instabox-mcp

Read a file or list a directory in a machine

instabox_list_files

Read-onlyIdempotent

Lists a directory (up to 5,000 entries, directories first) or reads a text file (up to 256 KiB) from a running cloud machine as root; binary files return metadata only.

Instructions

List a directory (up to 5000 entries, directories first) or read a text file (up to 256 KiB) from a machine, live and as root. Binary files come back with binary: true and no content. Use instabox_exec for larger files. The machine must be running (an idle-paused one is woken).

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_files"
  }
}

Input Schema

Name	Required	Description	Default
`id`	Yes	Machine ID (m_...) or its unique name
`path`	No	Absolute path (default /)	/

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 1, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description still adds real behavioral detail: 5000-entry and 256 KiB caps, directories listed first, binary files returned as `binary: true` with no content, root-level live access, and the paused-machine wake behavior. These are exactly the surprises an agent needs pre-call.

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, limits and semantics front-loaded before the alternative-tool pointer and the prerequisite. Every clause carries distinct information.

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?

With no output schema, the description does the work of describing the return shape (entries, ordering, binary flag, no content). The only gap is truncation/overflow behavior past the stated caps, which matters for a listing tool but is a minor omission given everything else covered.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3; the description earns an extra point by clarifying that `path` may point at either a directory or a file and that `id` accepts a name as well as an m_ id. It does not, however, say what happens to entries beyond the 5000 cap or how truncation is signalled.

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

Purpose5/5

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

States a specific dual verb (list directory / read text file) against a named resource (a machine), and immediately scopes it with entry and byte limits. An agent can distinguish it from instabox_exec and instabox_write_file without opening any schema.

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

Usage Guidelines5/5

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

Explicitly routes the agent to instabox_exec for larger files, and states the prerequisite that the machine must be running (with idle-paused machines woken automatically). That is a when-to-use plus a when-to-use-something-else in a single sentence.

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