Skip to main content
Glama
Sign In
KubeGuard-MCP

KubeGuard-MCP

by Lokesh-Guttikonda
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

Audit cluster risk

audit_cluster_risks
Read-onlyIdempotent

Aggregates Kubernetes manifests and kubectl, Docker, and Helm commands into a 0-100 risk score with top risks, RBAC escalation paths, secret exposure counts, and command verdicts.

Instructions

Aggregate risk across manifests (workloads, Services, Secrets, Roles/Bindings) and a list of kubectl/docker/helm commands into one 0-100 risk score with the top risks, RBAC escalation paths, secret exposure counts and per-command zero-trust verdicts.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "audit_cluster_risks"
  }
}

Input Schema

NameRequiredDescriptionDefault
roleNooperator
commandsNoCommands to classify
manifestsNoManifest text, or {filename: content} for several files

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered. The description adds genuine value beyond them by enumerating what the analysis produces: an aggregate 0-100 score, top risks, RBAC escalation paths, secret exposure counts and per-command zero-trust verdicts.

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 dense sentence that front-loads the action and ends with the concrete outputs. No filler, though the parenthetical resource list makes it longer than strictly necessary.

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?

With no output schema, the description carries the return-value burden and does so well by listing every output element. The remaining gap is the 'role' parameter's effect and what happens when manifests or commands are omitted (all parameters optional).

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 coverage is 67%, and the description maps loosely to two parameters by naming manifest kinds (workloads, Services, Secrets, Roles/Bindings) and describing commands as kubectl/docker/helm. However, the 'role' enum (viewer/operator/admin) is not explained anywhere, and it is unclear how the role changes the scoring output.

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 ('Aggregate') and resources ('manifests ... and a list of kubectl/docker/helm commands') plus the produced artifact ('one 0-100 risk score'). It implicitly distinguishes itself from siblings by being the aggregate over manifests and commands rather than the single-purpose validate_manifest or classify_command, but never names those siblings explicitly.

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?

Usage is only implied: the agent can infer this is the umbrella audit for when it has both manifests and commands. There is no explicit when-to-use or when-not-to-use, and no routing such as 'use classify_command for a single command instead'.

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