Frisk runs on your own machine — the client starts it, so there is no endpoint to ping. 43 installs a week from npm. Last commit 30 Oct 2026.
Screen the counterparty of an x402 payment before an agent pays it. Runs offline by default.
We read the source, 3 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
proc = subprocess.run(
os.path.join(HERE, os.pardir, "mcp-dependency-census", "npm_stdio.json"),
COPY package.json pnpm-lock.yaml pnpm-workspace.yaml .npmrc ./
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add frisk -- npx -y frisk-mcp
{
"mcpServers": {
"frisk": {
"command": "npx",
"args": [
"-y",
"frisk-mcp"
]
}
}
}
[mcp_servers.frisk]
command = "npx"
args = ["-y", "frisk-mcp"]
{
"mcpServers": {
"frisk": {
"command": "npx",
"args": [
"-y",
"frisk-mcp"
]
}
}
}
{
"servers": {
"frisk": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"frisk-mcp"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
FRISK_API_KEY (Hosted API key. Without it the server screens entirely offline), FRISK_BASE_URL (Override the hosted endpoint. Defaults to https://api.tryfrisk.dev).
What the chain records about an address before you pay it, and whether a payment fits it.
Check a payee before your agent pays: sanctions, lookalike domains, payment details, invoice fraud.
Check tokens, pages and x402 payments before your agent trusts them. Offline verdicts.
Pre-send risk check for AI agents that move money — screen an address or payment URL before sending.
Check x402 endpoint reliability on Algorand before an agent routes a payment there.
Verify x402 payment endpoints before an AI agent pays: scam scan, on-chain checks, trust scores.
Offline scam check for agents: verify links and payments before acting (allow, ask or deny).
Check stablecoin and x402 payments before an AI agent pays: approve, hold or reject.
Answers built from our own checks of this server.