Skip to main content
Glama

Inspect Engine Archive

inspect_engine_archive
Idempotent

Inspect Unity IL2CPP metadata, Godot .pck, and Electron .asar archives without external game-engine toolchains, recovering C# types, methods, string literals, and packed file entries.

Instructions

Inspect a Unity IL2CPP global-metadata.dat binary (versions 24..31) or Godot Engine resource pack (.pck v1/v2/v3) in pure TypeScript without external game-engine toolchains or target execution. Recovers IL2CPP image assemblies, C# TypeDefinitions (namespaces, names, value/enum flags, method/field counts), MethodDefinitions (declaring types, parameter counts, metadata tokens), string literals, and Godot res:// packed file entries (offsets, sizes, MD5 digests, encryption flags).

Example tool call

This call uses example arguments supplied in the tool’s input schema.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "path": "/artifacts/global-metadata.dat",
      "max_files": 2000,
      "max_types": 1000,
      "max_methods": 2000,
      "max_strings": 1000
    },
    "name": "inspect_engine_archive"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesAbsolute filesystem path to a Unity IL2CPP global-metadata.dat binary, Godot Engine .pck archive, or Electron .asar archive.
max_filesNoMaximum number of bundled files to return for Godot .pck or Electron .asar archives (default 2000).
max_typesNoMaximum number of C# TypeDefinitions to return for IL2CPP metadata (default 1000).
max_entriesNoOptional alias for max_files: maximum number of archive entries/files to return.
max_methodsNoMaximum number of C# MethodDefinitions to return for IL2CPP metadata (default 2000).
max_stringsNoMaximum number of IL2CPP string literals to return (default 1000).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior3/5

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

Annotations already declare destructiveHint=false, idempotentHint=true and openWorldHint=false, so the safety profile is largely covered. The description adds real context — pure-TypeScript parsing, no target execution, supported format versions — but is silent on truncation behavior for the max_* limits, behavior on malformed/unsupported binaries, and on why readOnlyHint is false for what reads as a read-only parser, a mild tension worth surfacing.

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 dense sentences that front-load the verb, accepted formats, and version ranges before the enumeration of recovered data. There is no filler, though the long parenthetical enumerations make it dense to scan.

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?

With six parameters, no output schema, and full schema coverage, the description needs to carry the return-value and edge-case story. It does describe the kinds of data returned, but omits Electron .asar support entirely and says nothing about truncation or failure modes, leaving a meaningful gap for a multi-format parser.

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%, so the baseline is 3. The description does add some meaning by mapping output categories (type definitions, method definitions, string literals, packed file entries) onto the max_types/max_methods/max_strings/max_files knobs, but it never explains the max_entries alias or what happens when limits are hit.

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 two precisely scoped resources — Unity IL2CPP global-metadata.dat (v24..31) and Godot .pck (v1/v2/v3) — and enumerates what it recovers. However, the schema's own `path` description also accepts Electron .asar archives, which the description never mentions, so coverage of the tool's stated inputs is incomplete. It also does not differentiate itself from siblings such as inspect_keyed_archive or inspect_electron_page.

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

Usage Guidelines2/5

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

There is no when-to-use or when-not-to-use guidance and no named alternative. The phrase 'without external game-engine toolchains or target execution' explains the tool's implementation constraint, not the conditions under which an agent should pick it over another inspector. An agent must infer routing purely from the file formats listed.

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