wazuh-mcp

Read an agent's system inventory

wazuh_agent_inventory

Read-onlyIdempotent

Read inventory collected from an endpoint: packages, processes, ports, network, hardware, OS, hotfixes. Check what is installed, listening, or missing.

Instructions

Read collected inventory from one endpoint: installed packages, running processes, listening ports, network interfaces and addresses, hardware, OS or Windows hotfixes. Use it for questions like 'what is listening on this host', 'is package X installed', or 'what patches are missing'.

Input Schema

TableJSON Schema

Name	Required	Description
`sort`	No	Sort field, '-' prefix for descending.
`limit`	No
`query`	No	Raw Wazuh query filter for precise conditions, e.g. 'local.port=443' for ports or 'state=LISTENING'.
`offset`	No
`search`	No	Substring match across the component's fields, e.g. 'openssl' for packages or 'nginx' for processes.
`agent_id`	Yes	Agent ID, e.g. '001'.
`component`	Yes	Which inventory component to read.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 8, 2026

TDQS

A4.4/5.0

Behavior4/5

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

The annotations (readOnlyHint=true, idempotentHint=true, destructiveHint=false) already cover the key behavioral aspects. The description adds no conflicting information and implicitly confirms read-only behavior by saying 'Read inventory'. No side effects are stated, but none are needed given the annotations.

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?

The description is only two sentences, yet it conveys the full scope (components, sample questions) without padding. It is well-structured for quick parsing and decision-making.

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 an output schema present and the description covering usage and scope, the tool is adequately contextualized. It doesn't mention prerequisites like agent existence or error cases, but these are not essential given the schema and the tool's simplicity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Descriptions for key parameters are helpful: query and search include concrete examples ('local.port=443', 'openssl'), agent_id and component are clearly explained, and sort describes the descending prefix. However, limit and offset lack descriptions, leaving a small gap in schema coverage (71%) that is not fully compensated.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States the exact function—reading system inventory from an endpoint—and lists the specific components (packages, processes, ports, etc.). It also provides concrete example questions that clarify the tool's scope, distinguishing it from sibling tools focused on alerts, rules, or health.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

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

Explicitly tells when to use the tool via example questions ('what is listening on this host', 'is package X installed', 'what patches are missing'). While it doesn't mention alternatives like wazuh_find_software or wazuh_get_agent, the usage scenarios are clear and actionable.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.