import { CodeBlock } from '@/components/code-block'; import { pageMetadata } from '@/lib/seo'; import Link from 'next/link'; export const metadata = pageMetadata({ title: 'Security', description: 'How BuildMyMCPServer secures your MCP servers — per-server Docker isolation, AES-256-GCM encrypted secrets, OAuth 2.1 and a hardened control plane.', path: '/security', }); const PILLARS = [ { title: 'Per-server isolation', body: 'Every customer MCP server runs in its own Docker container. No shared process, no shared filesystem, no shared memory. One server compromised does not affect any other.', }, { title: 'Encrypted secrets', body: 'API keys and credentials are AES-256-GCM encrypted at rest in Postgres with a 32-byte key sourced from env. Decryption happens only at the moment of container ENV injection. Plaintext is never logged.', }, { title: 'OAuth 2.1, no API keys for end users', body: 'Every generated server is an OAuth 2.1 Resource Server. PKCE, Dynamic Client Registration (RFC 7591), Resource Indicators (RFC 8707), RS256-signed JWTs. Short-lived, audience-bound, replay-resistant.', }, { title: 'No token passthrough', body: "When a tool calls a downstream API, it uses its own server-side credentials — not the user's OAuth token. Tokens never leak across trust boundaries. This is mandated by the MCP authorization spec.", }, { title: 'Static security checks', body: 'Every LLM-generated tool body is scanned for banned patterns (eval, new Function, child_process) before Docker build. Prompt-injection markers like "ignore previous instructions" also trip the check. Build fails fast, no risky code ships.', }, { title: 'Container hardening', body: 'Production containers run with --read-only, --cap-drop=ALL, --security-opt=no-new-privileges, CPU and memory limits. Network egress can be restricted to whitelisted domains per server.', }, { title: 'Audit log', body: 'Every privileged action — login, logout, server create/iterate/delete — is recorded with IP, timestamp, user, and metadata. Available via /audit for Team-and-above orgs.', }, { title: 'Rate limiting', body: 'Default 100 requests/min/IP per tool, enforced at the Traefik layer before traffic ever reaches your container. Daily preview + build caps per tier protect against runaway LLM spend.', }, { title: 'AI provider by tier — transparent', body: "Hobby (free) tier uses Zhipu's GLM model (servers in China) for prompt analysis — chosen for cost so we can offer a real free tier. Pro, Team and Enterprise use Anthropic Claude (US). Enterprise can request EU-only data residency. The provider is shown live in the wizard so you always know where your prompt is going.", }, ]; export default function Security() { return (
We host code generated by an LLM, on behalf of customers, that exposes their internal APIs to AI clients. The threat model is real. Here is what we do about it.
{p.body}
Found a vulnerability? Email{' '} security@buildmymcpserver.com {' '} with a clear reproduction. We respond within 48h. We do not run a paid bounty yet, but we will credit you publicly in the changelog (or anonymously if you prefer).
SOC 2 Type I is targeted for Q4 2026. The GDPR posture is described in our{' '} privacy policy . If you need a DPA or other contracts ahead of SOC 2, reach out — Team and Enterprise customers get one on request.