Skip to main content
Glama
OpenCyber Harness
by mitkox

oc_urlfinder

Destructive

Discover and collect URLs from web targets by running URL-finding commands with explicit arguments in an engagement workspace, using relative paths for engagement artifacts.

Instructions

Run urlfinder from the OpenCyber web toolkit. The container executes urlfinder 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_urlfinder"
  }
}

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

C2.6/5.0
Behavior3/5

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

Annotations already declare destructive=true, openWorldHint=true, idempotentHint=false, so the risk profile is conveyed for free. The description does add real behavior beyond that: argv tokens are passed directly and shell parsing is never used, which tells an agent how to quote/construct arguments and that shell metacharacters are inert. It still omits what the tool writes or alters on disk, which matters for a destructive 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 compact sentences with no filler, and the execution model is stated up front before the path convention. Nothing is redundant, though the space is spent on mechanics rather than purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive, open-world, non-idempotent tool this definition leaves the agent without a functional account of what urlfinder does or what it mutates, and stdin handling is unexplained. An output schema exists so return values needn't be described, but the pre-invocation picture is still thin relative to the risk annotations.

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 coverage is 0%, so the description must carry the load; it gives useful meaning for `arguments` (raw argv, no shell interpretation) and `working_directory` (relative artifact paths scoped to the engagement namespace). It says nothing about the `stdin` parameter or what `engagement_id` concretely controls, leaving gaps across the four parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose2/5

Does the description clearly state what the tool does and how it differs from similar tools?

"Run urlfinder from the OpenCyber web toolkit" restates the tool name and only locates it in a product family; it never says what urlfinder actually does (URL/archive discovery) or what effect invoking it has. An agent that doesn't already know the underlying binary learns nothing functional from the description.

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 when-to-use guidance, no condition under which a sibling tool would be preferred, and no prerequisites or exclusion criteria. The only usage-adjacent statement is "use relative paths for engagement artifacts," which is a path convention rather than guidance on selecting this tool.

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