instabox-mcp

Browse a snapshot's files

instabox_list_snapshot_files

Read-onlyIdempotent

List a snapshot directory or read a text file from installed software without booting a machine; /data paths are excluded.

Instructions

List a directory or read a text file from a snapshot's installed software without starting a machine. Files under /data are not shown.

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": {
      "id": "<id>"
    },
    "name": "instabox_list_snapshot_files"
  }
}

Input Schema

Name	Required	Description	Default
`id`	Yes	Snapshot ID (sn_..., or im_... for older ones)
`path`	No	Absolute path (default /)	/

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 1, 2026

TDQS

A3.5/5.0

Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds two genuinely useful behaviors not in the annotations: no machine is started, and /data contents are invisible. It stays silent on read behavior for large or binary files, which matters because it claims to read file contents.

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?

Two tight sentences with the capability stated first and the /data caveat second; nothing is padding. Slightly awkward that the name says 'list' while the description also claims read behavior, though the description resolves it.

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

Completeness4/5

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

For a read-only two-parameter tool with full annotation coverage and full schema coverage, this covers what an agent needs to choose and call it. Remaining gaps (output shape of a directory listing, size/type limits when reading a file) are modest, and no output schema exists to absorb them.

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 coverage is 100% and both parameters (id format sn_/im_, absolute path with default /) are fully documented in the schema itself. The description contributes the /data exclusion, a real semantic constraint on path values, but nothing about how a path resolving to a file versus a directory changes the call.

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 specific verbs (list a directory, read a text file) and a specific resource (a snapshot's installed software), and adds a distinguishing constraint ('without starting a machine'). It does not explicitly contrast itself with the closely-named sibling instabox_list_files, which operates on a running machine, so the differentiation is only implicit.

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?

'Without starting a machine' hints at when this is preferable to a machine file listing, but the agent must infer that instabox_list_files/instabox_exec are the alternatives. No explicit when-not guidance beyond the /data exclusion.

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