npmargus-codescan

React, Next.js, Node — SCA, SAST, secrets. argus-codescan bin only (no name collision).

npm install -D argus-codescan
npx argus-codescan scan all .

npmjs.com

pipargus-scan

Full CLI + MCP server. SAST, DAST, SCA, IaC, Terraform, Ansible.

pip install "argus-scan[all-tools]"
argus scan all /path/to/project

pypi.org

pipargus-languages

Java, PHP, Flutter, Terraform, Ansible — bundled rules, no external tools.

pip install argus-languages
argus-languages scan /path/to/project

pypi.org

goargus

Single binary CLI — spawns the Python MCP core.

go install github.com/argus-code-scanning/argus-codescan-mcp/packages/go/cmd/argus@latest

packages/go

dockerghcr.io/argus-code-scanning/argus-codescan-mcp

All scanners bundled. MCP server or one-shot CLI scan. Pinned KICS.

docker pull ghcr.io/argus-code-scanning/argus-codescan-mcp:latest
docker run --rm -v "$(pwd):/workspace" \
  ghcr.io/argus-code-scanning/argus-codescan-mcp scan all /workspace

Docker guide

vscodeArgus Security Scanner

VS Code extension — inline diagnostics, MCP Content-Length framing.

# Install from VS Code Marketplace
# Search: Argus Security Scanner

Extension

MCP configuration

Works with any MCP client via stdio — not limited to a single IDE.

Add to your MCP config (e.g. ~/.cursor/mcp.json, Claude Desktop, or VS Code Argus extension):

{
  "mcpServers": {
    "argus": {
      "command": "argus",
      "args": ["mcp"]
    }
  }
}

Cursor — ~/.cursor/mcp.json

Claude Desktop — ~/Library/Application Support/Claude/claude_desktop_config.json

VS Code — Argus extension MCP (Content-Length framing)

Any MCP client — stdio: command argus, args ["mcp"]

Tool	Description
`scan_sast`	Static code analysis — all languages
`scan_dast`	Dynamic scan of a running web app
`scan_sca`	Vulnerable dependency detection
`scan_secrets`	Leaked API keys, tokens, passwords
`scan_iac`	Terraform, K8s, Dockerfile, Helm, Ansible misconfigs
`scan_terraform`	Deep Terraform scan (tfsec, tflint, KICS)
`scan_ansible`	Ansible playbook & role security scan
`scan_container`	Container image CVE scanning
`scan_ml`	AI/ML security — model loading, LLM keys, prompt injection
`scan_all`	Everything in parallel — includes ML and database rules
`compare_scans`	Diff scans or compare against a baseline file
`check_tools`	List which scanners are installed
`apply_fix`	Run a confirmed ESLint or Semgrep patch locally

Pick your stack

MCP configuration