Dump Windows Vault credentials to retrieve saved passwords from the local credential store. Use when you need to extract stored secrets for security assessments.
Dump Windows Vault credentials (saved passwords)
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the full burden of behavioral disclosure. It states the extraction action but omits critical operational traits: the need for admin/SeDebugPrivilege (implied by the sibling mimikatz_privilege_debug), dependence on DPAPI master keys, antivirus/EDR detection risk, and failure modes when the vault is locked, empty, or legacy-only. For a credential-exfiltration tool, this is a significant transparency gap.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
A single sentence with no wasted words; every token carries meaning. The structure is minimal but appropriate for a parameterless tool. It stops short of a top score because a second clause naming the sibling for in-memory credentials would have improved routing behavior without adding bulk.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a security-sensitive mimikatz operation with zero annotations and no output schema, one sentence is not enough. The agent gets no return-shape information, no privilege prerequisites, no warning about sensitivity or detection, and no clue which of the many credential-dumping siblings covers other sources. The description is incomplete for safe and correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters and effectively 100% schema coverage, so the baseline of 4 applies. The description's parenthetical adds mild context about the data involved, and there are no parameters left undocumented. No deduction is warranted.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb+resource pair — 'Dump' + 'Windows Vault credentials' — and the parenthetical '(saved passwords)' clarifies what kind of data is extracted. The Vault target is distinct from siblings like lsadump_sam, sekurlsa_logonpasswords, or dpapi_masterkey, but the description never explicitly contrasts itself with those alternatives, so differentiation is partial.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
There is no statement of when to use this tool versus the 21 siblings. An agent cannot tell from the description whether Vault credentials differ from what sekurlsa_logonpasswords (in-memory logon passwords), lsadump_secrets, or dpapi_masterkey would recover, and no preconditions or exclusions are given. No usage guidance is present.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.