Security & Testing MCP Servers for Devin Desktop

Manage ConsentEase consent banners and cookie inventories from your coding agent.

Free website check: HTTPS setup and security headers, scored with plain-English fixes. No account.

Reverse engineering of .NET assemblies and native binaries: decompile, search, compare, patch.

Shows an AI assistant the last cypress run: command log, errors, screenshots, DOM of failed tests.

Finds PII and credentials in PDFs, screenshots and scanned documents

Inspects live IPv4/IPv6 DNS resolution, TLS certificate issuer/expiry, and HTTP security grade.

Replay real HTTP traffic against base and changed builds; flag behavior changes the intent omits.

Edge Case Museum MCP — 'Your code works. Except for these wonderfully terrible inputs.'

Find failing, flaky, and slow Playwright tests on Endform and keep your suite healthy as it grows.

Test your AI agents for security and safety weaknesses, and re-verify the fixes.

Accessibility scans with evidence, public reports, and fresh checks after fixes.

Fraud risk score for signups and orders from email, IP, phone and user-agent

Detecta e mascara dado pessoal brasileiro (CPF, CNPJ, RG, e-mail) antes do texto ir a uma IA. LGPD.

Local, execution-free analysis of binaries, app bundles and archives for CLI and agents.

Check if a package or MCP server is safe before installing. Find tools, connectors, datasets.

Agent-safe secrets from self-hosted Vaultwarden/Bitwarden: injected into commands, masked in output

Persist failure simulations. No external fault injection or transfers. Customer key required.

Audits any Base/EVM address for bytecode risk, proxy patterns, honeypot selectors, and balance.

Who can change an EVM contract or Safe: proxy admin, owner, Safe signers, timelock. Free alerts.

Local MCP tools that keep secrets out of agent context: redact files, scan commits, verify webhooks.

OSINT lookups across breach, people, domain, crypto, and image sources, paid per lookup.