Agent Firewall MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 107 installs a week from npm. Last commit 1 Nov 2026.
Input/output safety for AI agents: known-pattern injection and obfuscation scan, URL/IP, secrets.
We read the source, 23 h ago · rules 995398eba69f
Found in continuous integration, deployment or infrastructure files, or in a neighbouring package of the same monorepo. None of this is installed when you add the server: it describes how the project is built and released. We list it because a leaked key in a build pipeline is still a real problem, but it is not something this server does on your machine.
const r = spawnSync(comspec, ['/d', '/s', '/c', line], {
out.innerHTML = head + "\n\n" + JSON.stringify(j,null,2);
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Today is the operative word: we check Agent Firewall MCP every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 agent-firewall-mcp -- npx -y agent-firewall-mcp
{
"mcpServers": {
"agent-firewall-mcp": {
"command": "npx",
"args": [
"-y",
"agent-firewall-mcp"
]
}
}
}
[mcp_servers.agent-firewall-mcp]
command = "npx"
args = ["-y", "agent-firewall-mcp"]
{
"mcpServers": {
"agent-firewall-mcp": {
"command": "npx",
"args": [
"-y",
"agent-firewall-mcp"
]
}
}
}
{
"servers": {
"agent-firewall-mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"agent-firewall-mcp"
]
}
}
}
Email safety for AI agents: scan inbound for prompt-injection/phishing + outbound for secret leaks.
Security firewall for AI agents — scans MCP calls for injection, secrets, and risks.
Security scanner for AI agents: prompt injection, leaked secrets, PII, and SSRF-risk URL detection.
Security scanner for MCP servers and skills: Unicode injection, patterns, secrets.
AI agent security: 7 MCP tools for injection detection, PII scanning, command safety, DLP.
HSM-backed vault secrets for AI agents (JIT fetch) plus prompt-injection and threat scanning.
Scans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection
Scans code for insecure LLM/AI integration: exposed keys, unsafe output, prompt injection
Answers built from our own checks of this server.