Security Scanning

Cybersecurity MCP server: 323 prompts + 7 workflows for red team, blue team, SOC, cloud, OSINT.

Free passive security scanning - check any domain's DMARC, TLS, headers, and exposures.

Read-only MCP server giving AI agents the web as compact, ranked, verified evidence. Local cross-encoder reranker, NLI claim verification, semantic cross-source agreement and contradiction detection. No API keys.

WARDEN MCP firewall — blocks poisoned MCP servers before any tool runs. ARGUS-3 agent CLI (argus); wallet and crypto optional.

Scans code changes for leaked secrets and insecure config, with actionable fixes for AI agents.

Knock, knock. Who's there? Subdomain enumeration via Certificate Transparency and wordlist DNS brute force, with wildcard detection. CLI, library and MCP server. Zero dependencies.

Scan a project for leaked secrets, risky MCP configs, and unsafe automation before handing it to an AI coding agent (Claude Code, Cursor, Codex). Zero dependencies, runs locally.

AgentGate core engine: MCP scanning rule engine, lockfile spec, client config discovery

Andesyte local security CLI and MCP server: check code and dependencies without uploading source.

Full-spectrum wireless security MCP server — WiFi (WPA/WPA2/WPA3, KRACK, Dragonblood, PMKID, Evil Twin), Bluetooth (BlueBorne, KNOB, BLE), RF/SDR (RollJam, sub-GHz), NFC/RFID (Mifare, EMV relay), Cellular/5G (IMSI, SS7), IoT (Zigbee, Z-Wave, LoRa, MQTT),

Security linter for environment variables, Docker, CI, Kubernetes, and runtime configuration.

MCP server for AI coding agents (Claude Code, Cursor, Cline, etc.): verify packages before installing, assess MCP servers before adding them, scan for secrets, audit agent configs, and self-review staged changes before committing.

List the tools your AI agent can call, ranked by how dangerous they are, and which are unguarded.

MCP server that lets AI agents drive your real, logged-in browser: visible cursor, takeover, handoff, approvals, origin allowlist.

Dangerous config and secret scanner for AI coding agents, MCP, and local automation projects.

Classifies prompt injection, jailbreaks, and out-of-scope user input before agents act on it.

Agentic OS MCP Server — 150+ tools with on-demand loading (26 core), Streamable HTTP transport, background task engine, browser automation, TF-IDF semantic memory, multi-agent orchestration. Zero API keys.

Security scanner for MCP servers. Find vulnerabilities before your AI agent does.

Production readiness for vibe-coded apps. 52 checks for security, reliability, and performance.

Twelve selectable red-team agent modes for DeepSeek Harness: one dispatcher plus eleven specialists, each carrying a staged engagement ledger, stage gates, a shared experience store and OT write-confirmation. Built on the MIT-licensed dsh-redteam-model an