Skip to main content
Glama

Open Binary

open_binary
Idempotent

Validates and opens local binaries, executables, archives, or analysis databases for reverse engineering; supports explicit DOS COM and raw-binary interpretation when headers are absent.

Instructions

Open a local executable, application bundle, archive, JavaScript, source map, plist, or analysis database after validation. format=dos-com explicitly interprets 1..65280 headerless bytes as a DOS COM analysis image. format=raw-binary interprets headerless bytes with a required architecture and entry_point; file offset 0 maps at that address. Omission preserves header-based detection. provider_id selects one deep provider or deterministic auto selection; the binding remains stable until close or an explicit switch, with no failure fallback. Reopening the same target and profile retains its active database and metadata edits. An optional analysis snapshot is imported atomically and must match the binary identity, concrete provider, and canonical analysis profile exactly; importing into a session with metadata mutations requires closing and reopening it first.

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": "/tmp/fixture"
    },
    "name": "open_binary"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesAbsolute local filesystem path for the analysis target; relative paths are rejected.
formatNoExplicit headerless interpretation: dos-com or raw-binary. Omission preserves header-based detection.
providerNoAlias for provider_id: selects one deep provider ('ghidra', 'hopper', 'ida-mcp', 'zero-install') or 'auto'.
entry_pointNoCaller-supplied load and entry address (0xhex). File offset 0 is mapped here. Required with format=raw-binary; rejected otherwise.
provider_idNoExact deep-analysis provider ID, or automatic selection when omitted.
architectureNoCaller-supplied CPU family. Required with format=raw-binary; rejected otherwise.
snapshot_pathNoAbsolute local filesystem path for the analysis snapshot; relative paths are rejected.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only declare write/idempotent/open-world/non-destructive flags, and the description adds substantial behavior beyond them: provider binding stays stable until close or explicit switch with no failure fallback, reopening the same target and profile preserves the active database and metadata edits, and snapshot import is atomic and must match identity, provider, and profile exactly. Those are precisely the non-obvious traits (state persistence, no auto-fallback, import preconditions) an agent needs and that the annotations cannot express.

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?

Despite its length, the text is front-loaded with the action and resource set, then moves in order from format modes to provider binding to reopening to snapshot import. Nearly every clause carries a constraint or invariant that changes how the call is made, so there is little filler.

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 7-parameter session-opening tool with no output schema, the description covers the risky and ambiguous paths (headerless formats, provider pinning, state retention, snapshot compatibility). It leaves unstated what "validation" actually checks, what a successful open returns for subsequent session tools to reference, and how failures surface, which is a modest but real gap given there is no output schema to fall back on.

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, but the description adds real meaning the schema lacks: the 1..65280-byte limit for dos-com, the fact that file offset 0 maps to the supplied entry_point for raw-binary, that omission preserves header-based detection, and that provider_id resolves to a deterministic auto selection. It does not fully explain the provider/provider_id alias relationship or snapshot_path matching details beyond identity, keeping it just short of the top score.

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?

The first sentence gives a specific verb ("Open") and enumerates the concrete resource classes it accepts (executable, app bundle, archive, JavaScript, source map, plist, analysis database), plus the validating precondition. An agent can distinguish this session-opening tool from siblings like open_jeb_project or the inspect_* tools without consulting the schema.

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

Usage Guidelines4/5

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

It gives clear conditional guidance: omit format to keep header-based detection, use dos-com for 1..65280 headerless bytes, use raw-binary only with architecture and entry_point, and close/reopen before importing a snapshot into a session with metadata mutations. What is absent is any explicit statement about when to prefer this tool over a sibling opener, so it stops at conditional context rather than full alternative routing.

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