Skip to main content
Glama
OpenCyber Harness
by mitkox

oc_curl

Destructive

Execute curl requests in an isolated engagement workspace with direct argv token handling—no shell parsing—and relative paths for artifacts.

Instructions

Run curl from the OpenCyber web toolkit. The container executes curl 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_curl"
  }
}

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

B3.3/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true, openWorldHint=true and non-idempotent, so the safety profile is covered. The description adds genuinely useful behavior beyond that: argv tokens are passed without shell parsing, meaning no pipes, redirects or globbing, which materially changes how an agent must construct the call. It stops short of describing error/exit-code reporting.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short sentences, front-loaded with the operation, then the safety-critical no-shell detail, then the path convention. No filler and nothing buried.

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 no explanation, and the no-shell execution model is well covered. However, with zero schema description coverage the omission of stdin semantics, engagement_id meaning, and how failures surface leaves real gaps for an agent constructing calls.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

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 burden. It clarifies that `arguments` are argv tokens rather than a shell string, which is valuable, but says nothing about `stdin`, `engagement_id`, or the exact meaning of the default working directory ('.') relative to the 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?

States a specific verb and resource: run curl from the OpenCyber web toolkit, with the container executing curl directly. An agent immediately knows this is a raw curl executor rather than, say, a structured HTTP client. It does not name a sibling runner such as oc_bash to delineate the boundary, which keeps it 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?

The description gives execution context (runs from the selected engagement namespace, relative paths for engagement artifacts) but never says when to choose this over oc_bash or a dedicated HTTP tool, nor any precondition or exclusion. Usage is only inferable from the tool name.

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