Skip to main content
Glama

thanaton_exec_command

Execute shell commands in an isolated, hardware-virtualized MicroVM sandbox and return stdout, stderr, exit code, and execution latency.

Instructions

Execute an arbitrary shell command (bash, sh) inside an isolated, hardware-virtualized MicroVM sandbox. Returns stdout, stderr, exit code, and execution latency.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "command": "<command>"
    },
    "name": "thanaton_exec_command"
  }
}

Input Schema

NameRequiredDescriptionDefault
commandYesThe shell command to execute inside the MicroVM (e.g., 'python3 -c "print(2+2)"', 'npm test', 'git status')
sandbox_idNoOptional existing sandbox ID. If omitted, an ephemeral sub-6ms sandbox will be provisioned automatically.
timeout_msNoMaximum execution timeout in milliseconds (default: 15000)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.6

TDQS

B3.3/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden. It usefully discloses the isolation model (hardware-virtualized MicroVM) and the return payload (stdout, stderr, exit code, latency). But for an arbitrary-command-execution tool it says nothing about destructive potential, network or filesystem reach, credential exposure, whether the sandbox is destroyed afterward, or permission requirements.

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

Conciseness5/5

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

Two sentences, zero filler. The capability is front-loaded and the return contract follows immediately, so an agent can read the essential facts in a single pass.

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 tool whose whole job is running arbitrary code with no annotations and no output schema, the definition covers the environment and return shape but leaves major operational questions open: side effects and reversibility, timeout failure behavior, and how it relates to the near-neighbor run_code sibling.

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%: the command, sandbox_id, and timeout_ms parameters each already carry their own descriptions, including examples and the 15s default. The description adds no parameter-level meaning beyond that, so the baseline 3 applies.

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?

States a specific verb and resource: execute an arbitrary shell command (bash, sh) inside an isolated, hardware-virtualized MicroVM sandbox. That is far more specific than the name alone. However, it never distinguishes itself from the sibling thanaton_run_code, which by name plausibly overlaps, so an agent cannot pick between them from the description alone.

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

Usage Guidelines3/5

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

Usage is implied rather than stated: the tool is the one to call for shell-level commands in a sandbox. There is no explicit when-to-use, when-not-to-use, or pointer to alternatives such as thanaton_run_code or thanaton_spawn_sandbox plus thanaton_run_code, which matters given the sibling overlap.

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

Deploy Server

Other Tools