Skip to main content
Glama

Security in the Loop

Offline security feedback for AI coding agents through MCP.

Project idea

Static scanners check the code the agent proposes. Their findings point to specific rules and source locations so the agent can revise the edit before the helper applies the approved bytes.

A proposed edit is scanned, revised from findings when needed, and applied through a checked write when policy allows it.

Related MCP server: CodeMore MCP Server

Quick start

The verified 0.5.0 release candidate uses a macOS ARM64 helper and a Linux ARM64 Docker image. Verified release scope.

Clone this repository and start at its root on an Apple silicon Mac with Docker Desktop. You will prepare the Trivy database and build artifacts locally.

  1. Prepare the pinned scanners and fresh Trivy data, then build the image and helper. Build from source.

  2. Set up a project in Codex and review its project hooks. Setup configures the private MCP URL and runs the scanner services in Docker. Connect Codex.

  3. Ask Codex to create a small file through the checked write path. Check for an applied receipt and acknowledgment. Try one checked edit.

If you have a helper archive and its matching local image, use the local bundle guide.

How it works

The project hook and helper send isolated snapshots to Docker over loopback MCP. The offline worker scans them, and the helper applies approved edits on the host.

A project hook holds a supported edit while the helper captures the worktree. The helper sends isolated baseline and candidate snapshots to the loopback MCP gateway. A worker with networking disabled scans those snapshots. Codex receives findings and can revise the proposal. The helper verifies the current worktree and records a receipt when it applies the approved bytes.

Project folders stay on the host. Downloads happen during explicit preparation or data maintenance. Scans use pinned engines and prepared local data.

The hook boundary is checked_path_only. An exclusive write boundary requires a harness that controls every write path. Architecture.

Scanner coverage

Area

Scanners

Source code

Semgrep CE, Bandit, Gosec

Secrets

Gitleaks, TruffleHog

Dockerfiles

Hadolint

Infrastructure configuration

Trivy, Checkov, KICS

Supported dependency inventories and image archives

Trivy

Scanner API keys and database servers are unnecessary. Unsupported inputs, scanner failures, and missing, stale or corrupt required data are explicit errors. Supported inputs and policy.

Development and verification

License

Copyright 2026 sathwikv143. The project's original source is licensed under Apache 2.0. The scanner tools have their own license terms. Project license · Upstream scanner notices

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI agents to scan GitHub repositories for security vulnerabilities, deployment blockers, and code quality issues. It provides detailed findings and auto-generated code patches to help developers ensure their code is production-ready.
      40 npm
      MIT
    • A
      license
      A
      quality
      B
      maintenance
      Enables AI coding agents to run fast, sandboxed pre-flight validation—tests, type-checking, linting, security audits, Git safety scans, and fix suggestions—before committing or pushing code, with instant caching and optional Docker isolation.
      10
      12 npm
      MIT
    • F
      license
      Not graded
      quality
      B
      maintenance
      Enables AI coding assistants to scan every file they write before it reaches disk, blocking CRITICAL and HIGH security findings at generation time. Covers secrets, GitHub Actions AI-agent surfaces, prompt injection, Docker, Terraform, and package supply-chain risks.
      47 PyPI
      2
      -