Skip to main content
Glama
OpenCyber Harness
by mitkox

oc_objdump

Destructive

Disassemble and inspect binaries by running objdump with direct argv tokens inside an engagement workspace, avoiding shell parsing for controlled binary analysis.

Instructions

Run objdump from the OpenCyber binary toolkit. The container executes objdump directly with the supplied argv tokens; shell parsing is never used. Runs from the selected engagement namespace; use relative paths for engagement artifacts.

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": {
      "engagement_id": "<engagement_id>",
      "arguments": "<arguments>"
    },
    "name": "oc_objdump"
  }
}

Input Schema

NameRequiredDescriptionDefault
stdinNo
argumentsYes
engagement_idYes
working_directoryNo.

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare destructive=true, openWorld=false, idempotent=false, so the safety baseline is covered. The description adds genuinely non-redundant behavior: commands are executed directly with argv tokens and shell parsing is never used, which tells the agent pipes, globs, redirection, and chained commands will not work and must be expressed as discrete arguments. It does not address what could be destroyed or whether output files can be produced, which is notable for a destructive-flagged tool.

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?

Three sentences, front-loaded with the verb and resource, then execution semantics, then working directory scoping. Almost no filler, though 'from the OpenCyber binary toolkit' adds little beyond the tool name already implying it.

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?

An output schema exists, so return values need not be explained, and the execution model is well covered. However, with a 0%-coverage schema and four parameters, the description should also account for `stdin` and give at least a hint about argument ordering or expected objdump flags to be complete for agent invocation.

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 description coverage is 0%, so the description carries the full burden, and it partially does: `arguments` are 'supplied argv tokens', `engagement_id` maps to 'the selected engagement namespace', and `working_directory` maps to the relative-paths instruction. The `stdin` parameter is never mentioned, a real gap for a tool where feeding binary content on stdin is a plausible mode.

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: run `objdump` via the OpenCyber binary toolkit, with the exec model spelled out (direct argv, no shell). It cleanly distinguishes itself from other sibling `oc_*` tools, but does not name alternatives such as a readelf-style analyzer or binwalk.

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 practical guidance on execution context: run from the selected engagement namespace and use relative paths for engagement artifacts. It offers no when-to-use/when-not guidance relative to the many other binary-analysis siblings in the catalog.

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