Skip to main content
Glama
aether-mcp

aether-mcp

Official
by filescanio

Pivot: similar samples

find_similar
Read-only

Find samples with code and behavior similar to a given SHA-256 file, returning matches with similarity percentages, verdicts, first-seen dates, and tags to help identify malware variants.

Instructions

Samples whose code and behavior are similar to a file (Aether similarity search), the most similar and the most recent ones, with similarity %, verdict, first seen and tags. To open them, get their report_ids with one lookup_hash call (up to 100 SHA-256s).

When to use: To find variants of a sample.

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": {
      "sha256": "<sha256>"
    },
    "name": "find_similar"
  }
}

Input Schema

NameRequiredDescriptionDefault
sha256YesSHA-256 of the file.
min_similarityNoMinimum code similarity in %.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

A4.1/5.0
Behavior4/5

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

readOnlyHint=true already covers safety, and the description goes beyond it by disclosing the underlying engine, the shape of the returned fields, and the batch follow-up workflow with its 100-hash cap. It omits result-count limits, ordering rules beyond 'most similar and most recent', and whether the search is threshold-truncated.

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?

Three short sentences, front-loaded with the result description, then the follow-up workflow, then the trigger. Minor ambiguity in 'the most similar and the most recent ones', which gestures at ordering without pinning it down.

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 usefully compensates by naming the returned fields, and the pivot-then-lookup_hash chaining removes the main ambiguity for a similarity tool. It lacks result-count and pagination context, which an agent would need to plan a large pivot.

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 100%: sha256 has a regex pattern and description, and min_similarity has default 95 plus min/max bounds, all documented in-schema. The description adds no further semantics about how min_similarity interacts with the returned set, so the baseline of 3 applies.

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 a specific resource and relationship: samples whose code and behavior are similar to a given file, via the named Aether similarity search. It also enumerates the returned fields (similarity %, verdict, first seen, tags), so an agent can tell this apart from plain lookup or generic search siblings without opening 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 Guidelines4/5

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

Gives an explicit when-to-use line ('To find variants of a sample') and a concrete follow-up path: open the results by passing up to 100 SHA-256s to one lookup_hash call. It does not state when NOT to use it, nor name search or pivot_ioc as alternatives, so it stops short of full routing guidance.

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