mcpm runs on your own machine — the client starts it, so there is no endpoint to ping. 529 installs a week from npm. Last commit 17 Sep 2026.
MCP security guard + package manager: trust-scored installs, blocks prompt injection and rug-pulls.
We read the source, 21 h ago · rules 3dff92dd89df
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.
return path.join(appDataDir(platform, home), "Claude", "claude_desktop_config.json");
const child = spawn(command, [...args], {
…EAmNQYMw1iG70ugdKnQq+wIeMoIZWLv+FX6lMZUiTkr0ECIQDiz4OU6dxPtNNccOF4pHafvCRXc5gvrLFADiFWmdJeYg==\n"}},"canonicalizedBody":"eyJhcGlWZXJzaW9uIjoiMC4wLjEiLCJraW5kIjoiZHNzZSIsInNwZWMiOnsiZW52ZWxvcGVIYXNoIjp7ImFsZ29yaXRobSI6InNoYTI1NiIsInZhbHVlIjoiZWE3MjFhYjA5MGE4MWUyMmNhNTllNzM5Zjg3NjU…
for (const [key, value] of Object.entries(process.env)) {
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 cli -- npx -y @getmcpm/cli
{
"mcpServers": {
"cli": {
"args": [
"-y",
"@getmcpm/cli"
],
"command": "npx"
}
}
}
[mcp_servers.cli]
command = "npx"
args = ["-y", "@getmcpm/cli"]
{
"mcpServers": {
"cli": {
"args": [
"-y",
"@getmcpm/cli"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"cli": {
"args": [
"-y",
"@getmcpm/cli"
],
"command": "npx"
}
}
}
Security middleware for MCP. Blocks prompt injection, PII leakage, and resource exhaustion.
Scan for prompt injection, secrets, PII, and vet MCP servers before installation
Security gateway for MCP agents: blocks prompt-injection-driven tool calls before they execute.
Security layer for AI agents: blocks prompt injection, detects fake packages, scans vulnerabilities.
MCP security scanner: detect tool poisoning, prompt injection & rug-pulls - 10 OWASP heuristics.
Security scanner for MCP servers and skills: Unicode injection, patterns, secrets.
Multi-agent LLM security layer detecting prompt injection and jailbreaks.
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
Answers built from our own checks of this server.