Skip to main content
Glama
IBM Aspera CLI

IBM Aspera CLI

Official
by IBM

execute_ascli_command

Run any Aspera CLI (ascli) command in-process and return structured results for transfers, packages, and administration. Show the equivalent bash command line to the user.

Instructions

Execute any ascli (Aspera CLI) command in-process and return its result.

COMMAND DISPLAY (MANDATORY) Whenever you execute an ascli command or present its results, you MUST ALWAYS explicitly show the equivalent command line in your response to the user as bash syntax (e.g. ascli plugin command --option=value).

SYNTAX args is a JSON array of strings mirroring the CLI command line. Element 0 : plugin name (aoc, faspex5, node, server, config, …). Elements 1+: sub-commands, positional arguments, and --option=value flags in any order. Structured values use an extended-value prefix on the relevant element: "@json:{...}" — inline JSON object or array (preferred: no shell quoting) "@preset:name" — expand a saved preset "@base64:..." — base64-encoded value "@val:..." — literal string (no further decoding) "@secret:name" — secret entered by the user on a web page, never visible to you: use it for a secret the user did not give, e.g. "--password=@secret:password" Note: @stdin: is disabled; @ruby:, @file:, @uri:, @env: depend on the security level of the server. A secret (from @secret:, @vault:, @preset:) must be the whole value: no other prefix before it, not in @extend:.

AUTOMATIC FLAGS The server prepends extra_args to every call (default: --interactive=no --transfer.asynchronous=true). Do NOT repeat them. To override one, include it in args: later values take precedence. Commands never prompt: if credentials are missing, an error is returned; report it and stop.

DISCOVERY — never guess command or field names from training data Step 1 — commands of a plugin, with syntax: ["config", "commands", ""] Returns { syntax, description } for every command of that plugin. Notation: mandatory, [] optional, <a|b> enum, <arg...> variadic, arg:Hash typed. A line ending with <command...> and "(see: )" provides the commands of that path: list them with ["config", "commands", "", "", ...] (command words only). Omit to list the commands of all plugins (large). Step 2 — schema of a Hash argument (shown name:Hash), MANDATORY before calling such a command: ["", "", ..., "help"] Put the literal "help" in place of the Hash argument. Returns field names, types, required flags and descriptions. Never infer fields from server error messages. Step 2b — filter parameters of a list command: ["", "", ..., "--query=help"] Step 3 — all --flags of a plugin, with allowed values: ["config", "options", ""] Documentation: ["config", "documentation", "toc"] → { level, title, anchor } per heading ["config", "documentation", "local", ""] → one README section Presets (saved credentials): ["config", "preset", "overview"]

RESULT FORMAT Structured data is always in structuredContent (a JSON object; lists are under "items"). For lists, text content is limited to 100000 bytes (whole items only); when truncated, a WARNING line gives the real total. Read structuredContent.items for the full dataset — never report counts or search results from a truncated text block.

FILE LIST FOR TRANSFERS For all transfers (upload, download, package send, …), append source paths at the end of args — no --sources flag needed.

EXAMPLES ["config", "commands", "aoc"] ["aoc", "admin", "user", "create", "help"] ["config", "options", "aoc"] ["config", "documentation", "local", "leveraging-ai-assistance"] ["aoc", "--preset=myaoc", "packages", "list"] ["aoc", "--preset=myaoc", "admin", "user", "create", '@json:{"email":"a@b.com","name":"Alice"}'] ["aoc", "--preset=myaoc", "packages", "send", '@json:{"name":"pkg","recipients":["user@example.com"]}', "/local/a.txt", "/local/b.txt"] ["server", "--preset=myserver", "upload", "--to-folder=/uploads", "/local/a.txt"] ["server", "browse", "/", "--url=ssh://host:33001", "--username=user", "--password=secret"]

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": {
      "args": "<args>"
    },
    "name": "execute_ascli_command"
  }
}

Input Schema

NameRequiredDescriptionDefault
argsYesascli arguments: first element is the plugin name, followed by action and --option=value flags

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv4.29.0

TDQS

A4.9/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does so: it discloses that the server prepends extra_args, that later flags override earlier ones, that @stdin: is disabled while @ruby:/@file:/@uri:/@env: depend on security level, that @secret: values are never visible, and that secret prefixes must be the entire value.

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?

It is long, but header-delimited sections (SYNTAX, AUTOMATIC FLAGS, DISCOVERY, RESULT FORMAT, EXAMPLES) make it scannable and front-load the core purpose. The mandatory command-display block and repeated example coverage push it slightly past what is strictly needed.

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

Completeness5/5

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

No output schema exists, so the description explains returns itself: structured data lives in structuredContent, lists under "items", text truncated at 100000 bytes with a WARNING carrying the real total, and the instruction to read structuredContent rather than the truncated text. Nothing an agent needs to invoke it correctly is missing.

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

Parameters5/5

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

Schema coverage is 100% and the schema only says the first element is the plugin name, but the description adds a full grammar: element 0 plugin, elements 1+ sub-commands/positionals/flags in any order, and the @json:/@preset:/@base64:/@val:/@secret: extended-value prefixes with worked examples.

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?

Opens with a specific verb and resource: "Execute any ascli (Aspera CLI) command in-process and return its result." That states both the action and the execution model, and no sibling tools exist that need distinguishing.

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 prescribes a workflow: run ["config", "commands", "<plugin>"] before guessing command names, put literal "help" in place of any Hash argument, use --query=help for list filters, and check options/presets. It also states that commands never prompt and that missing credentials produce an error to report and stop on.

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