Skip to main content
Glama
OpenCyber Harness
by mitkox

oc_pwntools

Destructive

Execute pwn commands in an isolated engagement workspace to run binary exploitation workflows with direct argv execution and optional stdin or working paths.

Instructions

Run pwntools from the OpenCyber binary toolkit. The container executes pwn 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_pwntools"
  }
}

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
Behavior3/5

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

Annotations already declare destructiveHint=true, readOnlyHint=false and openWorldHint=false, so the safety profile is covered. The description adds genuinely non-obvious behavior – argv-only execution with no shell parsing – but says nothing about what happens on failure, whether output is captured, how stdin takes effect, or the consequences of running arbitrary binaries against engagement state.

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 tight sentences, front-loaded with what runs and how, then scoping. No filler; each sentence adds information. Minor opportunity lost by not folding the stdin/path guidance into one clause.

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 described. However, for an arbitrary-code-execution tool with a destructive annotation and four undocumented parameters, the definition omits stdin handling and any error/failure behavior, leaving the agent to guess at two parameters.

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 usefully explains `arguments` as raw argv tokens (not a shell string) and implies `working_directory` semantics via relative-path guidance, but leaves `stdin` completely unaddressed and only gestures at `engagement_id` through "selected engagement namespace".

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?

Names a specific verb and resource ("Run pwntools", "executes `pwn`") and adds the execution model – direct argv, no shell parsing – which distinguishes it from a generic shell tool like oc_bash. It stops short of naming an alternative, but the resource is unambiguous.

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 contextual instructions ("Runs from the selected engagement namespace; use relative paths for engagement artifacts") that tell the agent how to frame a call, but never states when to choose this over a shell or a purpose-built analysis tool, nor any preconditions or exclusions.

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