Adds security scanning directly into your AI coding workflow through seven specialized tools. Scan for hardcoded secrets, check MCP configurations for vulnerabilities, analyze CLAUDE.md and .cursorrules files for security issues, and run dependency CVE checks. Also includes STRIDE threat modeling, prompt injection testing, and pre-commit hooks. Requires a free API key from arcwall.io and works with Claude Code, Cursor, Windsurf, or any MCP-compatible editor. Reach for this when you want continuous security checks without leaving your AI assistant, especially useful for catching secrets before they hit version control or validating agent instruction files.
Security scanning for Claude Code, Cursor, Windsurf, and any MCP-compatible AI coding tool.
Get your free API key at https://arcwall.io
Add to your MCP config:
Claude Code (~/.claude/mcp.json):
{
"mcpServers": {
"arcwall": {
"command": "npx",
"args": ["@arcwall/mcp-server"],
"env": { "ARCWALL_API_KEY": "your-key-here" }
}
}
}
Cursor (.cursor/mcp.json): Same config. Windsurf: Add via MCP settings panel.
arcwall_scan_secrets — hardcoded credentialsarcwall_scan_mcp — MCP config vulnerabilitiesarcwall_scan_agent_instructions — CLAUDE.md, .cursorrules securityarcwall_threat_model — STRIDE analysisarcwall_check_prompt — prompt injection testingarcwall_pre_commit — pre-commit security checkarcwall_scan_dependencies — known CVEs in packagesAsk your AI assistant:
ARCWALL_API_KEY*secretYour Arcwall API key from arcwall.io/app.html
com.exploit-intel/eip-mcp
dmontgomery40/pentest-mcp
pantheon-security/notebooklm-mcp-secure
cyanheads/pentest-mcp-server
io.github.akhilucky/ai-firewall-mcp