Docker MCP Sandbox

create_sandbox

Spawn an isolated Docker container sandbox with a dedicated /workspace, CPU and memory limits, and a bash/sh environment for safe command and file operations.

Instructions

Spawns a new isolated Docker container sandbox with a dedicated /workspace directory, resource quotas, and bash/sh environment.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "create_sandbox"
  }
}

Input Schema

Name	Required	Description	Default
`env`	No	Optional environment variables
`image`	No	Docker image to use for the sandbox (e.g. node:20-alpine, python:3.11-slim)	node:20-alpine
`cpuLimit`	No	CPU cores limit (default 1.0)
`memoryLimitMb`	No	RAM limit in MB (default 512)

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Nov 10, 2026

TDQS

B3.2/5.0

Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full disclosure burden, and it does add real context: isolation via Docker, a persistent /workspace, enforced resource quotas, and an available shell. It does not say what identifier is returned, how long the sandbox lives, whether it starts immediately or must be torn down manually, or what happens on resource exhaustion.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single front-loaded sentence that names the resource first and enumerates the salient properties without filler. It is dense but every clause carries information, with no repetition of defaults or types.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a creation tool with four parameters, no annotations, and no output schema, the definition covers what gets created but not the return value (a sandbox ID is presumably required to use execute_command or destroy_sandbox) or lifecycle expectations. Adequate to call, but incomplete for chaining into the rest of the toolset.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so every parameter (env, image, cpuLimit, memoryLimitMb) is already documented with types and defaults. The description's reference to 'resource quotas' loosely corresponds to the CPU/memory parameters but adds no syntax, constraints, or format details beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb plus resource ('Spawns a new isolated Docker container sandbox') and adds distinguishing attributes: a dedicated /workspace, resource quotas, and a bash/sh environment. That is enough to tell it apart from destroy_sandbox and list_sandboxes by implication, though no sibling is named explicitly.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no when-to-use or when-not-to-use guidance, no mention of prerequisites such as needing an existing container runtime, and no pointer to the natural follow-on tools (execute_command, destroy_sandbox). The intended usage is only inferable from the verb 'spawns'.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server