About io.github.mlawsonking/agent-firewall-mcp
io.github.mlawsonking/agent-firewall-mcp is an MCP server in the Cloud category: input/output safety for AI agents: prompt-injection scan, URL/IP check, pwned passwords, PII scan.
Install
claude mcp add io-github-mlawsonking-agent-firewall-mcp -- npx -y agent-firewall-mcpnpx -y agent-firewall-mcpThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (5)
Agent FirewallUntrusted input: 11 injection/jailbreak patterns, 5 hidden-text signals, 22 secret and 3 PII patterns, URL and IP reputation
Parameters not published.
Code GuardAI-generated code: 31 regex rules across 12 categories (injection, SSRF, weak crypto, unsafe deserialization, XSS), plus the shared secret patterns
Parameters not published.
Email GuardInbound mail for the same injection patterns plus phishing signals, outbound for secret leaks and deliverability
Parameters not published.
Package GuardA package before install: does it exist (slopsquat), OSV vulns and malware advisories, typosquats
Parameters not published.
Payment GuardA payee before sending: OFAC EVM address lists, scam lists, honeypot simulation, ENS resolved then screened
Parameters not published.
Ask AI
Ask AI about io.github.mlawsonking/agent-firewall-mcp
Powered by Claude · Grounded in docs
Security checks
6 checks have not been run yet.