Arcwall Security runs on your own machine — the client starts it, so there is no endpoint to ping. 41 installs a week from npm. Last commit 7 May 2026.
Security scanning for AI coding tools. Detects secrets, threat models, and runs pre-commit checks.
What the code does
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.
const fullPath = path.join(scanPath, file);
entries = fs.readdirSync(dir, { withFileTypes: true });
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
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.
Connect this server
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 arcwall-security -e 'ARCWALL_API_KEY=<ARCWALL_API_KEY>' -- npx -y @arcwall/mcp-server{
"mcpServers": {
"arcwall-security": {
"command": "npx",
"args": [
"-y",
"@arcwall/mcp-server"
],
"env": {
"ARCWALL_API_KEY": "<ARCWALL_API_KEY>"
}
}
}
}[mcp_servers.arcwall-security]
command = "npx"
args = ["-y", "@arcwall/mcp-server"]
env = { ARCWALL_API_KEY = "<ARCWALL_API_KEY>" }{
"mcpServers": {
"arcwall-security": {
"command": "npx",
"args": [
"-y",
"@arcwall/mcp-server"
],
"env": {
"ARCWALL_API_KEY": "<ARCWALL_API_KEY>"
}
}
}
}{
"servers": {
"arcwall-security": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@arcwall/mcp-server"
],
"env": {
"ARCWALL_API_KEY": "<ARCWALL_API_KEY>"
}
}
}
}Put your own value in place of
<ARCWALL_API_KEY> (Your Arcwall API key from arcwall.io/app.html).
The author’s registry entry marks it as required.
Alternatives to Arcwall Security
same job, measured the same waySecurity scanning and threat detection for AI agents
AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.
Security tools for your AI: scan, pentest, check headers, guard code and scan repos for secrets.
Real-time semantic security for AI coding agents and MCP tools
Security scanner for MCP servers - detects tool poisoning and injection
AI security layer: code scanning, PII detection, prompt injection, secrets, CVEs
The local security layer for coding agents: secret redaction, injection checks and an MCP proxy.
AI security scanning and trust scoring. Stack-specific threat models. Free local scan.
Arcwall Security — questions
Answers built from our own checks of this server.