$ loading_
Protect AI agents with scans for injections, leaks, risky URLs, and passwords.
Copy the install command and let the AI configure it · recommended for beginners
Please install the "io.github.mlawsonking/agent-firewall-mcp" MCP server from askskill: Run: claude mcp add 'io-github-mlawsonking-agent-firewall-mcp' -- npx -y agent-firewall-mcp
Scan AI-generated code for injections, secrets, SSRF, and risky patterns.
Check payment addresses or URLs for risk before AI agents send money.
Provide deterministic web reading, scraping, RSS, DNS, and SSL checks for AI agents.
Scan inbound and outbound emails for prompt injection, phishing, and secret leaks.
Verify package safety for AI coding agents and detect supply-chain risks.
All six agent guard suites in one local MCP server, with optional cloud intelligence.
Scan prompts and tool inputs to block prompt injection risks.
Detect prompt injections and jailbreaks to secure LLM applications and workflows.
Secure AI agents locally with cost controls, injection blocking, and action approvals.
Scan agent-generated code for vulnerabilities, prompt injection, and semantic security issues.
Add authorization, delegation, provenance, and audit controls to AI agents.
Provides OWASP-oriented security capabilities for AI agents and MCP workflows.