- Conduid
- Marketplace
- #sandboxing
MCP servers tagged sandboxing
38 live MCP servers tagged "sandboxing", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with sandboxing.
alfonsograziano/node-code-sandbox-mcp
A Node.js–based Model Context Protocol server that spins up disposable Docker containers to execute arbitrary JavaScript.
Box
Run AI agents in a sandbox that restricts what they can execute, read, write, and reach on the network. Box combines OS isolation with default-deny Dogwood policies and credential…
Agent Harness Generator
Create custom AI agent harnesses for any repository using this CLI generator.
Metaharness
🛠️ The meta-harness for AI agents — scaffold your own focused, branded agent harness with its own npx CLI, MCP server, memory, learning loop, and witness-signed releases. Works wi…
Tupper
Open-source sandboxes for AI agents — run untrusted, AI-generated code safely on your own machine.
AI Native Linux Icebreaker
Talk to your computer. Icebreaker transforms natural language into safe Linux actions through isolated AI brains, kernel-enforced sandboxes. An AI-native operating system with tru…
Castor
The Universal 245K Agent Microkernel for Local LLMs.
Mcpbash
Embedded sandbox with MCP proxy
Intentframe
Structural security, governance and execution for AI agents: validate actions before they touch files, credentials, network, APIs, or money.
Maker
Describe an MCP server in plain English — get back a working, tested project. Optional checked LLM code-gen pass writes real tool implementations.
Node Code Sandbox MCP
# 🐢🚀 Node.js Sandbox MCP ServerThis repository hosts a Node.js server that implements the Model Context Protocol (MCP) for running JavaScript in isolated Docker containers. It all…
NullSec RedTeam AI
Authorization-first, MCP-governed security execution for explicitly approved environments.
Handyman MCP
Stateful AI Agent Infrastructure with Persistent FTS5 Memory and Sandboxed Execution.
Pydeno
Run AI-generated JavaScript from Python, securely, in a sandbox: real V8 in a supervised, OS-sandboxed worker process (Seatbelt, Landlock, seccomp), with your Python functions as…
Agentbox
Open-source sandboxed runtime for AI agents — gVisor/Docker isolation, credential vault, immutable audit log. Built after CVE-2026-25253.
Mcode
A native C++23 coding-agent harness with a Luau extension layer. One static binary, no runtime, ~8 MB.
Agent Chassis
Contract-first orchestration for long-running coding agents: scoped work records, local dispatch, review evidence, and enforcement provenance.
ClawCrate
Policy + evidence for everything your AI agent executes. 🦀 Kernel-native sandbox for agent commands & MCP servers — Landlock+seccomp (Linux), Seatbelt (macOS). Tamper-evident, off…
Prolog Agent Toolkit
Prolog Agent Framework, Reusable Agent Skills, MCP Server Pattern, Neurosymbolic AI, and Safe Multi-Engine Execution (Scryer, SWI, Trealla, Tau).
Limitlesslibrary
Local, verified reuse for AI agents with fail-closed protection: exact components, source-free methods, receiver-owned verification, and adoption evidence.
Agent Runtime Lab
Secure, durable agent runtime in Java: validated DAG execution, sandboxed tools, MCP, approvals, crash recovery, evaluations and measured benchmarks.
GhostInTheShell MCP
🔒 A sandboxed, read-only MCP server that safely exposes system health, Docker diagnostics, and log intelligence to AI agents like Claude — with strict path whitelisting, context c…
Clanker
Self-improving AI agent harness in Zig 0.16 — gated self-patch loop, sandboxed WASM tools, CLI + web UI
LLM Agnostic Icm Framework
Model-agnostic ICM framework: a folder structure as agent architecture for Copilot, Claude, Codex, or any CLI
Command Scope Contract
Bounded shell and CLI execution for AI agents: structured contracts, policy-gated execution, hardened Linux runtime enforcement, and signed receipts.
Secure Claude
A hardened, containerized environment for running Claude Code as an AI agent with access to local tools via the Model Context Protocol (MCP).
Safe MCP Suite
Two hardened MCP servers - a terminal executor and a file organizer - on one shared deny-by-default safety core, with a fail-closed audit trail and undoable file moves.
Orkis
An agentic AI platform for .NET: run autonomous agents under graduated supervision — durable pause/resume runs, Firecracker-sandboxed execution, persistent workspaces with a super…
AI Agents Research
Field research and feature analysis for AI coding agents — sandboxing, orchestration, plugins, community tooling, SDLC patterns.
Rest Pty
Terminals as a service — drive PTY sessions over REST and MCP.
Openbots
Persistent, named Claude teammates as a native macOS app — sandboxed sessions, visible agent-to-agent handoffs, shared Obsidian vault. No API key: rides your Claude subscription.
Two Stage Sanitization Architecture
Two-stage security architecture to mitigate indirect prompt injection attacks in rich content via privilege separation
Mcpwith Codemode Cc
EDU AI LAB: codemode - new way how LLM can exec code inside MCP srv (Contrast & Compare old ways)
Dagr
The DAG-Native Symbolic AST Slicing Hypervisor & Safety Sandbox for AI Coding Agents
Ggsrun
High-performance Google Drive CLI and Model Context Protocol (MCP) Server for LLM/AI agents. Natively execute Google Apps Script (GAS) under a secure whitelisted runtime sandbox,…
Ggsrun
High-performance Google Drive CLI and Model Context Protocol (MCP) Server for LLM/AI agents. Natively execute Google Apps Script (GAS) under a secure whitelisted runtime sandbox,…
Ggsrun
High-performance Google Drive CLI and Model Context Protocol (MCP) Server for LLM/AI agents. Natively execute Google Apps Script (GAS) under a secure whitelisted runtime sandbox,…
Super MCP
Unify all your MCP servers with a secure, sandboxed proxy