Skip to main content
Glama
OpenCyber Harness
by mitkox

oc_python

Destructive

Run inline Python source or an engagement-relative script file inside the OpenCyber container to execute security tasks asynchronously with client-cancellable jobs.

Instructions

Run inline Python source or an engagement-relative Python file inside the OpenCyber container. Provide exactly one of source or path. Execution uses the OpenCyber Python environment and is asynchronous and client-cancellable.

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>"
    },
    "name": "oc_python"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathNo
stdinNo
sourceNo
environmentNo
engagement_idYes
script_argumentsNo
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, openWorldHint=true and idempotentHint=false, so the risk profile is covered. The description adds genuinely useful context beyond that — execution happens inside the OpenCyber container, is asynchronous, and is client-cancellable — but it never explains what the destructive potential actually means (filesystem writes, network egress) or any timeout/limit behavior.

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 with no filler, and the source/path exclusivity rule is stated early. It could be tightened slightly by folding the environment note into the first sentence, but nothing is wasted.

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 described. But for a 7-parameter, destructive, open-world execution tool, the definition leaves most parameters and the practical safety envelope (network access, working-directory scope, environment variable injection) undocumented.

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%, so the description must carry parameter meaning, and it only explains the source-vs-path mutual exclusion. Five other parameters (stdin, environment, engagement_id, script_arguments, working_directory) receive no explanation at all in either the schema or the description.

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 gives a specific verb and resource ('Run inline Python source or an engagement-relative Python file inside the OpenCyber container'), which is far more informative than the bare name. It implicitly distinguishes itself from oc_bash by naming Python explicitly, but never states the distinction outright, so a 4 rather than 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 Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

'Provide exactly one of source or path' is a real usage constraint that tells the agent how to combine the two main inputs. However, there is no guidance on when to choose this tool over oc_bash for shell work, no prerequisites, and no note on when inline source is preferable to a file.

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