Skip to main content
Glama
OpenCyber Harness
by mitkox

oc_theharvester

Destructive

Run theHarvester in an isolated engagement workspace to collect OSINT/enumeration data from explicit argv tokens without shell parsing; pass arguments as an array and use relative artifact paths.

Instructions

Run theharvester from the OpenCyber enumeration toolkit. The container executes theHarvester 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_theharvester"
  }
}

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

A3.6/5.0
Behavior4/5

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

Annotations already declare destructive=true, openWorld=true, readOnly=false and non-idempotent, so the risk profile is covered. The description adds genuinely useful context beyond that: the binary is executed directly with supplied argv tokens and shell parsing is never used, which tells the agent arguments are passed literally, plus the engagement-namespace scoping and relative-path convention. It does not mention timeouts or expected runtime for a long-running recon binary.

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, then execution semantics, then working-directory convention. No filler or repetition; the only minor weakness is that the third sentence is a bit terse about what an 'engagement artifact' path looks like.

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 annotations carry the safety profile. However, for an arbitrary-argv binary execution tool in a catalog of dozens of recon tools, the definition never says what kind of results theHarvester produces or bounds on runtime, leaving the agent to guess whether it is the right recon step.

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% across four parameters, so the description must carry the load. It meaningfully explains `arguments` (raw argv tokens, no shell interpretation) and implies `working_directory` via the relative-path note, but `stdin` and the exact semantics of `engagement_id` (namespace selection/authorization scope) are left undocumented.

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?

The description names a specific verb ("Run") and a specific resource ("theharvester from the OpenCyber enumeration toolkit"), and identifies the exact binary invoked, which is enough to distinguish it from the many sibling binaries. It stops short of stating what theHarvester actually enumerates (emails, hosts, subdomains), so an agent relies on prior knowledge of the tool.

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?

Usage context is only implied: the tool is for running theHarvester, and the note about the engagement namespace and relative artifact paths gives invocation guidance. There is no explicit when-to-use/when-not framing, no prerequisites, and no pointer to any alternative recon sibling (e.g. amass, autorecon) despite a large sibling 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