Skip to main content
Glama
x746b

Windows Forensics MCP Server

by x746b

file_analyze_pe

Perform static analysis on Windows PE files to extract headers, imports, exports, sections, hashes, Authenticode metadata, and suspicious indicators for forensic triage.

Instructions

Perform static analysis on Windows PE files (EXE/DLL/SYS). Extracts headers, imports, exports, sections, hashes, Authenticode metadata including SpcSpOpusInfo program name, and suspicious indicators.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
file_pathYesPath to the PE file to analyze
detail_levelNoLevel of detail: minimal (hashes+type), standard (+ sections/imports), verbose (+ all data)standard
extract_stringsNoExtract ASCII/Unicode strings (can be verbose)
calculate_hashesNoCalculate MD5, SHA1, SHA256, Imphash
check_signaturesNoInspect Authenticode metadata and known packer/crypter signatures

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.4.5
    • changedInput schema / properties / check_signatures / description
      Previous value: -"Check for known packer/crypter signatures"New value: +"Inspect Authenticode metadata and known packer/crypter signatures"
  2. Addedv1.3.0

TDQS

A4.3/5.0
Behavior4/5

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

No annotations are present, so the description carries the disclosure burden. It explicitly says 'static analysis', signaling a read-only operation, and lists the extracted data (headers, imports, exports, hashes, Authenticode metadata, suspicious indicators). It does not mention performance caveats or limitations, but the static nature and output scope are well disclosed.

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?

A single, front-loaded sentence that states the core action and then lists the extracted artifacts in a compressed sequence. Every element adds information, with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The definition covers the input type, the analysis action, and the output categories, while the schema fully documents all five parameters and defaults. Without an output schema, the enumerated extraction list gives the agent a good picture of the return content; no critical missing context for invoking the tool.

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?

Since schema_description_coverage is 100%, baseline is 3. The description adds no parameter-level semantics beyond the schema; it mentions output categories but not how they map to the detail_level, extract_strings, calculate_hashes, or check_signatures parameters.

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?

The description opens with a specific verb ('Perform static analysis') and a concrete resource ('Windows PE files (EXE/DLL/SYS)'), then enumerates the output categories. This clearly distinguishes it from sibling forensic tools focused on EVTX, registry, or disk artifacts.

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?

It clearly establishes the file type this tool applies to, so an agent can select it for PE files. However, it does not mention alternatives or conditions where another tool (e.g., api_analyze_imports for import-focused analysis) would be preferable.

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