Meta Ad Library Spend MCP by AdSpendSpy
REMOTE · WWW.ADSPENDSPY.COM
Facebook and Meta Ad Library ads with estimated ad spend per ad, top landing pages and alerts.
Available components
Last scanned (6 hours ago)
Scores higher than 54% of remote servers
Reachable. Last reached 5 Nov 2026.
Category Marketing and SEO
Recent critical change
Authorization (24 Oct 2026). See the changelog before you install this server.
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security57
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (track_brand). See how to fix → View diagnostics → Fail
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability77
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 2334 tokens (~137/item across 17 items; 17 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management40
- Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage86
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 59% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 17 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 18 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a current MCP spec version (2026-07-28).Pass
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 4 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.
- 2 Nov 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.
- 31 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.
- 29 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.
- 26 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.
- 25 Oct 26 0
- Stability: unverified → 0.03 ▲ functional
- 24 Oct 26 +27
- Authorization: pass → fail ▼ critical
- Transport: unverified → pass ▲ security
- Injection markers: unverified → pass ▲ security
- First check of Judged manipulation: pass security
- MCP protocol: unverified → pass ▲ functional
- Schema quality: unverified → 100 ▲ functional
- Tool coverage: unverified → 100 ▲ functional
- First check of Schema quality: fail functional
- First check of Destructive annotations: pass functional
- First check of Schema quality: fail functional
- First check of Tool coverage: 59 functional
- First check of Schema quality: good functional
- 23 Oct 26 +14
- HSTS header: unverified → fail ▼ security
- Transport: fail → unverified ▼ security
- Authorization: unverified → pass ▲ security
- First check of Authorization: pass security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 5 Nov 2026 · Probed https://www.adspendspy.com/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=adspendspy.com | CN=WE1,O=Google Trust Services,C=US | 19 Oct 2026 | 17 Jan 2027 | ECDSA 256 | ECDSA-SHA256 | fc25527575ac05d9133f92cb7205a86f |
| SANs: adspendspy.com, *.adspendspy.com | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of www.adspendspy.com. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| com. | present | 19718 | 13 | Verified |
| adspendspy.com. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
| Header | Value |
|---|---|
| x-content-type-options | nosniff |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://www.adspendspy.com/mcp | Verified | 200 | |
| http (plaintext) | http://www.adspendspy.com/mcp | HTTPS enforced | 301 | https://www.adspendspy.com/mcp |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
check_brands_tracked Check advertiser tracking ~33
Check whether each string Meta page ID is actively tracked by your account.
| Name | Type | Req | Description |
|---|---|---|---|
| page_ids | array | yes | – |
No output schema declared.
No examples provided.
compare_advertisers Compare advertisers ~82
Compare 2 to 6 tracked advertisers side by side: category, active ads where known, estimated 30-day spend range and one top ad each. A name AdSpendSpy does not track is listed as not tracked and never replaced by a similar brand. No sign-in needed.
| Name | Type | Req | Description |
|---|---|---|---|
| brands | array | – | – |
| page_ids | array | – | – |
No output schema declared.
No examples provided.
find_similar_advertisers Find similar advertisers ~141
List up to six tracked advertisers similar to a brand (same Facebook page category or niche), each with category, active ads where known, estimated 30-day spend range and one top ad. No sign-in needed. Pass page_id when known, otherwise the exact brand name.
| Name | Type | Req | Description |
|---|---|---|---|
| brand | string | – | Exact brand or advertiser name as the user wrote it, e.g. "Gymshark". Used only when no page_id is given; never matched to a differently named brand. |
| limit | integer | – | – |
| page_id | string | – | Numeric Meta page ID of the advertiser, as returned in earlier results. Preferred when known. |
No output schema declared.
No examples provided.
get_ad_details Inspect an ad creative ~84
Retrieve one ad of an advertiser you actively track by its internal AdSpendSpy ad ID (internal_ad_id), not its Meta ad ID. Saved lists and favorites do not retain MCP ad access after you remove a tracked brand on the website.
| Name | Type | Req | Description |
|---|---|---|---|
| ad_id | integer | yes | Internal AdSpendSpy ad ID (internal_ad_id in ad listings); never a Meta ad ID. |
No output schema declared.
No examples provided.
get_ad_lists Read saved ad lists ~76
Read your saved lists, with ad creatives limited to advertisers you actively track. list_id selects one owned list; ad_id reports which of your lists contain that internal ad ID and takes precedence when both are supplied. Saving an ad does not bypass tracking limits.
| Name | Type | Req | Description |
|---|---|---|---|
| ad_id | integer | – | – |
| list_id | integer | – | – |
No output schema declared.
No examples provided.
get_advertiser_ads Show an advertiser's Meta ads ~276
Show one brand's active Meta ads (Facebook and Instagram). For brands AdSpendSpy tracks: active ad count, an estimated 30-day spend range split into EU/UK and US where available, and up to six top ads with image or video, headline, text, days running, platforms and landing domain. A brand name is matched exactly; if only similar names exist, it returns them as candidates and no ads. With live_lookup true, an untracked brand is looked up live in the Meta Ad Library (up to ten newest ads, no spend). No sign-in needed. Pass page_id when known, otherwise brand.
| Name | Type | Req | Description |
|---|---|---|---|
| brand | string | – | Exact brand or advertiser name as the user wrote it, e.g. "Gymshark". Used only when no page_id is given; never matched to a differently named brand. |
| country | string | – | Two-letter ISO country code such as "DE", "US" or "GB" when the user names a country; "ALL" for worldwide. |
| live_lookup | boolean | – | True only after a previous call returned candidates and none is the brand the user means. Live lookups are limited per conversation and per day. |
| page_id | string | – | Numeric Meta page ID of the advertiser, as returned in earlier results. Preferred when known. |
No output schema declared.
No examples provided.
get_pending_alert_count Count pending alerts ~20
Read the number of pending alerts for your account.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_projects Read advertiser projects ~54
Read your projects. public_id selects one owned project; brand_id selects memberships for an actively tracked internal brand record and takes precedence when both are supplied.
| Name | Type | Req | Description |
|---|---|---|---|
| brand_id | integer | – | – |
| public_id | string | – | – |
No output schema declared.
No examples provided.
get_top_ads_stats Analyze estimated ad spend ~169
Analyze latest cumulative estimated spend in EUR for your tracked advertisers. page_id is an exact advertiser filter. timeframe filters when ads were last seen, NOT spend accrued during that period. Creative breakdowns sample the top 1,000 ads; response metadata states matched and sampled counts and full-match aggregate spend. Zero can mean unavailable estimates.
| Name | Type | Req | Description |
|---|---|---|---|
| active_only | – | – | – |
| category | string | – | – |
| media_type | string | – | – |
| page_id | string | – | Meta advertiser page ID, kept as a string. |
| project | string | – | all, my_brands, unassigned, or an owned project public_id. Every choice stays within your tracked brands. |
| q | string | – | – |
| timeframe | string | – | Last-seen window; never a period-spend calculation. |
No output schema declared.
No examples provided.
get_top_landingpages_stats Rank landing pages by estimated spend ~200
Rank the landing pages of your tracked advertisers by latest cumulative estimated spend in EUR. Ads are grouped by landing URL with ad, advertiser and active-ad counts, the top-spending advertiser and, when one is stored, a screenshot as screenshot_url (site path) and screenshot_full_url (absolute URL). page_id is an exact advertiser filter; q matches part of the landing URL. timeframe filters when ads were last seen, NOT spend accrued during that period. Zero can mean unavailable estimates.
| Name | Type | Req | Description |
|---|---|---|---|
| active_only | – | – | – |
| limit | integer | – | – |
| page_id | string | – | Meta advertiser page ID, kept as a string. |
| project | string | – | all, my_brands, unassigned, or an owned project public_id. Every choice stays within your tracked brands. |
| q | string | – | Substring of the landing URL. |
| timeframe | string | – | Last-seen window; never a period-spend calculation. |
No output schema declared.
No examples provided.
list_alerts List spend alerts ~193
List spend alerts for ads of advertisers you actively track, newest first (event ad.spend_alert). Each item carries the alert threshold and the estimated spend when the alert was created. Without since_id or cursor the last 30 days are returned. since_id returns only items with a higher alert_id. Spend is a latest cumulative estimate in EUR; null means unknown. Reading alerts does not mark them as sent. Use page_id or project, not both.
| Name | Type | Req | Description |
|---|---|---|---|
| cursor | string | – | Opaque pagination.next_cursor returned by the previous page with the same filters. |
| limit | integer | – | – |
| page_id | string | – | Meta advertiser page ID, kept as a string. |
| project | string | – | Public_id of one of your projects. Cannot be combined with page_id. |
| since_id | integer | – | Return only items with a higher id (internal_ad_id for new ads, alert_id for alerts). |
No output schema declared.
No examples provided.
list_brand_ads List advertiser ads ~153
List creative summaries for one tracked advertiser, newest internal ID first, or with sort spend highest latest cumulative estimated spend first (use it for an advertiser's top ads). pagination.next_cursor returns the next page. Each ad carries internal_ad_id (AdSpendSpy ID) and meta_ad_id (the ad on Meta).
| Name | Type | Req | Description |
|---|---|---|---|
| active_only | boolean | – | – |
| cursor | string | – | Opaque pagination.next_cursor returned by the previous page with the same filters. |
| limit | integer | – | – |
| media_type | string | – | – |
| page_id | string | yes | Meta advertiser page ID, kept as a string. |
| sort | string | – | newest = newest internal ID first; spend = highest estimated spend first. |
No output schema declared.
No examples provided.
list_new_ads List new ads of tracked brands ~198
List ads that newly appeared for advertisers you actively track, newest first (event ad.new). An ad counts as new when it started at most 7 days before it was first seen, so the back catalog of a freshly tracked advertiser is excluded. Without since_id or cursor the last 30 days are returned. since_id returns only items with a higher internal_ad_id. Spend is a latest cumulative estimate in EUR; null means unknown. Use page_id or project, not both.
| Name | Type | Req | Description |
|---|---|---|---|
| cursor | string | – | Opaque pagination.next_cursor returned by the previous page with the same filters. |
| limit | integer | – | – |
| page_id | string | – | Meta advertiser page ID, kept as a string. |
| project | string | – | Public_id of one of your projects. Cannot be combined with page_id. |
| since_id | integer | – | Return only items with a higher id (internal_ad_id for new ads, alert_id for alerts). |
No output schema declared.
No examples provided.
list_tracked_brands List tracked advertisers ~53
List your actively tracked advertisers and their string page_id values.
| Name | Type | Req | Description |
|---|---|---|---|
| project | string | – | all, my_brands, unassigned, or an owned project public_id. Every choice stays within your tracked brands. |
No output schema declared.
No examples provided.
search_advertisers Search Meta Ad Library advertisers ~74
Search AdSpendSpy's Meta Ad Library database for an advertiser or brand by name. Returns up to five matching brands with category, logo, number of active ads where known, and the page_id. No sign-in needed.
| Name | Type | Req | Description |
|---|---|---|---|
| query | string | yes | Brand or advertiser name, e.g. "Gymshark". |
No output schema declared.
No examples provided.
search_tracked_brands Find a tracked advertiser ~49
Search your tracked advertisers by name, Meta page ID, or stored Facebook URL. Searches existing local data only; does not resolve vanity URLs through paid providers.
| Name | Type | Req | Description |
|---|---|---|---|
| q | string | yes | – |
No output schema declared.
No examples provided.
track_brand Start tracking an advertiser ~172
Add a known advertiser to your tracked brands before reading its ads. Changes your AdSpendSpy account: the advertiser joins your tracked brands and AdSpendSpy starts importing its ads. Requires a Meta page_id and brand_name and consumes one of your existing account tracking slots, not an extra subscription. Repeating an active tracking is idempotent, even at the limit. New imports run in the background, so ads may not be ready yet. Returns tracked_count, tracked_limit, remaining_slots and ingestion_state. There is no MCP removal tool: remove brands on the AdSpendSpy website. Does not search Meta or resolve advertiser names or URLs.
| Name | Type | Req | Description |
|---|---|---|---|
| brand_name | string | yes | Advertiser display name, not a URL or an instruction. |
| page_id | string | yes | Meta advertiser page ID, kept as a string. |
No output schema declared.
No examples provided.
How do I install the Meta Ad Library Spend MCP by AdSpendSpy server?
Meta Ad Library Spend MCP by AdSpendSpy is a hosted endpoint at https://www.adspendspy.com/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · www.adspendspy.com
claude mcp add --transport http com-adspendspy-adspendspy 'https://www.adspendspy.com/mcp'
What is the Meta Ad Library Spend MCP by AdSpendSpy server?
Meta Ad Library Spend MCP by AdSpendSpy is listed in the public MCP registry as com.adspendspy/adspendspy. Facebook and Meta Ad Library ads with estimated ad spend per ad, top landing pages and alerts. This page covers its hosted endpoint (https://www.adspendspy.com/mcp).
Is the Meta Ad Library Spend MCP by AdSpendSpy server safe to use?
Meta Ad Library Spend MCP by AdSpendSpy scores 69 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Meta Ad Library Spend MCP by AdSpendSpy server expose?
Meta Ad Library Spend MCP by AdSpendSpy exposes 17 tools: search_advertisers, get_advertiser_ads, find_similar_advertisers, compare_advertisers, list_tracked_brands, and 12 more. Their descriptions and schemas cost roughly 2,027 tokens of context every time the server is loaded.
Does the Meta Ad Library Spend MCP by AdSpendSpy server require authentication?
No. We connected to Meta Ad Library Spend MCP by AdSpendSpy without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Meta Ad Library Spend MCP by AdSpendSpy server still maintained?
Meta Ad Library Spend MCP by AdSpendSpy is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.