1. Conduid
  2. Marketplace
  3. #sandbox
Tag

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.

67
live servers
48
avg trust
4.9K
most stars
1

Microsandbox

zerocore-ai

hosted platform for secure execution of AI code. Great for Code Interpreter, Data Analysis, Browser Use.

★ 4.9Kupdated 6 months agoApache-2.0
92
2

Sandbox

agent-infra

All-in-One Sandbox for AI Agents that combines Browser, Shell, File, MCP and VSCode Server in a single Docker container.

★ 2.7Kupdated 6 months agoApache-2.0
92
3

Moltis

moltis-org

A Rust-native claw you can trust. One binary — sandboxed, secure, auditable. Voice, memory, MCP tools, and multi-channel access built-in.

★ 1.7Kupdated 6 months agoMIT
92
4

Opensandbox

alibaba

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…

★ 1.5Kupdated 6 months agoApache-2.0
92
5

Aenvironment

inclusionAI

Standardized environment infrastructure for Agentic AI development.

★ 254updated 6 months agoApache-2.0
80
6

Gru Sandbox

babelcloud

Cli and MCP for gbox. Enable AI agents to operate Android/Browser/Desktop like human.

★ 166updated 6 months agoApache-2.0
77
7

Ironcurtain

provos

A secure* runtime for autonomous AI agents. Policy from plain-English constitutions. (*https://ironcurtain.dev)

★ 66updated 6 months agoApache-2.0
75
8

Kilntainers

Kiln-AI

MCP server to give every agent an ephemeral Linux sandboxes for executing shell commands.

★ 31updated 6 months agoMIT
69
9

Eve

Filesystem-first framework for durable backend AI agents that run anywhere.

67
10

Sandbox

JohanLi233

Fast cold-boot MicroVM sandboxes for AI agents on cocoon

★ 36updated 8 months agoApache-2.0
66
11

Codemode

cnap-tech

Programmatic tool calling / Code Mode for MCP — turn any OpenAPI spec into two sandboxed tools (search + execute).

★ 3updated 6 months agoMIT
65
12

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.

64
13

OpenRath

An open-source, PyTorch-like runtime for dynamic multi-agent and multi-session workflows.

64
14

Astrid

Astrid is a portable, capability-secure operating system for composable software.

64
15

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…

59
16

Leash

Leash by StrongDM - take your AI agents for a walk

59
17

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…

59
18

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…

59
19

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.

52
20

mavdol/capsule/mcp-server

Run untrusted Python/JavaScript code in WebAssembly sandboxes.

52
21

Zerobox

Lightweight, cross-platform process sandboxing powered by OpenAI Codex's runtime. Sandbox any command with file, network, and credential controls.

52
22

Wirken

The enterprise gateway for autonomous agents. Identity management, per-channel isolation, credential vault, per-session tamper-evident audit log.

52
23

Agentty

AI pair programming in your terminal — one static binary, sub-ms startup, any model

52
24

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.

52
25

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…

44
26

Helm AI Kernel

Fail-closed execution firewall for AI agents: quarantine MCP tools, proxy OpenAI-compatible requests, emit signed receipts, and verify EvidencePacks offline.

44
27

sandock

git+sandock-ai

Model Context Protocol (MCP) server for Sandock - Sandbox in Docker for AI Agents

39
28

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…

39
29

Boxlite MCP

Powered by BoxLite - embeddable sandbox with hardware-level isolation and no daemon. The SQLite of sandbox, coming soon as open source.

39
30

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…

39
31

Shannot

Human-in-the-loop execution for LLM agents

39
32

hileamlakB/PRIMS

submitted code in an isolated environment.

39
33

CloseClaw

A lightweight and security-focused Python implementation of OpenClaw.

39
34

Fence

Local-first security scanner, MCP protocol inspector, dynamic fuzzer, Docker sandbox, and report generator for Model Context Protocol servers.

39
35

Wolido/OpenAaaS

adapter`.

39
36

capsulerun/bash

Sandboxed bash for agents. Run untrusted commands in WebAssembly sandboxes with no setup required.

39
37

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…

39
38

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…

39
39

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.

39
40

Darwin Agentic Cloud

Verifiable and free cloud compute for AI agents. webMCP + MCP native. Check out our sandboxed Beta + research in the README

39
41

Crawl

AI-powered web crawler — self-hosted Firecrawl alternative. Crawl, extract, render JS, search. CLI + MCP + REST API + Dashboard.

37
42

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.

37
43

Anvil

Portable Rust Agent Client Protocol (ACP) server with model routing, tools, permissions, sandboxing, sessions, and MCP integration.

37
44

Capgate

Compile MCP tool manifests into sandbox policies (bwrap, egress rules, and more).

37
45

Shatale MCP Server

MCP server for Shatale — AI agent payment infrastructure with 17 tools for purchases, virtual cards, merchant catalog, and policy engine

37
46

Terminal Guardian

Secure Model Context Protocol server for safe, sandboxed terminal access for AI assistants

37
47

Webview Host

Secure webview host for Model Context Protocol (MCP) servers with elicitation support

37
48

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…

37
49

Codemode Workers

Expose any API to an LLM agent as two sandboxed MCP tools (search + execute) on Cloudflare Workers.

37
50

Fedreg MCP Server

Code-mode MCP server for the U.S. Federal Register, Electronic Code of Federal Regulations, and regulations.gov APIs.

37
← Previous Page 1 of 2 Next →