Skip to content
secure-mcp
Esc
navigateopen⌘Jpreview
On this page

secure-mcp

Defensive, agent-first security audits over MCP: scope repositories, route stack-aware guidance, and produce structured remediation findings.

read-only by design stdio transport

Security review that agents can carry forward

secure-mcp gives coding agents a small, structured toolkit for defensive code review. It inventories a repository, detects its stack, loads only the knowledge packs it needs, and turns likely weaknesses into remediation-ready findings.

The server is intentionally local. It reads files under an approved project_root, never executes the target project, and keeps stdout reserved for MCP JSON-RPC.

The operating model

Scope first

Start with project structure and architecture so scans stay bounded and stack-aware.

Remediate clearly

Every finding carries evidence, classification, impact, remediation, residual risk, and verification.

Verify before reporting

Heuristics are candidates. Agents confirm data flow before treating a signal as a finding.

What it covers today

Surface Coverage
Web TypeScript, Next.js App Router, API handlers, cookies, CSRF, and NEXT_PUBLIC_ exposure
Apple platforms Swift, SwiftUI, Keychain, ATS, WebView bridges, deep links, and macOS controls
React Native Expo config, SecureStore, OTA boundaries, deep links, and token storage
Cross-cutting Authentication, injection risks, secrets, threat modeling, and report rollup

Read the design notes

Understand the process boundaries, filesystem policy, progressive knowledge packs, and extension points.

Was this page helpful?