Skip to main content
Glama
OpenCyber Harness
by mitkox

oc_api_fuzz

Destructive

Run bounded single-parameter API fuzzing against authorized targets with caller-selected payloads and request limits, while preserving complete response evidence.

Instructions

Run a caller-bounded, single-parameter API fuzz matrix against an authorized target and preserve complete response evidence. The caller selects payloads and max_requests.

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>",
      "base_url": "<base_url>",
      "path": "<path>",
      "method": "<method>",
      "location": "<location>",
      "parameter": "<parameter>",
      "payloads": "<payloads>",
      "max_requests": "<max_requests>"
    },
    "name": "oc_api_fuzz"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYes
methodYes
headersNo
timeoutNo
base_urlYes
locationYes
payloadsYes
base_bodyNo
parameterYes
max_requestsYes
engagement_idYes
follow_redirectsNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.3/5.0
Behavior3/5

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

Annotations already declare destructiveHint=true, openWorldHint=true, non-idempotent, so the agent knows this is a real, state-affecting network operation. The description adds that requests are bounded by max_requests and that complete response evidence is preserved, but it omits rate limiting, whether findings are recorded, and what target state may be altered.

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?

Two tight sentences with the core action front-loaded and no filler; every clause carries information about scope, bounding, and evidence retention.

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 explained, and the destructive/open-world nature is covered by annotations. However, with 8 required parameters and zero schema documentation, the description leaves too many inputs (notably location and engagement_id) unexplained for a tool of this complexity.

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 12 parameters, so the description carries the full burden, yet it only explains payloads and max_requests. Critical inputs like location (where the parameter is injected), parameter, engagement_id, method, base_body, timeout, and follow_redirects receive no meaning at all.

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 a single-parameter API fuzz matrix against a target, bounded by the caller. The 'single-parameter' scoping and 'caller selects payloads' framing make its scope distinct from generic request tools, though no sibling is named for contrast.

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?

The phrase 'against an authorized target' implies a prerequisite (authorization) and 'caller-bounded' implies the max_requests cap governs usage, but there is no explicit when-to-use vs. when-not guidance and no alternative tool is named.

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