Skip to main content
Glama
wundervault

wundervault

Official

vault_save_secret

Save an existing secret into the owner's vault by pointing to its file or command, without exposing the value in chat; it waits for owner approval and returns only name, source, and length.

Instructions

Save a secret you ALREADY HAVE into the owner's vault, without reading it into this chat: point at the file it is in, or the command that prints it, and the helper takes the value from there. It waits for the owner, marked "saved by an agent"; no agent can use it until the owner saves it with their passkey and sets it up, so tell the owner it is waiting under Needs you. You get back the name, where it came from and its length, never the value.

Give exactly one of: from_file (an absolute path; read as your own user, up to 64 KB); from_command (a list: the program, then its arguments; no shell, 30 seconds, only what it prints on standard output; a failing command saves nothing); value (the text itself, only when it is already in this chat). With a file or command, pick takes one part: {env:"NAME"} for a NAME=value line (.env files), or {json:"a.b"} for a field of JSON. Otherwise the whole text is the value, less one final newline. Never cat or echo a secret to find it: use this tool.

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": {
      "save_as": "<save_as>",
      "purpose": "<purpose>"
    },
    "name": "vault_save_secret"
  }
}

Input Schema

NameRequiredDescriptionDefault
pickNoOptional, with from_file or from_command: {env:"NAME"} or {json:"a.b.c"}.
valueNoThe secret itself, only if it is already in this chat.
purposeYesWhy it should be in the vault (shown to the owner).
save_asYesName for the secret in the vault, 1 to 80 characters.
serviceNoOptional: the service it is for (e.g. "resend"), shown to the owner as a hint.
from_fileNoAbsolute path of the file holding the secret.
from_commandNoThe program and its arguments, e.g. ["gh","auth","token"]. No shell.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.5.0

TDQS

A4.7/5.0
Behavior5/5

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

With no annotations, the description carries the full burden and does: it discloses that the save is provisional ('It waits for the owner, marked "saved by an agent"'), that no agent can use it until the owner approves with a passkey, and that the caller gets back only name, origin and length, never the value. It also bounds the side effects precisely: file read as your own user up to 64 KB, command run without a shell with a 30-second limit and stdout only, and 'a failing command saves nothing'.

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?

The most important constraint (never read the secret into the chat) and the owner-approval consequence are front-loaded, and every sentence carries operational information. It is dense in the second paragraph and some owner-facing detail is packed into long clauses, but nothing is genuinely 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?

Seven parameters, a nested object, mutually exclusive modes and no output schema — the description covers all of it, including what the caller receives back in place of a value. An agent can call this correctly without consulting anything else.

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

Parameters5/5

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

Schema coverage is already 100%, so the baseline would be 3, but the description adds real meaning the schema does not: the mutually exclusive selection rule across from_file/from_command/value, the {env:"NAME"} and {json:"a.b"} shapes for pick, the 'absolute path' requirement, the 64 KB cap, the no-shell/30s/stdout-only constraints on from_command, and the 'whole text less one final newline' extraction rule. This is well beyond restating the schema.

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?

States a specific verb and resource ('Save a secret ... into the owner's vault') plus the key mechanism ('point at the file it is in, or the command that prints it'), so the action is unmistakable. It does not name or differentiate against any sibling vault tool (e.g. vault_send_secret), which keeps it just short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

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

Gives explicit mode selection ('Give exactly one of: from_file ... from_command ... value'), a hard condition for the value mode ('only when it is already in this chat'), and a negative instruction ('Never cat or echo a secret to find it: use this tool'). That is when-to-use, when-not-to-use, and the alternative, all spelled out.

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