuses', 'user_device', 'user_os'.
Inputs: demographic_class, limit.
meta_ads_search_geo_locationsSearch Meta Ad Geo LocationsARead-onlyIdempotent
Search Meta's geographic targeting catalog by query string. Returns location keys to use in targeting.geo_locations.
Args:
q (string): Search term (e.g., "New York", "Japan")
location_types (string[], optional): Filter by types: 'country', 'region', 'city', 'zip', 'geo_market', 'electoral_district'.
limit (number, optional): Max results (default 25)
Inputs: q (required), location_types, limit.
meta_ads_search_interestsSearch Meta Ad InterestsARead-onlyIdempotent
Search Meta's interest targeting catalog by keyword. Returns interest IDs suitable for use in an ad set's targeting.flexible_spec.
Args:
q (string): Search term (e.g., "baseball", "cooking", "travel")
limit (number, optional): Max results (default 25)
Returns: { data: [{ id, name, audience_size_lower_bound, audience_size_upper_bound, path, topic }] }
Inputs: q (required), limit.
meta_ads_search_pages_by_nameSearch Meta Pages by NameARead-onlyIdempotent
Search the user's pages by a case-insensitive substring of name or username.
Internally fetches /me/accounts then filters client-side. Meta's Graph API does not expose a server-side name filter on /me/accounts.
Args:
search_term (string): Substring to match against page name or username.
Inputs: search_term (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 35 tools
Each tool targets a distinct resource and action, such as retrieving ads by account, adset, or campaign, and separate search tools for interests, behaviors, demographics, etc. There is minimal overlap or ambiguity.
All tool names follow a consistent `meta_ads_<verb>_<object>` pattern, using lowercase and underscores. Variations like `meta_ads_get_ads_by_adaccount` and `meta_ads_search_interests` are predictable and uniform.
With 35 tools, the count is well above the typical 15-25 range considered reasonable. While the domain is complex, the number feels excessive and could be streamlined.
The tool set is heavily read-oriented, covering listing, retrieving, and searching for various objects. However, it lacks essential write operations like create, update, or delete for campaigns, ad sets, ads, and creatives, which is a significant gap for typical advertising workflows.
Maintenance
Related MCP Connectors
Meta Ads MCP server: run Facebook and Instagram campaigns, ad sets, ads and reports from AI.
60+ Meta Ads tools for AI agents: audits, campaign management, audiences and CAPI tracking.
Meta Ads MCP server: 10 tools for Facebook and Instagram reports, ads, Ad Library. Ads start paused.
Meta Ads MCP server with 47 tools for campaigns, creatives, audiences, and insights.
Related MCP Servers
- AlicenseAqualityBmaintenanceA Model Context Protocol server that allows AI models to access, analyze, and manage Meta advertising campaigns, enabling LLMs to retrieve performance data, visualize ad creatives, and provide strategic insights for Facebook and Instagram platforms.351,368Business Source 1.1
- AlicenseCqualityCmaintenanceA local Model Context Protocol server that enables interaction with the Meta Marketing API to manage ad accounts, campaigns, and creatives. It provides tools for targeting research, insight reporting, and campaign management through local MCP clients like Claude Code and Cursor.4079AGPL 3.0
- AlicenseNot gradedqualityBmaintenanceA Model Context Protocol server that lets AI assistants run your Meta Ads end to end — launch campaigns, upload creatives, update budgets, and dig into performance through natural conversation. Works across Facebook, Instagram, and other Meta surfaces.Business Source 1.1
- FlicenseNot gradedqualityDmaintenanceA comprehensive MCP server for managing and analyzing Meta Ads (Facebook/Instagram) with over 80 natural-language tools for AI agents like Claude Desktop.-