Skip to main content
Glama
OpenCyber Harness
by mitkox

oc_scalpel

Destructive

Carve files from forensic artifacts by running Scalpel with explicit arguments in an isolated engagement workspace, avoiding shell parsing.

Instructions

Run scalpel from the OpenCyber forensics toolkit. The container executes scalpel 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_scalpel"
  }
}

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

B3.2/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, idempotentHint=false and openWorldHint=false, so the safety profile is covered by structured data. The description adds genuinely useful execution semantics: argv is passed directly with no shell parsing, and execution is scoped to the engagement namespace. It does not say that scalpel writes carved output files to disk, where those artifacts land, or that existing files could be overwritten — a notable omission 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, front-loaded with the action, then the execution model, then the path convention. Nothing is redundant, though the namespace/path sentence is slightly elliptical about which parameter it maps to.

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

Completeness4/5

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 the description covers the execution model and path scoping that the schema leaves blank. The remaining gap is behavioral: no mention of carved output artifacts or overwrite risk, which matters given destructiveHint=true.

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 and it only partially does. It clarifies `arguments` as raw argv tokens to scalpel, ties `engagement_id` to the selected engagement namespace, and implies `working_directory` via the relative-path instruction; `stdin` is never mentioned and no argument format or example is given.

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 `scalpel` binary from the OpenCyber forensics toolkit, with the invocation mechanism (argv tokens, no shell) spelled out. An agent can tell exactly which binary this wraps. It does not differentiate itself from sibling carving/inspection tools such as oc_binwalk, so it falls 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 when-to-use or when-not-to-use guidance and no named alternative among the many oc_* siblings. The only contextual instruction is operational ('runs from the selected engagement namespace; use relative paths'), which tells the agent how to invoke rather than when to choose 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