Agent Firewall Mcp
- Updated July 5, 2026
- mlawsonking/MCP
Input/output safety layer for agents: prompt-injection scanning, URL/IP reputation checks, pwned-password lookups, and PII scanning.
About
Agent Firewall MCP is an input/output safety layer for AI agents. It scans for prompt-injection, checks URLs and IPs against reputation data, looks up pwned passwords, and detects PII flowing through the agent. A solo builder shipping an autonomous agent wires it in as a general firewall so untrusted input and sensitive output are screened at every turn.
- Prompt-injection scanning
- URL and IP reputation checks
- Pwned-password lookups
- PII detection on I/O
Agent Firewall Mcp by the numbers
- Data as of Jul 7, 2026 (Skillselion catalog sync)
claude mcp add agent-firewall-mcp -- npx -y agent-firewall-mcpAdd your badge
Show developers this MCP server is listed on Skillselion. Paste this into your README.
| Package | agent-firewall-mcp |
|---|---|
| Transport | STDIO |
| Auth | None |
| Last updated | July 5, 2026 |
| Repository | mlawsonking/MCP ↗ |
What it does
Input/output safety layer for agents: prompt-injection scanning, URL/IP reputation checks, pwned-password lookups, and PII scanning.
Who is it for?
General guardrails on an autonomous agent
Skip if: Network-level infrastructure firewalling
What you get
- input/output safety verdict
Recommended MCP Servers
1Claw VaultHSM-backed vault secrets for AI agents (JIT fetch) plus prompt-injection and threat scanning.2
1passwordMCP server for 1Password service accounts — tools and resources for vaults and credentials18
402sentinel McpAssess an x402 counterparty's risk BEFORE paying: allow/review/block, scored on-chain (Base).1
A2adependencyinspector McpRemote MCP for A2A dependency inspector MCP, structured receipts, audit logs, and reviewer-ready evi
A2a Governance Bridge McpA2A Governance Bridge MCP server.A2aidentitytoll McpRemote MCP for A2A caller identity, scope policy, verdict receipts, and audit history.