How do I get an API key?
Visit https://arcwall.io and sign up for a free API key.
@rom-baro
Basic information
Security scanning for Claude Code, Cursor, Windsurf. Detects secrets, scans MCP configs, generates threat models.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"arcwall": {
"command": "npx",
"args": [
"@arcwall/mcp-server"
],
"env": {
"ARCWALL_API_KEY": "your-key-here"
}
}
}
}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.
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.
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.
Visit https://arcwall.io and sign up for a free API key.
It works with Claude Code, Cursor, Windsurf, and any MCP-compatible AI coding tool.
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`.
For Cursor, use the same JSON config as Claude Code in `.cursor/mcp.json`. For Windsurf, add the server via the MCP settings panel.
Yes. Dashboard: https://arcwall.io/app.html. Docs: https://arcwall.io/docs.html.

MCP server for AI Agents — exposes Yocoolab feedback threads and design selections as tools
Gives AI agents public URLs (tunnels) for localhost, live HTTP traffic inspection, snapshot publishing, and access control. Part of LocalCan, the ngrok alternative for Mac, Windows and Linux. Free plan.

Local-first credential broker for MCP. AI coding agents (Claude Code, Cursor, Codex…) call APIs, SSH and databases through scoped presets; secrets stay in your OS keychain and never enter the agent's context.
Query your team's drift, vulnerability, and migration data from any AI assistant. Vibgrate MCP connects Cursor, Claude, ChatGPT, Windsurf, or VS Code to Vibgrate Cloud: 51 tools for DriftScores, CVEs and EOL runtimes, up
Console, Backend and CLI to manage Capgo Instant update and Native build for Capacitor apps Build and upload to app store your mobile app
Comments