SUNGLASSES
Input firewall for AI agents: scan text and files before they're read. Local, no network by default.
Description from the maker (original English)
Prompt-injection shield for agents: read pages, scan content, audit MCP servers and skills. x402.
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.
PSS_PRIVATE_KEY, PSS_MAX_SPEND_USDValues marked secret are keys to your account. Never share them or paste them into a chat.
You need
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
https://api.powerstripsecurity.workers.dev/mcpOpen Claude Desktop → Settings → Developer → Edit Config, and paste this into claude_desktop_config.json
{
"mcpServers": {
"power-strip-security": {
"command": "npx",
"args": [
"-y",
"power-strip-security-mcp"
],
"env": {
"PSS_PRIVATE_KEY": "your-value",
"PSS_MAX_SPEND_USD": "your-value"
}
}
}
}Run this in your terminal
claude mcp add --transport http power-strip-security https://api.powerstripsecurity.workers.dev/mcpclaude mcp add power-strip-security --env PSS_PRIVATE_KEY=your-value --env PSS_MAX_SPEND_USD=your-value -- npx -y power-strip-security-mcpFill in the empty values before running it.
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"power-strip-security": {
"url": "https://api.powerstripsecurity.workers.dev/mcp"
}
}
}Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"power-strip-security": {
"command": "npx",
"args": [
"-y",
"power-strip-security-mcp"
],
"env": {
"PSS_PRIVATE_KEY": "your-value",
"PSS_MAX_SPEND_USD": "your-value"
}
}
}
}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": {
"power-strip-security": {
"type": "http",
"url": "https://api.powerstripsecurity.workers.dev/mcp"
}
}
}Paste into .vscode/mcp.json in your project
{
"servers": {
"power-strip-security": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"power-strip-security-mcp"
],
"env": {
"PSS_PRIVATE_KEY": "your-value",
"PSS_MAX_SPEND_USD": "your-value"
}
}
}
}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.
ChatGPT connects only to servers on the internet:
https://api.powerstripsecurity.workers.dev/mcpMenu names can differ slightly by plan and over time.
Your choice stays on this device in a cookie; no account needed.
PSS_MAX_SPEND_USD envThese settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
Tool names and descriptions exactly as the server reported them on Nov 6, 2026. The maker wrote them, not us; we show them as plain text.
read_urlFetch a public web page or PDF with hidden text and exfiltration links removed, plus a prompt-injection report. Use it instead of fetching untrusted URLs yourself; for content you already have, use check_prompt_injection. Returns risk (0-1), level, findings, content and wrapped_t
check_prompt_injectionScan HTML or text you already have (an email, a document, a tool result, a page fetched elsewhere) for prompt injection before it reaches your prompt. To fetch a URL, use read_url instead; for MCP tool definitions or skill files, use audit_mcp_server or audit_agent_skill. Returns
audit_mcp_serverCheck an MCP server for tool poisoning before connecting: hidden instructions, sensitive-file access, exfiltration parameters, cross-tool shadowing, rug pulls. For skills or AGENTS.md use audit_agent_skill. Give url (tools are listed read-only, never called) or the pasted tools,
audit_agent_skillCheck an agent skill (SKILL.md with its scripts and references) or AGENTS.md, CLAUDE.md, .cursorrules before loading it: prompt injection, curl | bash, encoded commands, credential theft, exfiltration, hardcoded keys, persistence. For MCP servers use audit_mcp_server. Give files
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 9, 2026
The publisher (AlbertBalestrini) is not the repo owner (AlbertBalestrini); someone else may have listed it
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
Responded in 150 ms (HTTP 200)
No sign-in needed
Read 4 tool descriptions and found no hidden instructions to the AI
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
It passed 2 of 3 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.
You need to fill in: PSS_PRIVATE_KEY
Either way works: install it on your computer or connect to the cloud version.
The GitHub repo last changed –, and the latest version (0.2.0) reached the registry 9 days ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
In the same category: SUNGLASSES, KillerSkills, Draugr
Servers in the same category from other makers, sorted by stars.
Reading a card:↓ Downloads per weeki★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Input firewall for AI agents: scan text and files before they're read. Local, no network by default.
Security verdicts for agent skills and MCP servers, from sandbox runs, before you install them.
Security scanning for AI agents: SAST, SCA, secrets, IaC, DAST, ranked by real risk.
No README found in the repo