MCP Gateway Scan runs on your own machine — the client starts it, so there is no endpoint to ping. 58 installs a week from npm. Last commit 15 Jul 2026.
Read-only MCP/agent-gateway readiness scanner — scores a repo across 7 security dimensions.
We read the source, 20 h ago · rules 3dff92dd89df
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
/\b(promptfoo|garak|pyrit|red[_-]?team|jailbreak|injection[_-]?test|eval(?:uation)?[_-]?(?:gate|suite)|refusal[_-]?rate)\b/i;
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.
/\b(promptfoo|garak|pyrit|red[_-]?team|jailbreak|injection[_-]?test|eval(?:uation)?[_-]?(?:gate|suite)|refusal[_-]?rate)\b/i;
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch MCP Gateway Scan and you get told the day something new turns up.
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 mcp-gateway-scan -- npx -y mcp-gateway-scan
{
"mcpServers": {
"mcp-gateway-scan": {
"args": [
"-y",
"mcp-gateway-scan"
],
"command": "npx"
}
}
}
[mcp_servers.mcp-gateway-scan]
command = "npx"
args = ["-y", "mcp-gateway-scan"]
{
"mcpServers": {
"mcp-gateway-scan": {
"args": [
"-y",
"mcp-gateway-scan"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"mcp-gateway-scan": {
"args": [
"-y",
"mcp-gateway-scan"
],
"command": "npx"
}
}
}
35-probe LLM/agent security red-team scan (injection, jailbreak, MCP abuse) with report.
Agent supply-chain security, scanner consensus, x402 reliability, and commerce MCP tools.
A shared team wiki your coding agents read and write — across every repo and every MCP client.
Project memory across sessions for AI agents. A queryable decision log in the repo.
Read-only MCP server: your agent sees all your sibling repos but structurally cannot touch them
Read-only IBKR MCP: account, positions, brief, regime, stress, reporting, Edge, and risk.
FinishKit MCP: scan GitHub repos for security vulnerabilities, deployment blockers, and quality
Scan any public GitHub MCP-server repo for security issues. 37 MCP-specific L1 rules, 8 languages.
Answers built from our own checks of this server.