Skip to main content
Glama
OpenCyber Harness
by mitkox

oc_ghidra

Destructive

Runs Ghidra directly with supplied arguments in a selected engagement workspace to analyze binaries; no shell parsing is used.

Instructions

Run ghidra from the OpenCyber binary toolkit. The container executes ghidra 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_ghidra"
  }
}

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

B3.4/5.0
Behavior4/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false, and idempotentHint=false, so the risk profile is covered. The description adds real behavioral context beyond that: argv tokens are passed directly with no shell parsing (an injection-safety guarantee), and the process runs scoped to the selected engagement namespace.

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 short sentences, front-loaded with purpose followed by execution semantics and path scoping. No filler, though the toolkit attribution in the first sentence is largely redundant with the tool name.

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?

The output schema exists, so return values need no explanation, and the safety annotations are covered. However, stdin handling is undocumented and there is no steer on when a Ghidra run is the right choice versus other reverse-engineering siblings, which matters for a destructive, non-idempotent exec wrapper.

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 0%, so the description must carry the load. It implies the mapping of `arguments` to argv tokens, `engagement_id` to the active namespace, and `working_directory` to relative engagement paths, but it never mentions the `stdin` parameter at all, leaving one of four parameters unexplained anywhere.

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 the `ghidra` binary from the OpenCyber toolkit. The agent knows exactly what will execute. It does not differentiate from sibling binary wrappers such as oc_apktool or oc_binwalk, so it stops short of a 5.

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 explicit when-to-use or when-not-to-use guidance, and no alternative tool is named. The operational note about relative paths and the engagement namespace is invocation hygiene, not selection guidance.

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