AI Defense Stack

Agent & MCP security

Strands Box: open-source sandbox engine for AI agents

Strands Box is an open-source sandbox engine for AI agents from Amazon Web Services. It is released under the Apache-2.0 license and is offered as: CLI, Self-hosted.

  • Last reviewed
Visit Strands Box (opens in a new tab) Documentation (opens in a new tab) Source code (opens in a new tab)
Open sourceApache-2.0 Layer 7: Agent and tool access

Best for

Developers who run coding or other agents locally on a Mac and want default-deny file, program and network rules with credentials kept outside the agent

Consider instead if

  • You need a sandbox that runs on Linux today, with kernel-level isolation and YAML policies. See OpenShell.

What Strands Box does

Strands Box is an open-source (Apache-2.0) sandbox engine for AI agents, launched by AWS's Strands team on October 7, 2026 as a developer preview. It restricts what an agent can execute, read, write and reach on the network by combining operating system isolation with policies written in Dogwood, an open source policy language that uses permit and forbid rules. Operations the policy engine checks are denied unless a rule permits them, and enforcement points include network egress, Python and shell interpreters and an MCP broker. An egress gateway can add API credentials to permitted requests so the agent never receives the secrets. It currently supports local execution on macOS with Apple silicon, with Linux planned.

This summary is our own wording of the sourced facts on this page.

Key facts

Each value links to the page that states it, with the date we checked it.

Vendor
Amazon Web Services Source, checked October 21, 2026: aws.amazon.com (opens in a new tab)
Status
Active Source, checked October 21, 2026: api.github.com (opens in a new tab)
Open source
Yes: Apache-2.0 Source, checked October 21, 2026: aws.amazon.com (opens in a new tab)
Repository
github.com Source, checked October 21, 2026: aws.amazon.com (opens in a new tab)
GitHub stars
451 as of October 21, 2026 Source, checked October 21, 2026: api.github.com (opens in a new tab)
Latest push
October 22, 2026 Source, checked October 21, 2026: api.github.com (opens in a new tab)
Latest release
October 7, 2026 Source, checked October 21, 2026: api.github.com (opens in a new tab)
Deployment
CLI, Self-hosted Source, checked October 21, 2026: github.com (opens in a new tab)
Pricing model
Free Source, checked October 21, 2026: aws.amazon.com (opens in a new tab)
Website
github.com Source, checked October 21, 2026: github.com (opens in a new tab)
Documentation
github.com Source, checked October 21, 2026: github.com (opens in a new tab)
API reference
Not documented in the sources we checked
Quickstart
Not documented in the sources we checked
Security page
github.com Source, checked October 21, 2026: github.com (opens in a new tab)
Attestations or disclosure
Reports go to the AWS Vulnerability Disclosure Program on HackerOne or by email, not public issues Source, checked October 21, 2026: github.com (opens in a new tab)

Capabilities

As documented by the vendor or project. The tag is our label from a controlled vocabulary.

Integrations

Where Strands Box fits in our AI security layers

Our analysis

Our editorial model, not a standard. The primary layer follows the category, except for tools whose main documented job is detection and response; other layers rest on a capability the sources document. How the model works.

AI security layers that Strands Box covers, with the role, how each applies and what it rests on
LayerRoleHow it appliesBased on
L7 Agent access Agent and tool access Primary Limit which tools, MCP servers, data and credentials an agent can use, and require approval for risky actions. Follows its category, Agent & MCP security
L8 Monitoring Monitoring and response Also covers Documents logging of policy decisions in OTLP JSON. Logs policy decisions in OTLP JSON

OWASP LLM Top 10 mapping

Our analysis

The risk list is OWASP's (Top 10 for LLM Applications, 2025). The mapping is our analysis, and each row rests on a capability the sources document.

OWASP LLM risks mapped to Strands Box, with the capabilities each mapping rests on
RiskHow it appliesBased on
LLM02 Sensitive Information Disclosure An egress gateway adds credentials to permitted requests, so the agent never holds secrets it could leak. An egress gateway adds configured API credentials or AWS SigV4 signing to permitted requests so the agent never receives the secrets
LLM06 Excessive Agency Default-deny rules and OS isolation limit what files, programs and network destinations an agent can use. Runs agents in an operating system sandbox with file, program and network access set in a box.toml file; Dogwood permit and forbid policies, with default deny, enforced at network egress, Python and shell interpreters and an MCP broker

Not mapped in our analysis: LLM01, LLM05, LLM07. These are risks we expect tools in this category to cover; the sources we checked do not document a matching capability.

Alternatives and related tools

More in Agent & MCP security, ranked within the category by Coverage Score.

Cisco DefenseClaw

Cisco

Open sourceApache-2.0
  • CLI
  • Self-hosted

Scans skills and MCP servers, inspects agent tool calls and keeps an audit trail around AI coding agents.

Best for: Security teams that want scanning, guardrails and an audit trail around the coding agents developers already run, starting in observe mode before anything is blocked

Coverage Score 76 out of 100
  • LLM01 Prompt Injection
  • LLM02 Sensitive Information Disclosure
  • LLM06 Excessive Agency

Reviewed

Docker MCP Gateway

Docker

Open sourceMIT
  • CLI
  • Self-hosted

Proxies AI clients to MCP servers it runs as isolated Docker containers, with tool filters and call logs.

Best for: Developers and platform teams that already use Docker and want MCP servers to run in containers behind one gateway with per-server tool selection

Coverage Score 72 out of 100
  • LLM02 Sensitive Information Disclosure
  • LLM06 Excessive Agency

Reviewed

agentgateway

agentgateway (a Series of LF Projects, LLC)

Open sourceApache-2.0
  • CLI
  • Self-hosted
  • Cloud-native

Open-source proxy that applies auth, CEL policy and guardrails to LLM, MCP and agent-to-agent traffic.

Best for: Platform teams that want one open-source gateway in front of MCP servers and LLM providers, with token validation, CEL rules per MCP method and pluggable guardrails

Coverage Score 69 out of 100
  • LLM02 Sensitive Information Disclosure
  • LLM06 Excessive Agency

Reviewed

Strands Box FAQ

Is Strands Box open source?

Yes. The AWS post says it is licensed under Apache 2.0, and the code is on GitHub at strands-agents/box.

Which platforms does it support?

The README says it currently supports local execution on macOS with Apple silicon, and that Linux support is planned. The AWS post says support for other operating systems is a next priority.

What is Dogwood?

The AWS post describes Dogwood as an open source policy language that Strands Box uses. Rules are written as permit and forbid statements, and some rules can depend on earlier actions.

Key facts you can cite

We have no commercial relationship with Amazon Web Services.

Sources & last reviewed

Last reviewed . We compile from the vendors' own public pages and repositories and we do not run the products. Source links open in a new tab. Found a mistake? Report a correction.