- Conduid
- Marketplace
- #sandbox
MCP servers tagged sandbox
67 live MCP servers tagged "sandbox", ranked by trust score. Tags come from package metadata and repository topics, so this list covers servers across every category that work with sandbox.
Microsandbox
hosted platform for secure execution of AI code. Great for Code Interpreter, Data Analysis, Browser Use.
Sandbox
All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.
Moltis
A Rust-native claw you can trust. One binary — sandboxed, secure, auditable. Voice, memory, MCP tools, and multi-channel access built-in.
Opensandbox
OpenSandbox is a general-purpose sandbox platform for AI applications, offering multi-language SDKs, unified sandbox APIs, and Docker/Kubernetes runtimes for scenarios like Coding…
Aenvironment
Standardized environment infrastructure for Agentic AI development.
Gru Sandbox
Cli and MCP for gbox. Enable AI agents to operate Android/Browser/Desktop like human.
Ironcurtain
A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)
Kilntainers
MCP server to give every agent an ephemeral Linux sandboxes for executing shell commands.
Eve
Filesystem-first framework for durable backend AI agents that run anywhere.
Sandbox
Fast cold-boot MicroVM sandboxes for AI agents on cocoon
Codemode
Programmatic tool calling / Code Mode for MCP — turn any OpenAPI spec into two sandboxed tools (search + execute).
Forkd
Fork() for AI agent microVMs. Spawn 100 children in ~100ms from a warm parent; BRANCH a live VM in ~150ms. KVM-isolated, snapshot CoW.
OpenRath
An open-source, PyTorch-like runtime for dynamic multi-agent and multi-session workflows.
Astrid
Astrid is a portable, capability-secure operating system for composable software.
ScienceClaw
ScienceClaw is a personal research assistant built with LangChain DeepAgents and AIO Sandbox infrastructure, adopting a completely new architecture beyond OpenClaw. It offers stro…
Leash
Leash by StrongDM - take your AI agents for a walk
Open Cowork
Open-source AI agent desktop app for Windows & macOS. One-click install Claude Code, MCP tools, and Skills — with sandbox isolation, multi-model support, and Feishu/Slack integrat…
Sandbase Harness
Open-source CMA-compatible agent runtime for any model, with MCP tools, sandboxed sessions, audit, replay, and a local console. Includes a native DeepSeek Harness bundle over stdi…
Agentrove
Your own Claude Code UI, sandbox, in-browser VS Code, terminal, multi-provider support (Anthropic, OpenAI, GitHub Copilot, OpenRouter), custom skills, and MCP servers.
mavdol/capsule/mcp-server
Run untrusted Python/JavaScript code in WebAssembly sandboxes.
Zerobox
Lightweight, cross-platform process sandboxing powered by OpenAI Codex's runtime. Sandbox any command with file, network, and credential controls.
Wirken
The enterprise gateway for autonomous agents. Identity management, per-channel isolation, credential vault, per-session tamper-evident audit log.
Agentty
AI pair programming in your terminal — one static binary, sub-ms startup, any model
Nehemiah
On-demand Linux computers you can hand to an AI — real Firecracker microVMs with a browser, terminal, coding agents, and an AI that drives them.
Pydantic AI Backend
File Storage & Sandbox Backends for Pydantic AI: console tools for file operations, Docker-isolated sandboxes for safe execution, and permission system with presets for access con…
Helm AI Kernel
Fail-closed execution firewall for AI agents: quarantine MCP tools, proxy OpenAI-compatible requests, emit signed receipts, and verify EvidencePacks offline.
sandock
Model Context Protocol (MCP) server for Sandock - Sandbox in Docker for AI Agents
Avakill
🔪 Open-source safety firewall for AI agents. Intercepts tool calls before they execute, enforces YAML policies, and kills dangerous operations in real-time. Works with OpenAI, Ant…
Boxlite MCP
Powered by BoxLite - embeddable sandbox with hardware-level isolation and no daemon. The SQLite of sandbox, coming soon as open source.
Sandcastle
Describe what you want. Go home. Sandcastle ships it. 6 AI providers, EU data residency, smart failover, cost intelligence, 20 step types, 236 templates. European-built, open sour…
Shannot
Human-in-the-loop execution for LLM agents
hileamlakB/PRIMS
submitted code in an isolated environment.
CloseClaw
A lightweight and security-focused Python implementation of OpenClaw.
Fence
Local-first security scanner, MCP protocol inspector, dynamic fuzzer, Docker sandbox, and report generator for Model Context Protocol servers.
Wolido/OpenAaaS
adapter`.
capsulerun/bash
Sandboxed bash for agents. Run untrusted commands in WebAssembly sandboxes with no setup required.
Openhermit
OpenHermit is the open-source platform for deploying fleets of AI agents as production services — durable state, sandboxed execution, managed at scale, and the channels you alread…
Claude Architect
Claude Code delegates coding to isolated CLI agents it doesn't trust (Codex, OpenCode, Pi, Pythinker), freezes what they produce, verifies it independently, and merges only what a…
Agent Workspace Linux
Isolated Linux desktop workspaces for AI agents — a hidden, agent-owned desktop and browser over MCP, so an agent can do GUI and web work without touching your real desktop.
Darwin Agentic Cloud
Verifiable and free cloud compute for AI agents. webMCP + MCP native. Check out our sandboxed Beta + research in the README
Crawl
AI-powered web crawler — self-hosted Firecrawl alternative. Crawl, extract, render JS, search. CLI + MCP + REST API + Dashboard.
Orchestrator Ts
Orchestrate MCP servers with Code Mode - let LLMs write TypeScript code for complex workflows. Supports multi-server coordination, secure VM sandboxing, and 60-75% token savings.
Anvil
Portable Rust Agent Client Protocol (ACP) server with model routing, tools, permissions, sandboxing, sessions, and MCP integration.
Capgate
Compile MCP tool manifests into sandbox policies (bwrap, egress rules, and more).
Shatale MCP Server
MCP server for Shatale — AI agent payment infrastructure with 17 tools for purchases, virtual cards, merchant catalog, and policy engine
Terminal Guardian
Secure Model Context Protocol server for safe, sandboxed terminal access for AI assistants
Webview Host
Secure webview host for Model Context Protocol (MCP) servers with elicitation support
Mcpwasm
Static MCP host: run untrusted MCP tool.js files sandboxed in QuickJS-wasm (Cloudflare Workers or Node), with explicit host capabilities (fetchOrigin, callInternal, extraCapabilit…
Codemode Workers
Expose any API to an LLM agent as two sandboxed MCP tools (search + execute) on Cloudflare Workers.
Fedreg MCP Server
Code-mode MCP server for the U.S. Federal Register, Electronic Code of Federal Regulations, and regulations.gov APIs.