Reviews the code, the identities and the exposure of one service, and writes down what it found rather than a score.
Built for: The engineer given a week to answer whether a service is safe enough to put in front of customers.
The button opens the checkout, where 6 servers and 4 skills are listed one by one with what each does to the bill — free, already yours, monthly or a one-off licence. Nothing is charged until you confirm it there, in Stripe’s own card frame on that page rather than a redirect, and each paid member keeps its own budget cap.
The reason to buy a stack rather than five listings: each line below needs more than one member connected at the same time.
Scan an MCP server's own source for secrets, injection risk and misconfiguration before it is added to anything.
Review authentication and authorisation code statically — session handling, identity checks, permission gaps.
Look up an attacker technique in MITRE ATT&CK and check whether the detection for it exists at all.
Check an address against AbuseIPDB when a log line raises the question of who that was.
What each part contributes, and why it was picked over the obvious alternative. Prices and permissions are read from the listings, so nothing here can disagree with the catalogue.
Scans MCP servers for vulnerabilities, secrets, injection risk and misconfiguration — the check that belongs before an install, not after.
MITRE ATT&CK lookups and detection-coverage analysis, so a review talks about named techniques instead of adjectives.
Checks the reputation of an address from inside the review, which is the question a suspicious log line always raises next.
The code under review, its history and the merge request the findings will be attached to.
Read-only access to see what data the service can actually reach — the difference between a theoretical exposure and a real one.
The public surface as DNS presents it: what resolves, what points where, and which record nobody remembers creating.
A static review specifically for authentication and authorisation flaws, which is where most real findings in an application review come from.
Turns the dependency audit into the specific upgrades, so the supply-chain half of the review ends with actions.
Installs the external repository scanner from a pinned, reviewable commit — a supply-chain habit worth having in a security desk of all places.
Answers what breaks if this changes, which is what turns a finding into a fix somebody is willing to merge.
Every member is a subscription or a licence bought once, so the monthly figure is a price rather than an estimate: what moves it is adding or dropping a member, not how hard the stack is worked. The one assumption is that a one-off licence is spread over a year so it can sit in the same column as a subscription.
| Part | What you are paying for | Monthly, as quoted |
|---|---|---|
| Security Auditor | from $19/mo | $19/mo |
| Mitre | Free | — |
| Abuseipdb | Free | — |
| Gitlab | Free | — |
| Postgres | Free | — |
| Cloudflare DNS | Free | — |
| Skills | ||
| Auth Review | $49 · $4.08/mo over 12 months | $4.08/mo |
| Audit Dependencies | $69 · $5.75/mo over 12 months | $5.75/mo |
| repo-scan | $15 · $1.25/mo over 12 months | $1.25/mo |
| Impact Analysis with GitNexus | Free · context cost only | — |
| Everything above | $19 of servers plus $11 of skills, the same in a quiet month and a busy one | $30/mo |
Subscriptions at their monthly plan price; one-off licences spread over 12 months. One-off purchases in this stack total $133 — Auth Review $49, Audit Dependencies $69, repo-scan $15 — paid once and spread here so they sit in the same column as a subscription. Everything arrives on one mcprush invoice, taken by Stripe from the card on your account, not one per publisher — mcprush.com is the merchant of record and each publisher is paid out of it.
Install only these and the bill is nothing: 5 servers and 1 skill, 39 of the 43 tools.
Left out, and what goes with it:
Security Auditor at from $19/mo. Each of those plans states the calls it includes in a month, and running past one never arrives as a larger invoice: the gateway refuses the call over the allowance and returns an MCP error naming the plan. The figure above is what the stack costs in a busy month as well as a quiet one — what a heavy month changes is which plan you need, not what this one bills.
Budget caps are set per install and enforced at the gateway, so a retry loop is refused at the cap rather than left to run through an allowance overnight.
One step per part, in the order they are useful: connect what the work reads before what it writes, and install the skills that decide how the work is done last. Each step is a command you can read before you run it.
npx mcprush@latest stack add sec-reviewNothing in this stack installs from one command today: 10 members are either paid, run from its own source, or a skill with its own command — the steps above name each one. Nothing is connected until you approve it.
Installed together, these tool surfaces add up. It is the first thing a security reviewer asks for, so what has been counted — and what nobody has counted yet — is on the page rather than in a PDF.
| Member | Tool surface | Write tools |
|---|---|---|
| Abuseipdb | not imported | not recorded |
| Cloudflare DNS | not imported | not recorded |
| Gitlab | not imported | not recorded |
| Postgres | not imported | not recorded |
A stack's blast radius is the union of its members, not the worst of them. That union cannot be taken here, because 4 members of 6 have no imported tool surface — so the figure a review asks for is missing rather than low, and a member marked not imported is one nobody has counted rather than one that cannot write.
A stack is a default, not a verdict. These are the substitutions the maintainer would make, and what each one costs or saves.
A second scanner over the same package, with different engines behind it; run it when a finding needs a second opinion rather than instead of the first.
The same review against a repository hosted on Bitbucket, for teams whose code never moved to GitLab.
Written by the maintainer, kept on the page rather than in a support thread.
It is not a penetration test. Everything here reads code, configuration and public reputation data — nothing here attacks a running system.
It cannot revoke anything. Findings come out as text; changing a role, a key or a rule stays with whoever owns it.
A clean pass here is not a certification. The MCP scanner covers MCP servers, the auth review covers your code, and neither speaks for the other.
A stack has an owner: whoever keeps it re-checks the combination when a member changes, and the members themselves are published by the people named on each row.
Writes the migration, proves it on a branch, and says what it will do to the table before it touches the real one.
Designs the endpoint, wires the auth and the payment, and reviews the shape before it is public and permanent.
Takes a green branch to a running deployment, and keeps the DNS, the cluster and the access list honest on the way.