Meta Ads MCP Server (superpower-growth/meta-ads-mcp) is an MCP server listed on the M8ven Trust Index. It scores 48 out of 100, grade D. It declares 21 tools. No publisher has claimed this listing.

D
Caution
48/100

Meta Ads MCP Server

Provides access to Meta Marketing API for comprehensive ad analytics and AI-powered video creative analysis.

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

superpower-growth

Source: Glama

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

Install from

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
🚨
Known vulnerabilities in dependencies: 1 critical, 12 high
Affects packages this MCP installs at runtime. Upgrade or remove the affected dependency.
🔐
You'll be asked for 9 credentials: ANTHROPIC_API_KEY, FACEBOOK_APP_SECRET, GEMINI_API_KEY, GOOGLE_OAUTH_CLIENT_SECRET, META_ACCESS_TOKEN, NOTION_API_KEY, SCRAPECREATORS_API_KEY, SESSION_SECRET, SHIP_AD_API_KEY
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes24 tools · 3 behind config

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

analyze-ad-themes

Analyze messaging themes across video ads and correlate with performance. Groups ads by spoken theme (e.g. pain-agitate-solve, social-proof), emotional tone, or creative approach. Shows which messaging strategies drive the best CTR, CPC, and ROAS. Requires video analyses to be cached first via batch

analyze-image-url

Download an image from URL or Google Drive folder, upload to GCS, and analyze with Gemini AI. For Drive folders, lists all images with dimensions/aspect ratios and analyzes the most recent one. Returns structured image analysis including visual elements, text overlays, emotional tone, color palette,

analyze-video-creative

Analyze video ad creative content using Gemini AI. Returns structured insights including scenes, text overlays, emotional tone, creative approach, target audience indicators, spoken audio transcript with timestamps, and spoken messaging theme analysis (e.g. social-proof, pain-agitate-solve, benefit-

analyze-video-url

Download a video from URL or Google Drive folder, upload to GCS, and analyze with Gemini AI. For Drive folders, lists ALL files with dimensions/aspect ratios (4:5, 9:16, etc.) and analyzes the most recent video. Returns structured video analysis including scenes, text overlays, emotional tone, and c

batch-analyze-video-creative

Analyze multiple video ad creatives in a single call. Processes ads in parallel (max 2 concurrent) using Gemini AI. Returns per-ad analysis results with scenes, text overlays, emotional tone, transcript, and spoken themes. Accepts 1-50 entries as ad ID strings or {adId, creativeId} objects. Pass cre

compare-entities

Compare and rank multiple campaigns, ad sets, or ads on performance metrics to identify top and bottom performers. Returns rankings, percentiles, statistical benchmarks, and highlights best/worst performers for each metric.

compare-time-periods

Compare campaign/adset/ad performance between two time periods to identify trends, improvements, and declines. Calculates percent changes for all metrics and highlights significant improvements or declines.

get-activity-log

Query account activity history showing budget changes, status changes (pause/unpause), bid changes, targeting updates, creative changes, and billing events. Use this to audit what actions were taken on the account.

get-account

Get basic information about a Meta ad account including name, ID, currency, and status

get-ad-creative-text

Retrieve ad creative text content including primary text, headline, and description for content analysis and ad categorization. Returns text from all active ads or specific ads by ID.

get-audience-overlap

Compare targeting specs across campaigns/ad sets to identify audience overlap. Analyzes geo, age, gender, interests, behaviors, and custom audience overlap pairwise. Flags high-overlap pairs that may compete in the same auction and waste budget.

get-campaign-config

Fetch campaign-level configuration settings including ASC (Advantage+ Shopping) settings, existing_customer_budget_percentage, bid strategies, budgets, and ad set targeting. Diagnoses common issues like missing customer budget caps and broad targeting.

get-creative-fatigue

Detect ad creative fatigue by analyzing daily frequency and CTR trends. Returns a fatigue score (0-100), frequency/CTR trends, and recommendation (healthy/monitor/rotate/critical). Use with a specific entityId to analyze a campaign, ad set, or ad over time.

get-creative-performance

Aggregate ad performance by creative ID across all ads using the same creative. Shows which creative variants perform best regardless of targeting or campaign structure. Returns ranked list with aggregated metrics, ROAS, custom conversions, and list of ad IDs per creative.

get-demographics

Query performance metrics segmented by demographic/placement breakdowns (age, gender, country, device, publisher platform, platform position). Three modes: "standard" for impressions/clicks/spend on all ads, "video" for completion funnel on video ads, "conversions" for conversion tracking by placeme

get-facebook-pages

Get Facebook Pages accessible by the authenticated user. Returns page IDs, names, categories, and linked Instagram actor IDs. Required for creating ad creatives.

get-performance

Query performance metrics at any level (campaign, adset, or ad). Includes CTR, CPC, CPM, ROAS, reach, custom conversions (subscription_created, etc.), ad relevance diagnostics (quality/engagement/conversion rankings), and optional AI video analysis. Supports preset and custom date ranges. Replaces g

get-saved-audiences

Get saved audiences for a Meta ad account. Returns audience names, IDs, and approximate sizes. Use to map ICP targeting to audience IDs for ad set creation.

get-video-metrics

Query video ad metrics including completion funnel (25/50/75/95/100%), ThruPlay, engagement depth (2s/15s/30s views), retention scores, average watch percentage, and drop-off weak points. Replaces get-video-performance and get-video-engagement.

list-ad-sets

List ad sets within a specific Meta campaign. Returns ad set names, IDs, statuses, and budgets. Critical for mapping Notion ad set names to Meta ad set IDs.

list-custom-conversions

List all custom conversion events available in the ad account. Returns friendly names that can be used in the customActions parameter of get-performance, get-creative-performance, and get-demographics tools.

sc-get-adbehind config

Get full details for a specific ad from the Meta Ad Library by ID or URL. Returns creative assets (video/image URLs), ad copy, CTA, landing page, impressions, spend, targeting demographics, and optionally a video transcript.

sc-search-adsbehind config

Search the Meta Ad Library by keyword or company name. For company searches, automatically resolves the company name to a Facebook page ID and fetches their ads. Supports filtering by country, status, media type, date range, and more. Use fetch_all: true to auto-paginate all results.

sc-search-companiesbehind config

Search for companies/pages in the Meta Ad Library by name. Returns page IDs that can be used with sc-search-ads to fetch a company's ads.

// known CVEs in dependencies1 critical12 high6 medium13 low

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

criticalvitest@4.0.18GHSA-5xrq-8626-4rwp

When Vitest UI server is listening, arbitrary file can be read and executed

high@modelcontextprotocol/sdk@1.25.3GHSA-345p-7cg4-v4c7

@modelcontextprotocol/sdk has cross-client data leak via shared server/transport instance reuse

highaxios@1.13.4GHSA-35jp-ww65-95wh

axios Vulnerable to Full Man-in-the-Middle via Prototype Pollution Gadget in `config.proxy`

highaxios@1.13.4GHSA-3g43-6gmg-66jw

axios Vulnerable to Credential Theft and Response Hijacking via Prototype Pollution Gadget in Config Merge

highaxios@1.13.4GHSA-43fc-jf86-j433

Axios is Vulnerable to Denial of Service via __proto__ Key in mergeConfig

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
🔐 secretANTHROPIC_API_KEY
configDEFAULT_AD_SET_ID
configDEFAULT_CAMPAIGN_ID
configDEFAULT_INSTAGRAM_ACTOR_ID
configDEFAULT_PAGE_ID
configDEFAULT_SAVED_AUDIENCE_ID
configFACEBOOK_APP_IDFrom Facebook App Settings
🔐 secretFACEBOOK_APP_SECRETFrom Facebook App Settings
configFACEBOOK_CALLBACK_URL
configFACEBOOK_MARKETING_API
configFIRESTORE_CACHE_TTL_HOURSCache TTL (default: 24)
configGCP_PROJECT_ID
configGCS_BUCKET_NAMEGCS bucket for video staging
🔐 secretGEMINI_API_KEYGemini API key (or use Vertex AI)
configGEMINI_MAX_CONCURRENT_ANALYSES
configGEMINI_MAX_COST_PER_ANALYSIS
configGEMINI_MODEL
configGEMINI_USE_VERTEX_AI
configGOOGLE_OAUTH_CALLBACK_URL
configGOOGLE_OAUTH_CLIENT_ID
🔐 secretGOOGLE_OAUTH_CLIENT_SECRET
configGOOGLE_SERVICE_ACCOUNT_JSONGCP service account key
configHOST
🔐 secretMETA_ACCESS_TOKENLong-lived token from Graph API Explorer
configMETA_AD_ACCOUNT_IDAd account ID (format: act_123456789)
🔐 secretNOTION_API_KEY
configNOTION_MEDIA_DB_ID
configPIPELINE_MAX_CONCURRENCY
configPIPELINE_POLL_INTERVAL_MS
🔐 secretSCRAPECREATORS_API_KEY
🔐 secretSESSION_SECRETRandom 32+ char secret (openssl rand -base64 32)
configSESSION_TTL
🔐 secretSHIP_AD_API_KEY
Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.
deployPORT
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

24/24 tools missing one or more hints — analyze-ad-themes (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); analyze-image-url (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); analyze-video-creative (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +21 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

License file

No license file

Add a LICENSE file (MIT, Apache-2.0, etc.).

Tool test coverage

Only 5/24 tools referenced in tests (21%)

Write tests that reference each tool by name so every tool has at least one test.

Production dependencies are patched

0 critical, 12 high severity in production deps — @modelcontextprotocol/sdk@1.25.3 (high), axios@1.13.4 (high)

Run npm audit fix, or upgrade the affected packages to a non-vulnerable version.

Dev dependencies

1 critical/high in dev-only deps (does not ship to users)

Upgrade dev dependencies when convenient.

Dependency freshness

1/16 production deps stale: axios-retry@2024-08-02 (2.1y)

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 6 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/superpower-growth/meta-ads-mcp?variant=verified)](https://m8ven.ai/mcp/superpower-growth/meta-ads-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: 3f93d1a8fe3746f7051e2e7c153f3dbe976cdaf5
code hash: 97756df64498f7489e32bada0812c7628dd550996f57f8cad157090fd471f2f1
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client