Skip to main content
Glama
OpenCyber Harness
by mitkox

oc_http_intruder

Destructive

Runs caller-bounded payload iteration through an HTTP workbench session against one query, header, body, or path parameter to test input handling.

Instructions

Run caller-bounded sniper-style payload iteration through an HTTP workbench session against one query, header, body, or path location.

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>",
      "session_id": "<session_id>",
      "method": "<method>",
      "url": "<url>",
      "location": "<location>",
      "parameter": "<parameter>",
      "payloads": "<payloads>",
      "max_requests": "<max_requests>"
    },
    "name": "oc_http_intruder"
  }
}

Input Schema

NameRequiredDescriptionDefault
urlYes
bodyNo
methodYes
headersNo
timeoutNo
locationYes
payloadsYes
parameterYes
session_idYes
max_requestsYes
engagement_idYes

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 the destructive, non-idempotent, open-world profile, so the safety burden is partly carried. The description adds real scope information ('caller-bounded' via max_requests, one location per invocation), but says nothing about request pacing, rate limiting, what happens to the session's history, or whether partial failure after N payloads is recorded.

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?

A single front-loaded sentence with no filler, but it is dense and stacks three undefined qualifiers ('caller-bounded', 'sniper-style', 'workbench session') before reaching the actionable content.

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, 11-parameter tool with zero schema descriptions and eight required arguments, one sentence is markedly under-specified. An output schema exists so return values need not be explained, but the per-parameter contract and the safety expectations of a destructive fuzzing run are not adequately covered.

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% across 11 parameters, so the description must compensate and only partially does: it clarifies that location selects among query/header/body/path, that parameter names the single injection point, and that max_requests bounds the run. It leaves url, method, headers, body, timeout, engagement_id, and payloads format entirely undocumented anywhere.

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 action (payload iteration) and its target (one query, header, body, or path location) in an HTTP workbench session, which is meaningfully different from the sibling oc_http_request/oc_http_repeater single-request tools. However, jargon like 'sniper-style' and 'caller-bounded' carry much of the meaning and are never defined, so the purpose is clear only to a reader already versed in fuzzing terminology.

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 never says when to choose this over oc_http_repeater, oc_http_request, or a generic fuzzing tool, nor does it state preconditions such as needing an existing workbench session or engagement. 'Sniper-style' implies one injection point per run but this is left implicit rather than stated as a usage rule.

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