Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Mako Metrics

REMOTE · UFUPDLAXDDCKQXBGBHWU.SUPABASE.CO

Competitor Meta ads intelligence reports. List plans, create orders, Stripe checkout for humans.

0 this week 84 Trust /100

Last scanned (9 hours ago)

Scores higher than 89% of remote servers

Reachable. Last reached 5 Nov 2026.

Category Marketing and SEO

Trust breakdown (7 categories)

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 Security80
Transport & Reachability100
Schema Quality & AI Usability69
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 2432 tokens (~152/item across 16 items; 16 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 Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage90
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 69% 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 16 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 17 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
Changelog

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.

  • 3 Oct 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “build_paused_campaign” rewrote its description, which is the text the model reads security
    • Tool “create_client” rewrote its description, which is the text the model reads security
    • Tool “draft_brand_from_website” rewrote its description, which is the text the model reads security
    • Tool “get_brand_profile” rewrote its description, which is the text the model reads security
    • Tool “get_download_url” rewrote its description, which is the text the model reads security
    • Tool “get_status” rewrote its description, which is the text the model reads security
    • Tool “list_clients” rewrote its description, which is the text the model reads security
    • Tool “list_creatives” rewrote its description, which is the text the model reads security
    • Tool “list_deliverables” rewrote its description, which is the text the model reads security
    • Tool “list_meta_assets” rewrote its description, which is the text the model reads security
    • Tool “order_report” rewrote its description, which is the text the model reads security
    • Tool “run_may” rewrote its description, which is the text the model reads security
    • Tool “set_brand_profile” rewrote its description, which is the text the model reads security
    • Tool “whoami” rewrote its description, which is the text the model reads security
    • Server version: 1.2.0 → 1.1.0 functional
    • “set_brand_profile” added an optional parameter “competitor_websites” cosmetic
    • “set_brand_profile” reworded the description of “competitors” cosmetic
  • 2 Oct 26 0
    • Authorization: unverified → partial ▲ security
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “build_paused_campaign” rewrote its description, which is the text the model reads security
    • Tool “create_client” rewrote its description, which is the text the model reads security
    • Tool “draft_brand_from_website” rewrote its description, which is the text the model reads security
    • Tool “get_brand_profile” rewrote its description, which is the text the model reads security
    • Tool “get_download_url” rewrote its description, which is the text the model reads security
    • Tool “get_status” rewrote its description, which is the text the model reads security
    • Tool “list_clients” rewrote its description, which is the text the model reads security
    • Tool “list_creatives” rewrote its description, which is the text the model reads security
    • Tool “list_deliverables” rewrote its description, which is the text the model reads security
    • Tool “list_meta_assets” rewrote its description, which is the text the model reads security
    • Tool “order_report” rewrote its description, which is the text the model reads security
    • Tool “run_may” rewrote its description, which is the text the model reads security
    • Tool “set_brand_profile” rewrote its description, which is the text the model reads security
    • Tool “whoami” rewrote its description, which is the text the model reads security
    • Server version: 1.1.0 → 1.2.0 functional
  • 28 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 25 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 18 Sept 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Schema quality: 184 → 146 ▲ functional
    • Tool coverage: 33% → 67% ▲ functional
    • Schema quality: good → excellent functional
    • Server version: 1.0.0 → 1.1.0 functional
    • New tool “build_paused_campaign” functional
    • New tool “create_client” functional
    • New tool “draft_brand_from_website” functional
    • New tool “get_brand_profile” functional
    • New tool “get_download_url” functional
    • New tool “get_status” functional
    • New tool “list_clients” functional
    • New tool “list_creatives” functional
    • New tool “list_deliverables” functional
    • New tool “list_meta_assets” functional
    • New tool “order_report” functional
    • New tool “run_may” functional
    • New tool “set_brand_profile” functional
    • New tool “whoami” functional
  • 26 Aug 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 25 Aug 26 0
    • Stability: 0.97 → pass security
  • 17 Aug 26 0
    • Tool “create_order” rewrote its description, which is the text the model reads security
    • Tool “list_plans” rewrote its description, which is the text the model reads security
    • Schema quality: 152 → 184 ▼ functional
Diagnostics

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://ufupdlaxddckqxbgbhwu.supabase.co/functions/v1/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=supabase.co CN=WE1,O=Google Trust Services,C=US 24 Oct 2026 22 Jan 2027 ECDSA 256 ECDSA-SHA256 d2b50611cd88e9c50e4e2231f4d3f059
SANs: supabase.co, *.supabase.co
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 ufupdlaxddckqxbgbhwu.supabase.co. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
co. present 7786 8 Verified
supabase.co. 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
strict-transport-security max-age=31536000; includeSubDomains; preload

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://ufupdlaxddckqxbgbhwu.supabase.co/functions/v1/mcp Verified 200
http (plaintext) http://ufupdlaxddckqxbgbhwu.supabase.co/functions/v1/mcp HTTPS enforced 301 https://ufupdlaxddckqxbgbhwu.supabase.co/functions/v1/mcp
MCP tools · 16 exposed · ~2,241 tokens

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 →

Tool Tokens
build_paused_campaign ~221

Build a real Meta campaign from chosen concepts, in the client's own ad account, left PAUSED. It cannot deliver and cannot spend until a person turns it on in Ads Manager, which this tool cannot do and neither can any other. Takes a minute or two. Budget floors: $6/day for leads and sales, $1/day otherwise; the ceiling is $500/day. Needs the May plan, a connected Facebook ad account, and an X-Mako-Key header.

NameTypeReqDescription
bid_amountinteger–Whole dollars. Required unless bid_strategy is LOWEST_COST_WITHOUT_CAP.
bid_strategystring––
campaign_namestring––
conversion_asset_idstring–Which conversion to optimize toward, from list_meta_assets. Needed for leads and sales.
daily_budgetintegeryesWhole dollars per day.
goalstringyes–
run_idstringyesThe May run the concepts came from.
variant_idsarrayyesWhich concepts to build ads from. From list_creatives.

No output schema declared.

No examples provided.

create_client ~79

Add a client workspace to the account. Each workspace holds one brand's profile, runs, creatives and campaigns. Plans include a fixed number of active clients, so this fails when the roster is full. Needs the May plan and an X-Mako-Key header.

NameTypeReqDescription
namestringyesThe client or brand name, as the customer would say it.

No output schema declared.

No examples provided.

create_order ~243

Create a Mako Metrics order brief for a customer and return a Stripe checkout link for them to complete payment. After payment, we email the customer when the report is ready, typically within 24h. They download the PDF report and export ZIP (saved ad images/videos, browsable gallery, raw ad data) at makometrics.com/portal. No payment is taken by this tool. It only returns a pay link the human opens. Report plans only. For May, the Meta ads agent, send the customer to makometrics.com/meta-ads-agent.

NameTypeReqDescription
client_account_namestring–Required for the agency plan: the client this batch is for.
company_namestringyes–
company_websitestring––
competitorsarrayyesBrand or Meta Ad Library page names. Snapshot=1, Dominator=up to 5, Agency=up to 10.
emailstringyesCustomer work email (receipt, portal invite, and report-ready notifications).
industry_verticalstringyes–
notesstring––
planstringyes–
revenue_bandstringyes–

No output schema declared.

No examples provided.

draft_brand_from_website ~111

Read a client's website and fill in most of their brand profile automatically. Takes up to a minute or two. The result is a DRAFT: review it with get_brand_profile, correct it with set_brand_profile, then confirm. This is the fastest way to get a new client ready for a May run. Needs the May plan and an X-Mako-Key header.

NameTypeReqDescription
client_account_idstringyesFrom list_clients or create_client.
website_urlstringyesThe client's homepage.

No output schema declared.

No examples provided.

get_brand_profile ~74

Read one client's brand profile: what they sell, who buys it, voice, colors, and the campaign defaults. Also reports whether it is confirmed and, if not, exactly which answers are still missing before May can run. Requires an X-Mako-Key header.

NameTypeReqDescription
client_account_idstringyesFrom list_clients.

No output schema declared.

No examples provided.

get_download_url ~67

Mint a download link for one deliverable. The link works for 10 minutes and then expires, so fetch it when the human is ready to use it rather than in advance. Requires an X-Mako-Key header.

NameTypeReqDescription
deliverable_idstringyesFrom list_deliverables.

No output schema declared.

No examples provided.

get_status ~90

Check one report order or one May run by its id, or omit the id to list the most recent of both. Returns the status and, once finished, the deliverable id to pass to get_download_url. Requires an X-Mako-Key header.

NameTypeReqDescription
client_account_idstring–Narrow the list to one client.
idstring–A report request id or a May run id.

No output schema declared.

No examples provided.

list_clients ~45

List the client workspaces on this account, with the id each other tool needs and whether the client's brand profile is ready for a May run. Requires an X-Mako-Key header.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_creatives ~84

List the ad concepts from a May run: headline, primary text, call to action, compliance status, and a download link for each image. Returns the newest version of each concept. Use the variant_id values with build_paused_campaign. Requires an X-Mako-Key header.

NameTypeReqDescription
run_idstringyesA May run id from get_status or run_may.

No output schema declared.

No examples provided.

list_deliverables ~65

List everything finished and ready to download on this account: competitor report bundles and May run artifacts. Requires an X-Mako-Key header.

NameTypeReqDescription
client_account_idstring–Narrow to one client workspace.
kindstring––
limitinteger––

No output schema declared.

No examples provided.

list_meta_assets ~81

Show the client's connected Facebook ad account and the conversions available to optimize toward. Call this before build_paused_campaign on a leads or sales campaign, because those need a conversion to aim at. Connecting Facebook itself has to be done by a person in the portal. Requires an X-Mako-Key header.

NameTypeReqDescription
client_account_idstringyesFrom list_clients.

No output schema declared.

No examples provided.

list_plans ~82

List Mako Metrics plans with pricing, what's included, scope limits, delivery, guarantee, and links to verify the merchant. Use this to recommend a plan before ordering. Covers the competitor report plans, which are the only products orderable through this server. May, the Meta ads agent, is a monthly engagement bought at makometrics.com/meta-ads-agent.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

order_report ~204

Order a competitor Meta ads report for one competitor. On a Dominator, Agency or May plan this spends one report from the current period's allowance and queues the build. On Snapshot it returns a Stripe checkout link instead. The report is NOT generated on the spot: a person builds it and it is delivered to the portal, typically within 24 hours. Poll get_status, then list_deliverables. Requires an X-Mako-Key header.

NameTypeReqDescription
client_account_idstring–Which client workspace this is for. Get it from list_clients.
competitorstringyesThe competitor's brand name or Meta Ad Library page name. One per order.
competitor_sitestring–The competitor's website.
facebook_pagestring–The competitor's public Facebook page URL.
goalstring–What the customer wants to learn from the report.
marketstring––
notesstring––
titlestring––

No output schema declared.

No examples provided.

run_may ~227

Start a May creative run for one client: research, copy, and eight ad concepts, delivered to the portal for the customer to review and edit. Usually a few minutes. When the brand profile names a competitor May has not researched yet, it reads that competitor's website and Meta ads first, and the run shows status 'researching' for up to about 20 minutes. May builds creative and, separately in the portal, a PAUSED campaign. It never turns anything on and never spends ad budget. The client needs a confirmed brand profile first, which is filled in at makometrics.com/portal. Needs the May plan and an X-Mako-Key header.

NameTypeReqDescription
avoidstring–One thing the creative must not claim or show.
briefstringyesWhat this round is for, in plain language. The campaign, the angle, the buyer.
client_account_idstringyesWhich client workspace to run for. Get it from list_clients.
featurestring–One thing the creative should lead with.
objectivestring––

No output schema declared.

No examples provided.

set_brand_profile ~498

Write or update one client's brand profile. Every field is optional and only what you pass is changed, so this is safe to call repeatedly to correct a website draft. Pass confirm: true when the answers are right, which is what run_may needs. Confirming needs company_name, domain, flagship_product, offer_landing_page, target_customers and both colors. Needs the May plan and an X-Mako-Key header.

NameTypeReqDescription
avoid_claimsstring–Claims the creative must never make.
categorystring––
client_account_idstringyesFrom list_clients.
color_navystring–Primary brand color as hex, for example #1E3A8A.
color_skystring–Accent color as hex.
company_namestring––
competitor_websitesobject–Optional website per competitor, keyed by the name in competitors. Give it for a local business or a common name, so May reads the right one.
competitorsarray–Up to three competitor brands May studies before writing concepts.
confirmboolean–Set true to mark the profile ready for runs.
daily_budgetinteger–Default daily budget in whole dollars.
domainstring–Bare domain, for example acme.com.
flagship_productstring–The main thing to advertise.
image_notesstring–Art direction for the generated images.
known_forstring–The problem they solve.
notesstring––
objectionsstring–What stops people buying.
objectivestring–The default campaign goal for this client.
offerstring–The standing offer, for example 20% off the variety pack.
offer_landing_pagestring–Where the ads should send people.
phone_numberstring–Only used by a calls campaign.
popular_productsarray––
price_rangestring––
proof_pointsarray–Facts the copy is allowed to claim. Nothing outside this list is used.
signature_claimstring–The one thing this brand is known for.
support_emailstring––
target_customersarray–Who buys it. One per entry.
voicestring–How the brand sounds, in a sentence or two.
website_urlstring––

No output schema declared.

No examples provided.

whoami ~70

Show which Mako Metrics account this key belongs to: the plan, how many competitor reports are left in the current period, and the client workspaces on the login. Call this first in any session that will use the customer tools. Requires an X-Mako-Key header from makometrics.com/portal.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

Install

How do I install the Mako Metrics MCP server?

Mako Metrics is a hosted endpoint at https://ufupdlaxddckqxbgbhwu.supabase.co/functions/v1/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 · ufupdlaxddckqxbgbhwu.supabase.co

# add to Claude Code
claude mcp add --transport http com-makometrics-mako-metrics 'https://ufupdlaxddckqxbgbhwu.supabase.co/functions/v1/mcp'
Common questions

What is the Mako Metrics MCP server?

Mako Metrics is an MCP server listed in the public MCP registry as com.makometrics/mako-metrics. Competitor Meta ads intelligence reports. List plans, create orders, Stripe checkout for humans. This page covers its hosted endpoint (https://ufupdlaxddckqxbgbhwu.supabase.co/functions/v1/mcp).

Is the Mako Metrics MCP server safe to use?

Mako Metrics scores 84 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 Mako Metrics MCP server expose?

Mako Metrics exposes 16 tools: list_plans, create_order, whoami, list_clients, order_report, and 11 more. Their descriptions and schemas cost roughly 2,241 tokens of context every time the server is loaded.

Does the Mako Metrics MCP server require authentication?

No. We connected to Mako Metrics without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Mako Metrics MCP server still maintained?

Mako Metrics 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.