Skip to main content
Glama
wiktorekdev

nuvio-mcp

by wiktorekdev
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Register this device

nuvio_register_device

Register a device or installation to a Nuvio account. Use a backend-accepted client name, then confirm with the token from the first call. Supports dry-run.

Instructions

Register a device/installation against the account. client_name must be one the Nuvio backend accepts (for example 'Nuvio Web'); other values are rejected by the backend. Cannot be undone: call it once to get a short-lived confirmation token, then call again with that token. Supports dry_run.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
dry_runNoReturn the diff without writing anything (no snapshot, no audit entry).
platformNo
client_nameYes
device_nameNo
client_versionNo
installation_idYes
confirmation_tokenNoToken from a previous call of this tool. Irreversible operations require a two-phase prepare/execute: call once to receive the token, then call again with it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv1.1.1
    • addedInput schema / properties / dry_run
      Added value: +{
+  "description": "Return the diff without writing anything (no snapshot, no audit entry).",
+  "type": "boolean"
+}
  2. First observedv1.0.0

TDQS

A4.4/5.0
Behavior5/5

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

The annotations already indicate this is a non-idempotent, mutating operation, and the description adds important detail: the operation cannot be undone, must be confirmed via a second call, requires a backend-accepted client_name, and supports dry_run. This meaningfully enriches the structured annotation data without contradiction.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three compact sentences with no filler. The irreversible two-phase requirement is front-loaded, followed by the backend constraint and dry_run support. Every sentence earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutating tool with no output schema, the description covers the non-obvious behaviors an agent needs: irreversibility, two-phase token confirmation, backend validation, and dry_run. It does not detail the exact success/error response or optional parameter formats, but the token flow is sufficiently described for correct invocation.

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?

The description adds key semantics for client_name (must be accepted by the backend) and explains confirmation_token's two-phase role, which is valuable given only 29% schema coverage. However, it leaves platform, device_name, client_version, and installation_id unexplained, so it does not fully compensate for the low schema-description coverage.

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 specific action and resource: 'Register a device/installation against the account.' This clearly differentiates it from the many sibling tools focused on profiles, addons, collections, and settings. The title is redundant, but the description gives a concrete verb+resource pair.

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?

Provides actionable usage context: client_name must be a backend-accepted value, and the two-phase call flow tells the agent to call once, receive a short-lived token, then call again with it. It does not explicitly name when not to use the tool or alternatives, but no close sibling exists, so the omission is minor.

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

Deploy Server

Other Tools