Skip to content
mcp/harbor
Verified official

agent firewall mcp MCP

v1.3.0

io.github.mlawsonking/agent-firewall-mcp

Input/output safety for AI agents: known-pattern injection and obfuscation scan, URL/IP, secrets.

transport:stdio runtime:npm
View source

Target client

run in your project directory 

claude mcp add agent-firewall-mcp -- npx -y agent-firewall-mcp

Adds it for this project only. Append --scope user to make it available everywhere. Claude Code docs

This listing does not declare its tools. Connect the server and your client will discover them on the handshake.