SocketlistSecurity / agent-firewall-mcp
agent-firewall-mcp
io.github.mlawsonking/agent-firewall-mcp · v1.3.0
Input/output safety for AI agents: known-pattern injection and obfuscation scan, URL/IP, secrets.
Install
npx -y agent-firewall-mcpTypical command from the package name. Check the README for required configuration and credentials before connecting it to real data.
Signals
| GitHub stars | 1 |
| npm weekly downloads | 72 |
| Last push | 1d ago |
| Licence | MIT |
| Open issues | 0 |
| SECURITY.md | No |
| Language | JavaScript |
| Latest version published | 2026-08-10 |
Signals captured from GitHub, npm and the official MCP Registry on October 15, 2026. See the scoring method.
Similar servers
SUNGLASSES
Score 80Input firewall for AI agents: scan text and files before an agent reads them. Local, no network.
prompt-protection
Score 85Scan prompts, tool definitions and model output for injection, and guard agent tool calls.
email-guard-mcp
Score 71Email safety for AI agents: scan inbound for prompt-injection/phishing + outbound for secret leaks.