Skip to main content
Glama
wundervault

wundervault

Official

vault_send_secret

Sets encrypted Cloudflare Worker secrets from a vault, so agents can deploy Workers needing API keys or connection strings without seeing plaintext.

Instructions

Put secrets from the owner's vault into a Cloudflare Worker's settings (as encrypted Worker secrets), without you ever seeing them. Use it when a Worker you build or deploy needs keys: a database connection string, a Stripe key, a webhook secret, another API key. The helper app reads each value and sends it straight to Cloudflare.

Give: using (the vault entry of a Cloudflare API token allowed to edit Workers), account (the Cloudflare account id), and items, a list of {secret (vault entry id), worker (the Worker's name), name (what its code reads, e.g. STRIPE_KEY for env.STRIPE_KEY)}. One call can set several secrets in one Worker, or one secret in several Workers. Find the secrets with vault_entries_list; if one the Worker needs is not there, ask the owner to add it to the vault (never to paste it here).

The owner approves the list ONCE (each pairing is shown); sending the same pairing again later asks nothing, except a secret the owner set to "Ask me first", which asks on every send (all of them on one card). Only plain text secrets can be sent. Plain settings that are not secret (URLs, ids, a Stripe publishable key) do not need this: put them in the Worker's config yourself. You get back, for each item, whether it was set.

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": {
      "using": "<using>",
      "account": "<account>",
      "items": "<items>",
      "purpose": "<purpose>"
    },
    "name": "vault_send_secret"
  }
}

Input Schema

NameRequiredDescriptionDefault
itemsYes
usingYesVault entry id of the Cloudflare API token (permission: Workers Scripts Edit).
accountYesCloudflare account id (32 characters).
purposeYesWhy (shown to the owner on the approval card).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.5.0

TDQS

A4.6/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the approval-once-per-pairing model, the 'Ask me first' exception that prompts on every send, plain-text-only limitation, batching semantics, and the return shape. It stops short of stating whether an existing secret of the same name is overwritten, or what happens on partial failure mid-batch for a multi-item write.

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?

Front-loaded with the outcome, then the input shape, then approval/return behavior — a logical order with no filler. It is dense and slightly long, but nearly every clause conveys a rule the agent needs; only the parenthetical examples could be trimmed.

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 an unannotated, four-required-parameter write tool with no output schema, the description covers prerequisites, approval flow, input shape, restrictions, and what comes back per item. An agent could call this correctly without opening the schema.

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 already 75%, yet the description still adds meaning: the `items` pairing model (several secrets in one Worker, or one secret across Workers) and the `name` example showing how it maps to `env.STRIPE_KEY`. It does not mention the `purpose` parameter explicitly (only the schema explains it) or the maxItems cap of 20.

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 first sentence names a specific verb and resource — putting vault secrets into a Cloudflare Worker's settings as encrypted Worker secrets — plus a distinguishing property (the agent never sees the values). It also implicitly separates itself from vault_entries_list (used to find entries) and from plain Worker config editing.

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?

Explicit when-to-use ('when a Worker you build or deploy needs keys') with concrete examples, an explicit when-not-to-use ('plain settings ... do not need this: put them in the Worker's config yourself'), and a named prerequisite tool for finding entries. Failure path is also routed ('ask the owner to add it to the vault').

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