SML Risk Firewall
Pre-trade risk checks for agent trades: orders vs your limits, signed receipts.
Description from the maker (original English)
Fetch a URL's response headers and grade CSP, HSTS, X-Frame-Options and related security headers.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Open Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"security-headers": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/basitalisandhu/mcp-security-headers:0.3.0"
]
}
}
}Run this in your terminal
claude mcp add security-headers -- docker run -i --rm ghcr.io/basitalisandhu/mcp-security-headers:0.3.0Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"security-headers": {
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/basitalisandhu/mcp-security-headers:0.3.0"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Paste into .vscode/mcp.json in your project
{
"servers": {
"security-headers": {
"type": "stdio",
"command": "docker",
"args": [
"run",
"-i",
"--rm",
"ghcr.io/basitalisandhu/mcp-security-headers:0.3.0"
]
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
This one runs on your computer, and ChatGPT can only connect to servers on the internet. Pick another app.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Runs on your computer; the tool list appears in your AI app after you install it.
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 7, 2026
The registry name was verified with the GitHub account basitalisandhu, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (0.3.0) reached the registry 10 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. You also need Docker on your computer.
In the same category: SML Risk Firewall, ipdata MCP by usefulapi, MaxMind minFraud MCP by usefulapi
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Pre-trade risk checks for agent trades: orders vs your limits, signed receipts.
Look up location, network, company and threat data for IP addresses and ASNs in ipdata.
MCP server for MaxMind minFraud — score transactions for fraud risk from your AI assistant.
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
Fetches a public URL's response headers and grades Content-Security-Policy, Strict-Transport-Security, X-Frame-Options, X-Content-Type-Options, Referrer-Policy, Permissions-Policy, the Cross-Origin-* headers, Set-Cookie attributes and information-disclosure headers, with an explanation and a recommendation per header. The response body is never downloaded.
Part of dev-mcp-servers. Stdio transport only; the server never opens a port.
| Tool | Input | What it returns |
|---|---|---|
check_url_headers | url, method? (HEAD or GET), max_redirects? (0 to 10, default 5) | HEAD request (GET on 405/501) to a public http(s) URL, redirects followed with the same checks on every hop, then a graded report. Refuses localhost, .local, .internal, private, loopback, link-local, CGNAT and cloud-metadata addresses, including names that resolve to them. |
grade_headers | headers (object), https? | The same grading for headers you already have, for example from curl -I. No network. |
explain_header | header | Purpose, recommended value and reference for one header. |
Claude Code:
claude mcp add security-headers -- docker run --rm -i ghcr.io/basitalisandhu/mcp-security-headers:0.3.0
Add -s user to make it available in every project. Any client that reads .mcp.json (Claude Code, Claude Desktop, Cursor):
{
"mcpServers": { "security-headers": { "command": "docker", "args": ["run", "--rm", "-i", "ghcr.io/basitalisandhu/mcp-security-headers:0.3.0"] } } }
Pin the version as shown so that an update cannot change what runs in your editor without you noticing. The package is not on npmjs.com yet, so npx does not work; see the repository README for GitHub Packages npm. From a checkout, use "command": "node", "args": [" /packages/security-headers/dist/index.js"] after npm install && npm run build at the repository root.
max_redirects hops, each validated. 10 s timeout per request. The host is resolved and every address checked before connecting; this does not defeat DNS rebinding between the check and the connection, so do not point the tool at hosts you do not trust to answer honestly. No telemetry.*. Disabled () and explicit origin allowlists retain the points; this is a heuristic, not a full browser policy validator.npm install # at the repository root
npm run build -w @basitalisandhu/mcp-security-headers npm test -w @basitalisandhu/mcp-security-headers
Tests use node:test and the SDK's in-memory transport; they do not reach the network.
MIT. See LICENSE.