mcp-server-wazuh

Search MITRE

search_mitre

Read-onlyIdempotent

Retrieves MITRE techniques known to the Wazuh manager to map threats and plan detections. Page results with limit and offset.

Instructions

List MITRE techniques known to the manager.

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": "search_mitre"
  }
}

Input Schema

Name	Required	Description	Default
`limit`	No	Page size, from 1 to 100
`offset`	No	Result offset, from 0 to 10000

Output Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv1.0.0Nov 4, 2026

TDQS

B3.2/5.0

Behavior3/5

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

The annotations already declare readOnlyHint, idempotentHint, openWorldHint and destructiveHint=false, so safety is fully covered and the bar is lower. The description adds only the scoping phrase "known to the manager", which gestures at a bounded dataset but does not clarify it; it says nothing about pagination behavior or what happens beyond offset limits.

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 short sentence with no filler, so nothing is wasted. It is, however, arguably terse to the point of underspecification, and there is no structure directing the agent to alternatives.

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?

With annotations covering safety and an output schema covering return values, the description's burden is limited to purpose and usage, and it half-delivers. For a zero-required-parameter paged listing tool the definition is usable, but the ambiguity of "known to the manager" and the list-versus-search mismatch leave real gaps.

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 100%, with limit and offset both documented in the schema, so the description need not restate them. It adds no meaning beyond the schema – notably it never confirms that this is a paginated, unfiltered listing, which is exactly the clarification an agent would want given the "search" name.

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?

"List MITRE techniques" gives a specific verb plus resource, and MITRE techniques are clearly distinct from the sibling resources (events, findings, vulnerabilities, agents, groups). The qualifier "known to the manager" is ambiguous, though – it is unclear whether this means techniques the manager can detect, has configured, or has data for – and the name says "search" while the description says "list", with no query parameter in the schema.

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?

No when-to-use guidance is offered: nothing says when to pick this over search_findings or search_vulnerabilities, whether techniques can be filtered by ID or tactic, or how results relate to other search_* tools. The only implied usage is that this is the MITRE reference lookup, which the agent must infer.

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

Deploy Server