Skip to main content
Glama
x746b

Windows Forensics MCP Server

by x746b

ntds_get_object_by_sam

Reads allowlisted offline NTDS metadata for an exact SAM account name, flagging deleted, recycled, or duplicate matches without decrypting credentials or requiring SYSTEM.

Instructions

Read allowlisted offline NTDS metadata for one exact SAM name. Retained deleted/recycled matches are flagged; duplicate matches are explicit. Does not decrypt credentials or require SYSTEM.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
fieldsNoAllowlisted metadata projection. Credential attributes are not exposed.
max_scanNoMaximum datatable records examined. Caps or schema uncertainty prevent complete-result claims.
domain_dnNoOptional exact, case-insensitive domain DN scope.
max_charsNo
ntds_pathYes
diagnostic_limitNo
sam_account_nameYesRequired exact case-insensitive SAM account selector; no wildcard or account-list mode.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
statusYes
objectsYes
returnedYes
matched_countYes
scan_completeNo
database_cleanNo
returned_charsYes
payload_clippedYes
schema_completeNo
results_completeYes
serialized_charsYes
match_count_exactNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.5.0

TDQS

A4/5.0
Behavior4/5

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

With no annotations, the description carries the safety profile: read-only metadata, allowlisted fields, no credential decryption, and no SYSTEM requirement. It also discloses edge-case behavior for deleted/recycled and duplicate matches. It does not cover permissions, scan limits, or error behavior in detail.

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?

Three compact sentences with the core operation and constraints front-loaded. No filler; each clause carries purpose, edge case, or safety information.

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?

Output schema exists so return values need not be explained, and the description adequately covers purpose and safety. However, for a 7-parameter tool with incomplete schema descriptions, it leaves several parameters and memory/scan-limit semantics unexplained.

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

Parameters2/5

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

The schema has only 57% description coverage across 7 parameters. The description adds no syntax or meaning beyond the schema's own SAM selector and allowlist notes, and it says nothing about ntds_path, domain_dn, max_chars, diagnostic_limit, or max_scan limits.

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 verb 'Read', resource 'allowlisted offline NTDS metadata', and exact selector 'one exact SAM name'. The SAM-name scope implicitly distinguishes it from sibling ntds_get_object_sid and other NTDS tools.

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?

Clearly implies use for exact SAM lookups and not for wildcard/list modes, and describes duplicate/deleted handling. Does not name an alternative when a SID lookup is needed, so it stops short of full when/when-not guidance.

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