"Using a terminal like PowerShell or Git Bash" matching MCP servers:

MCP server that vets LLM-emitted shell commands BEFORE execution — detects rm -rf nested deep in chains, package-manager glob removal (apt remove 'nvidia'), dd/mkfs filesystem destruction, chmod 777 / chown -R privilege blast, network-exfil via curl | bash, chained shutdown/reboot, git destructive ops. 30 detection rules across 8 families. Sub-second, local, free, MCP-native.

MCP server enabling Claude Code to capture screenshots of Windows applications through WSL2, allowing AI to diagnose UI errors and verify layouts.

A secure terminal execution server that enables controlled command execution with security features and resource limits via the Model Context Protocol (MCP).

Enables Claude AI to play a cookie-themed dungeon RPG, including clicking cookies, recruiting heroes, exploring dungeons, and managing inventory through natural language commands.

Provides tools for autonomous CVE detection, enrichment, and remediation across managed repositories using GHSA and NVD data. It enables automated triage and pull request creation for dependency fixes based on configurable severity policies.

This MCP server provides secure access to databases for AI agents, enforcing authentication, authorization, human approval, logging, and notifications to prevent dangerous actions.

Mints short-lived, scoped GitHub App installation tokens on demand for AI agents to access git repositories or the GitHub API.

MCP server for securely managing GitHub & GitLab credentials in an encrypted vault, allowing AI agents to retrieve tokens by org or group name automatically.

An MCP server for Git repository management with access key permissions, fine-grained access control, audit logging, and LLM-powered code analysis. Supports multi-repo management, branch/path-level rules, and a web admin interface.

Shehata Git MCP enables coding agents to perform policy-checked Git operations (stage, commit, pull, push) on repositories pinned to specific GitHub identities. It guards against credential exposure and blocks destructive commands like force push or reset.

Provides agent certification and trust verification tools for AI agents, enabling certification checks, trust score calculations, audit ticket issuance, and emergency kill switch activation through the A-SOC trust network.

A secure MCP proxy server with JWT authentication, SQL guardrails, rate limiting, and Kafka audit logging, enabling enterprise-grade access control for MCP clients like Cursor and Claude Desktop.

Enables AI agents to manage VPN infrastructure through provisioning, lifecycle control, traffic routing, and health monitoring.

MCP server for integrating with Grizzly SMS platform to rent virtual numbers, receive SMS verification codes, and manage activations directly from AI assistants like Cursor, Claude Desktop, and OpenClaw.

A fork of Playwright MCP that adds PhiShark preflight and browser-deep security checks to block or warn on phishing and high-risk pages.

Enables MCP clients to triage SOC alerts while enforcing a trust firewall across retrieval, memory, and privileged actions. It exposes tools for alerts, logs, memory, and alert actions, with defenses that refuse risky operations in the presence of attacker-controllable content.

Enables deterministic auditing of agent skills, system prompts, and downloaded file collections against eight malicious-skill supply-chain patterns, returning line-numbered findings and pass/flag verdicts without using an LLM or network calls.

Enables enterprise MCP security auditing through 12 deterministic no-LLM tools for evidence-gated claims, skill/prompt supply-chain audits, token profiling, and server auth-mode checks.

Enables deterministic, no-LLM scrubbing of secrets from text or logs before they enter agent context, supporting redaction, masking, and hashing without ever leaking the original value.

Provides tools to interact with the OpenCTI platform, including checking if a campaign exists.