Product · MCP Server
Plug Vezraa into Claude Desktop, Cursor, or any MCP-compatible client. Your agent calls the scanner, reads structured findings, and ships fixes — without leaving the chat.
How it works
From your dashboard. Scoped to your projects, revocable any time.
A single block in claude_desktop_config.json, cursor.json, or your client of choice.
Natural language. "Scan staging.myapp.com" — the agent picks the right tool and runs it.
Structured results land back in the conversation. Fix, dismiss, or re-run — all in chat.
Why it works
Claude Desktop, Cursor, Windsurf, Continue, Codex CLI. Anything that speaks MCP.
All scanner endpoints exposed as MCP tools. Findings, scores, and project metadata are queryable.
Run the MCP server locally against your own Vezraa API key for full control.
Long scans stream progress so the agent stays responsive — no silent 90-second waits.
Drop-in config
Works with Claude Desktop, Cursor, Windsurf, and any MCP client.
{
"mcpServers": {
"Vezraa": {
"command": "npx",
"args": ["-y", "@vezraa/mcp"],
"env": {
"Vezraa_API_KEY": "va_live_..."
}
}
}
}Claude Code one-liner: claude mcp add Vezraa npx @vezraa/mcp
Vezraa_scanFull production-readiness scan. Returns score + all findings across 17 categories.Vezraa_check_headersCheck which security headers are missing or misconfigured.Vezraa_check_dnsCheck SPF, DKIM, DMARC, and MX records for a domain.Vezraa_check_rlsTest if your Supabase tables are publicly readable.Vezraa_get_reportFetch a previous scan report by ID.