Arcwall Security MCP Server

@rom-baro

リポジトリ

基本情報

カテゴリ

開発者ツール

トランスポート

stdio

作者

rom-baro

投稿者

rom-baro

Arcwall Security MCP Server について

Security scanning for Claude Code, Cursor, Windsurf. Detects secrets, scans MCP configs, generates threat models.

#security #ai-security#threat-model#mcp #skills

Arcwall Security MCP Server の設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "arcwall": {
      "command": "npx",
      "args": [
        "@arcwall/mcp-server"
      ],
      "env": {
        "ARCWALL_API_KEY": "your-key-here"
      }
    }
  }
}

Arcwall Security MCP Server のツール

Scan workspace for hardcoded API keys, passwords, private keys, tokens, and credentials. Run before committing or deploying.

Scan MCP server configurations for prompt injection, excessive permissions, and unverified server origins. Scans .cursor/mcp.json, .vscode/mcp.json, .claude/mcp.json and other MCP config files.

Scan agent instruction files for security vulnerabilities. Covers CLAUDE.md, .cursorrules, .windsurfrules, AGENTS.md and other formats. Detects prompt injection, sensitive data, and missing guardrails.

Generate a STRIDE threat model for the current codebase. Identifies trust boundary gaps, authorization issues, data flow exposures, and architectural risks. Results saved to Arcwall dashboard.

Test a system prompt for injection vulnerabilities, jailbreak susceptibility, missing guardrails, and excessive agency. Include test messages to check multi-turn vulnerabilities.

Security check before committing. Scans staged files for secrets and checks MCP configs. Returns CLEAR TO COMMIT or BLOCKED with issues to fix.

Check dependencies for known CVEs. Scans package.json for vulnerable packages with safe version recommendations.

概要

What is Arcwall Security?

Arcwall Security is an MCP server that provides security scanning for Claude Code, Cursor, Windsurf, and any MCP-compatible AI coding tool. It helps developers find hardcoded secrets, MCP configuration vulnerabilities, insecure agent instructions, and other common security issues directly from the AI assistant.

How to use Arcwall Security?

Get a free API key at https://arcwall.io, then add the server configuration to your AI tool’s MCP config file (e.g., ~/.claude/mcp.json for Claude Code) with the command npx @arcwall/mcp-server and the ARCWALL_API_KEY environment variable. Restart the AI tool to enable scanning commands.

Key features of Arcwall Security

Scan for hardcoded credentials and secrets
Detect MCP config vulnerabilities
Analyze CLAUDE.md and .cursorrules security
Generate STRIDE threat models
Test prompts for injection vulnerabilities
Pre-commit security checks
Scan dependencies for known CVEs

Use cases of Arcwall Security

Scan a repository for secrets before sharing code
Check MCP configuration files for misconfigurations
Analyze AI agent instructions for unsafe patterns
Run a pre-commit security check to prevent vulnerabilities
Identify outdated or vulnerable dependencies

よくある質問

How do I get an API key?

Visit https://arcwall.io and sign up for a free API key.

What AI tools does Arcwall support?

It works with Claude Code, Cursor, Windsurf, and any MCP-compatible AI coding tool.

What scanning tools are available?

The server provides seven tools: `arcwall_scan_secrets`, `arcwall_scan_mcp`, `arcwall_scan_agent_instructions`, `arcwall_threat_model`, `arcwall_check_prompt`, `arcwall_pre_commit`, and `arcwall_scan_dependencies`.

How do I configure Arcwall in Cursor or Windsurf?

For Cursor, use the same JSON config as Claude Code in `.cursor/mcp.json`. For Windsurf, add the server via the MCP settings panel.

Is there a dashboard or documentation?

Yes. Dashboard: https://arcwall.io/app.html. Docs: https://arcwall.io/docs.html.

「開発者ツール」の他のコンテンツ

Termany

thinkany-ai

Agent-Native Terminal

174

Casefile

azimov777

One case file per task — shared by every session, agent and person that touches it. Self-hosted MCP server and live board. MIT.

Foremerge

naw103

Catch intent conflicts before code conflicts. The open-source coordination protocol for coding agents, built above Git.

LastPing

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci

Innovalyxx Sovereign Edge

edge.innovalyxx.com

Verified cyber-physical AI tools. 25 MCP tools, x402-payable on Base.