// SCAN REPORT

Sandbox MCP Server

6 tools. 6 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 11 Jun 2026

6 can modify or destroy data

0 read-only

6 tools total

Community server · catalogue entry verified 11/06/2026

How to control Sandbox MCP Server ↓

TOOL MAP

What Sandbox MCP Server exposes to your agents

Read (0) Write / Execute (5) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Sandbox MCP Server tools

Destructive · High exit_container Exiting and cleaning up a container terminates the running environment and disposes of its state. Execute · High execute_command_in_container This tool executes arbitrary commands within a containerized environment. Execute · High create_container_environment Spinning up a Docker container provisions real compute/OS-level resources and can have broad side effects (network exposure, resource consumption, potential escape vectors). Write · Medium create_file_in_container This tool creates files within a sandbox container, which is a write operation that modifies the container's filesystem.

6 of Sandbox MCP Server's 6 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Sandbox MCP Server

PolicyLayer is an MCP gateway — it sits between your AI agents and Sandbox MCP Server, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "exit_container": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "create_file_in_container": {
    "limits": [
      {
        "counter": "create_file_in_container_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Create a free account and register Sandbox MCP Server — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON SANDBOX →

Free to start. No card required.

FULL CATALOGUE

All 6 Sandbox MCP Server tools

DESTRUCTIVE 1 tools

Destructive exit_container closes a container to cleanup environment when finished

EXECUTE 2 tools

Execute execute_command_in_container Runs commands in a container Execute create_container_environment Creates a new Docker container with specified image

WRITE 3 tools

Write create_file_in_container Creates a file in a container Write export_dockerfile exports a docker file to create a persistant environment Write save_container_state Saves the container state to a persistent container

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Sandbox MCP Server

Can an AI agent delete data through the Sandbox MCP Server MCP server? +

Yes. The Sandbox MCP Server server exposes 1 destructive tools including exit_container. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Sandbox MCP Server? +

The Sandbox MCP Server server has 3 write tools including create_file_in_container, export_dockerfile, save_container_state. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Sandbox MCP Server.

How many tools does the Sandbox MCP Server MCP server expose? +

6 tools across 2 categories: Execute, Write. 0 are read-only. 6 can modify, create, or delete data.

How do I enforce a policy on Sandbox MCP Server? +

Register the Sandbox MCP Server MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Sandbox MCP Server tool call.

Deterministic rules across all 6 Sandbox MCP Server tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON SANDBOX →

Free to start. No card required.

6 Sandbox MCP Server tools catalogued and risk-classified — across an index of 43,000+ MCP servers.