Skip to main content
Glama
Sign In

Shipvo

by io.github.shipvo
OverviewDiscussionsAdmin

request_secret

Ask the person for an API key without it passing through this chat. Returns a one-time link to the Shipvo vault page (valid 10 minutes, works once) and a notice to show the person. The key goes straight into the vault: you never see it. Tell the person to open the link, then call secret_status to learn whether it was saved. Needs an owner token.

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": {
      "app": "<app>",
      "name": "<name>",
      "purpose": "<purpose>",
      "service": "<service>"
    },
    "name": "request_secret"
  }
}

Input Schema

NameRequiredDescriptionDefault
appYes
nameYesName for the key, e.g. STRIPE_KEY (letters, digits and underscores)
accessNoAccess the key should have (default read)
purposeYesWhy the app needs it, in plain English; shown to the person on the vault page
serviceYesService name (stripe) or its domain (api.example.com)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.4/5.0
Behavior5/5

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

Adds substantial context beyond the annotations: the return value is a one-time link valid 10 minutes that works once, plus a notice to display; the key lands in the vault and the agent never sees it; an owner token is required. The annotations only state readOnlyHint=false and destructiveHint=false, so this detail is genuinely additive and explains that the caller never handles the secret itself.

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?

Five short sentences, front-loaded with the action and the reason, followed by return shape, next step, and prerequisite. Slight redundancy between 'a notice to show the person' and 'Tell the person to open the link,' but no sentence is 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?

With no output schema, the description supplies the return payload (link + notice) and its lifetime; with 5 parameters at 80% schema coverage, the remaining gap is small. Prerequisite (owner token) and follow-up flow (secret_status) are both covered, so an agent can execute the full interaction without guessing.

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

Parameters3/5

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

Schema description coverage is 80%, so the schema already explains name, purpose, service and access; the description adds nothing per-parameter and never mentions 'app' or 'access'. The only adjacent hint is that a purpose is 'shown to the person', which duplicates the schema text. Baseline 3 applies when the schema carries the parameter documentation.

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 concrete verb and resource ('Ask the person for an API key') plus the key constraint ('without it passing through this chat'). The description makes clear this tool initiates a human-in-the-loop secret entry, which is distinguishable from the sibling secret_status that only checks the result.

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?

Gives the trigger (need an API key that must not transit chat) and the follow-up step ('call secret_status to learn whether it was saved'), which also implicitly routes the agent away from using this tool to check status. It also notes the prerequisite 'Needs an owner token.' Full marks would require an explicit when-not-to-use or a named alternative for other vault operations.

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

All Shipvo toolsInspect
Try in Browser
Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources