Skip to main content
Glama
OpenCyber Harness
by mitkox

oc_proxmark3

Destructive

Run Proxmark3 RFID/NFC commands against a passthrough USB device within an engagement namespace, capturing output for authorized physical-layer security testing.

Instructions

Interact with a Proxmark3 RFID/NFC research device. Requires host USB passthrough and the matching Proxmark3 firmware. 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_proxmark3"
  }
}

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

B3.1/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, openWorldHint=true, idempotentHint=false, and readOnlyHint=false, so the safety profile is carried by structured data. The description adds useful environment context the annotations cannot convey: USB passthrough and firmware-matching requirements, namespace scoping, and relative-path handling. It does not disclose that arbitrary proxmark client commands are executed verbatim, nor that effects may persist on physical cards or device state beyond the call.

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 with the device identity, prerequisites, and namespace/path rule front-loaded in that order. Nothing is redundant, though the density means the missing invocation details are conspicuous by their absence rather than trimmed for brevity.

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?

An output schema exists, so return values need no description, but for a command-passthrough wrapper with zero parameter documentation the definition is under-specified. An agent still cannot tell how to format the `arguments` array, whether a shell is involved, or what happens on non-zero exit, which are the details that determine correct invocation.

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 carries the full burden and largely fails it. Only working_directory gets indirect treatment via 'use relative paths for engagement artifacts'; the central `arguments` array, `stdin`, and `engagement_id` are never explained, leaving the agent to guess how commands are formed and whether stdin is piped to the client.

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 resource and its domain: a Proxmark3 RFID/NFC research device, which distinguishes it from the other hardware-adjacent siblings like oc_avrdude or oc_bladerf. However, 'Interact with' is vague about the actual mechanism — it never says whether it shells out to the proxmark3 client with the supplied argument array or performs some higher-level operation, so the agent must infer the invocation model.

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?

It states real prerequisites (host USB passthrough, matching firmware) and scoping guidance (runs from the selected engagement namespace, use relative paths), which is genuine when-to-use context. It gives no alternatives to prefer, no when-not-to-use conditions, and no warning about when running commands is risky versus benign, which matters for a device that can write to or brick tags.

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