"Security vulnerabilities and risks in MCP Server execution methods" matching MCP servers:

Enables a single Antigravity IDE to explicitly drive multiple isolated Antigravity CLI workers, choosing each worker's account, model, skills, task, and expected outputs while the bridge executes those decisions over STDIO with SQLite-backed task state. It returns bounded logs, cancellable task control, and immutable artifact exports whose chunks and whole files can be verified by SHA-256.

Enables Codex to manage a local Claude Code companion through MCP, implementing a dual-agent workflow where Codex handles reasoning and review while Claude Code performs engineering tasks.

Provides AI agents with standardized security scanning capabilities for authorized assessments, including host detection, port scanning, service fingerprinting, web vulnerability scanning, CVE verification, and report generation, all with unified JSON output and strict compliance controls.

A safety-constrained MCP server that exposes selected Kali Linux and Nmap capabilities within an authorized lab network, enforcing strict scope limitations and audit logging.

Enables Claude to execute Minecraft commands and get tab completions through the MasterControl API. Allows remote command execution and command discovery while the player is online on a server.

Provides a sandboxed Docker environment for executing Python code against API endpoints, exposing tools for discovery, inspection, execution, and reuse.

Enables AI agents to execute terminal commands and Python code on the host system with session management and smart output handling, leveraging Agent Zero's proven implementation.

Enables a Claude Code cloud session to run shell commands inside a chroot jail on your own computer and to call the MCP servers already installed there, with every request authenticated and relayed over a Cloudflare quick tunnel so no router port is opened and no SSH key or tunnel is ever handed to the cloud VM.

Enables AI clients to securely execute remote commands and transfer files over SSH through standardized MCP tools, with multi-host management, flexible authentication, and an admin console.

Enables LLMs to perform automated penetration testing and Active Directory reconnaissance through Mythic, with tools for executing PowerShell, AD recon, domain user enumeration, and Kerberoasting.

An educational MCP server exposing shell command execution (PowerShell and sh) and a benign tool for learning about MCP tools, resources, and security risks like tool poisoning.

Combines KC Chat Panel session interaction with AgentDock computer control tools, enabling Cursor Cloud Agent to chat and operate the local machine via AgentDock.

Enables AI clients to securely operate servers over SSH, including remote command execution and file transfer with a built-in web admin console and Windows tray app.

Demonstrates deceptive tool naming and unsanitized shell execution by exposing tools that perform OS fingerprinting and run local system commands through MCP. Intended for security research on vulnerabilities in the MCP ecosystem.

A single-purpose MCP server that lets an AI assistant run commands over SSH on a fixed, pre-configured host only, with an explicit per-call confirmation gate before execution.

Ephemeral MicroVM-isolated code execution for AI agents. Run Python, Node, or bash — fresh hardware-isolated VM per call, hard-purged after. No state persists between calls.

A persistent Python REPL MCP server for AI agents with stateful execution, real timeouts, crash isolation, and an MCP bridge to call other tools in the project.

Stateless command execution and process management MCP server for Claude. Enables searching file contents, executing commands with safety limits, listing processes, and terminating processes.

Executes privileged commands with mandatory human approval via a TUI prompt, supporting local and remote execution through sudo.

Enables LLMs to interact with remote servers via SSH, supporting command execution, file upload/download, and directory listing.