"CodeQL for Code Auditing" matching MCP servers:

MCP server that gives AI agents isolated, named Linux computers with stable IDs and lifecycle control. Supports multiple backends like Docker, Fly Machines, Modal, and E2B, with a dashboard for managing sandboxes.

MCP server that lets Claude Code drive the local Codex CLI as a sub-agent for concurrent queries and optional file/shell actions, using the CLI's existing login and sessions.

Cognitive security for AI-assisted development, preventing dangerous commands and large AI code rewrites when fatigued.

An MCP server that implements Claude Code-like functionality, allowing the AI to analyze codebases, modify files, execute commands, and manage projects through direct file system interactions.

Enables AI agents to execute SSH commands, read files, and list directories on remote hosts with a configurable command-safety policy.

mcp-node-zig is an MCP server for remote machines. Drop it on a build box, a homelab server, a Windows host or a VPS, and any MCP client can run commands, drive long-running processes and read and write files there over one authenticated HTTP endpoint.

Runs git-bash (MSYS2) commands for AI agents on Windows from outside the agent's sandbox, so pipelines, command substitution, and subprocesses work. Exposes exec, bash_info, doctor, and policy tools with timeouts, output spilling, concurrency limits, capability-based command gating, and JSONL auditing.

MCP server for E2B code sandbox, enabling creation, management, and execution of code in secure sandboxes using Python and shell commands.

Unofficial Powershell MCP server

SassyMCP is a comprehensive MCP server that replaces 75+ individual servers with one 34MB executable. It provides 274 tools for file operations, shell, desktop automation, GitHub/Git, Android interaction, network/security auditing, SSH, OCR, and Windows system management.

An agent-native shell as an MCP server, designed for LLM agents (like Claude Code) to execute commands with structured output, lazy detail retrieval, and effect tracking, minimizing token usage.

An MCP server that enables secure terminal command execution, directory navigation, and file system operations through a standardized interface for LLMs.

Windows-focused MCP server for terminal automation with persistent PowerShell sessions, live session logs, and VS Code integrated terminal bridge.

Gives Claude Code full control over tmux sessions, windows, and panes, with an optional Sonnet-based safety classifier for destructive commands.

An MCP server that provides secure code execution capabilities using AWS Bedrock AgentCore's CodeInterpreter, supporting Python, JavaScript, TypeScript, shell commands, and file operations.

A local STDIO MCP server for running one bounded command and waiting for its final result, eliminating model-driven polling. Designed for builds, test suites, and other trusted foreground commands.

Enables persistent SSH sessions and SFTP file transfers with native GUI credential prompts for secure remote server management. It supports background command execution, session pooling, and automatic connection reuse across multiple commands.

Gives MCP-compatible AI agents a full local terminal over stdio, enabling shell command execution, file reads and writes, content search, background processes, and stateful tmux sessions with variable capture, auditing, and a configurable command denylist. Requires no deployment or cloud setup.

A Model Context Protocol server for complete shell and SSH mastery, enabling command execution, interactive sessions, file transfer, and port forwarding with auditing and policy controls.

Enables running planned batches of shell commands in parallel locally or over SSH, with dependency ordering, timeouts, cancellation, and per-task result collection.

Agent-native SSH control plane with a local Web Terminal, human-in-the-loop secret input, keychain-backed profiles, and user-confirmed uploads for Codex, Claude Code, and MCP-compatible coding agents.

An MCP server that bridges LLM platforms with multiple socket_server targets, enabling batch parallel execution of packet capture, dial testing, command, and file operations with authentication, auditing, and status locking.

MCP server wrapping Kimi Code CLI (kimi-k2.5) to provide tools for filesystem, shell, web, and agent operations.

MCP server for running shell commands on a Linux development board via UART serial.

An MCP server that enables AI agents to execute terminal commands and Python code on the host system, leveraging Agent Zero's battle-tested implementation with session management and smart output handling.

Manage a fleet of OPNsense firewalls from an AI agent, inside guardrails it can't drive around. MCP server for central management of OPNsense firewall fleets. 129 tools across devices, config sync, tasks, schedules, templates, backups and remote consoles - destructive actions confirmation-gated, MCP-issued tokens lifetime-bounded, backup and storage secrets excluded from the toolset entirely.

Provides AI assistants with natural language access to IMAS data structures and enables remote facility exploration through SSH.

Enables MCP clients to list existing local terminal sessions, read current screen output, and send prompts to operator-approved terminals through an existing herdr-core Unix socket without starting or managing the core.

Linux sandboxes for AI agents, each a Firecracker microVM. Run code, keep files, pause and wake with memory kept, snapshot and fork.

Enables remote MCP clients to securely access a trusted macOS machine's local file system and command execution tools (mcp-combiner) via OAuth-authenticated HTTPS through Cloudflare Tunnel, without opening router ports.