Skip to main content
Glama
AIWerk

@aiwerk/mcp-server-vault

by AIWerk

save_login_item

Saves login credentials as a Vaultwarden login item with optional TOTP support, so sign-in secrets appear as real login entries instead of generic secrets. Create-only.

Instructions

Save login credentials (username, password, URL, optional TOTP seed) as a Vaultwarden login item in the mcp-agent-created collection. Use this instead of save_generated_secret when the credential is a sign-in (username + password), so it surfaces as a real login item with get_totp_code support. CREATE-only: cannot overwrite an existing item (name collision returns an error). At least one of username or password is required. All fields are E2E-encrypted with the vault org key before transmission. Sets mcp-created-by, mcp-created-at, mcp-expires-at, and mcp-used-in custom fields automatically. Blocked when READ_ONLY=1. Logs to DRY_RUN without creating a real cipher when DRY_RUN=1.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
uriNoOptional login URL (e.g. "https://app.example.com/login"). Stored as the login URI.
nameYesUnique name for this login within the mcp-agent-created collection. Case-sensitive. Name collision returns an error. Pick a distinct name.
totpNoOptional TOTP seed (otpauth:// URI or raw base32 secret). Enables get_totp_code on this item.
notesNoOptional non-sensitive annotation. Not the credential itself.
used_inNoFree-form context string, e.g. "smallinvoice portal login". Stored as mcp-used-in custom field.
passwordNoLogin password (max 4096 chars). Optional, but at least one of username or password is required.
usernameNoLogin username / account identifier. Optional, but at least one of username or password is required.
expires_in_daysNoDays until the item expires (sets mcp-expires-at). Default 30, max 365.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.2.3
    • changedInput schema / properties / name / description
      Previous value: -"Unique name for this login within the mcp-agent-created collection. Case-sensitive. Name collision returns an error — pick a distinct name."New value: +"Unique name for this login within the mcp-agent-created collection. Case-sensitive. Name collision returns an error. Pick a distinct name."
  2. First observedv0.2.2

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only supply readOnlyHint=false and openWorldHint=true. The description adds substantial non-obvious behavior: CREATE-only with collision errors, at least one of username/password required, E2E encryption with the vault org key before transmission, auto-set custom fields (mcp-created-by/at/expires-at/used-in), and environment gating (blocked when READ_ONLY=1, logs to DRY_RUN when DRY_RUN=1). This is exactly the value-add the structured fields don't provide.

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?

Dense but front-loaded: purpose and the sibling comparison come first, then constraints (CREATE-only, field requirement), then encryption and environment behavior. Every clause carries signal, though the paragraph is long and slightly dense; minor trimming could improve flow without loss.

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?

For a mutation tool with no output schema, the description covers what an agent needs: create-only semantics, failure mode (name collision), required-field rule, encryption, auto-set metadata, and READ_ONLY/DRY_RUN gating. Nothing material is missing given the rich schema and annotation coverage.

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

Parameters4/5

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

Schema coverage is 100%, so the schema already documents each field, giving a baseline of 3. The description adds a genuine cross-parameter constraint not encoded in the schema — 'At least one of username or password is required' (both are individually optional there) — and characterizes totp as enabling get_totp_code, which is useful semantics beyond the field list.

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?

Opens with a specific verb+resource: saving login credentials (username/password/URL/TOTP) as a Vaultwarden login item in a defined collection. It explicitly distinguishes itself from the sibling save_generated_secret by name and by the sign-in use case. An agent can identify the tool 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 Guidelines5/5

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

Gives an explicit routing rule: 'Use this instead of save_generated_secret when the credential is a sign-in (username + password).' It also notes the downstream benefit (get_totp_code support) and the hard constraint (CREATE-only, name collision errors), so when-to-use and when-not-to-use are both covered.

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