Skip to main content
Glama
SunLicense MCP server

SunLicense MCP server

Official

obfuscate_file

Obfuscate a local built file on SunLicense servers and download the protected output beside it; language is auto-detected unless an engine or profile is chosen.

Instructions

Obfuscate a local built file on SunLicense's servers and download the result next to it. The file is read from disk and uploaded straight to SunLicense; it is never shown to the model. The language is detected from the file unless you pass an engine or profile. This waits for the run to finish (it can take a few minutes) and returns the output paths; the exit is an error if the run fails. Needs the obfuscation feature (Lite or Standard).

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": {
      "file": "<file>"
    },
    "name": "obfuscate_file"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileYespath to a local built file (.jar, .zip, .js, .lua, .py); read and uploaded to SunLicense, never shown to the model
configNopath to a local raw engine-config file (advanced; runs the config as-is after checks)
engineNoan engine id, overriding the language's default
productNoa product id, to use that product's linked profile
profileNoa saved profile, by name or id (obfuscation_profiles_list)
outputDirNowhere to write the outputs; defaults to the input file's folder

Output Schema

NameRequiredDescriptionDefault
noteYes
engineYes
statusYes
taskIdYes
outputsYes
languageYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Goes well beyond the annotations: discloses that the file is uploaded to a third party and never shown to the model, that the call blocks for minutes, that output paths are returned, and that failure surfaces as an error. The only gap is that it doesn't say whether partial outputs are left on disk when a run fails.

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?

Front-loaded with the action and destination, then layered with data-handling, override, latency and entitlement facts in separate sentences. Dense but each sentence carries distinct information; only the trailing entitlement note feels tacked on.

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?

Covers the things an agent must know before calling a slow, upload-based mutation: data egress, blocking duration, return shape, error semantics, and feature entitlement. With an output schema present, return values need no further explanation.

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 already 100%, so the baseline is 3; the description adds real inter-parameter meaning by explaining that engine or profile overrides the detected language and that product pulls in that product's linked profile — relationships the flat schema does not express.

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 — obfuscate a local built file on SunLicense's servers — plus the side effect of downloading the result next to the input. No sibling tool is named, but none of the listed siblings are obfuscation-related, so an agent can still place it confidently.

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?

Gives useful preconditions (needs the Lite or Standard obfuscation feature) and explains that language is auto-detected unless an engine or profile is supplied. It never says when to prefer this over an offline/licensing alternative or what to do on entitlement failure, so usage is implied rather than fully routed.

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