Visual Sentinel

Add a server

vs_servers_create

Add a server to watch. For AGENT servers the answer includes the dashboard page that shows the command to install the agent on the server. Your plan sets how many servers you can link.

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": {
      "name": "<name>",
      "hostname": "<hostname>"
    },
    "name": "vs_servers_create"
  }
}

Input Schema

Name	Required	Description
`os`	No	LINUX (default) or MACOS, for the server agent.
`name`	Yes	Display name.
`tags`	No
`hostname`	Yes	Host name of the server, unique in the workspace.
`ipAddress`	No	Optional IPv4 or IPv6 address.
`description`	No
`environment`	No	For example production (default) or staging.
`cpuThreshold`	No	CPU percent that triggers an alert (1 to 100).
`diskThreshold`	No	Disk percent that triggers an alert (1 to 100).
`monitoringMode`	No	AGENT (install the Visual Sentinel agent on the server) or MANAGED_HOST (shared or managed hosting with no agent).
`hostingProvider`	No	With MANAGED_HOST: HOSTINGER or OTHER.
`memoryThreshold`	No	Memory percent that triggers an alert (1 to 100).
`hostingAccountKey`	No	With MANAGED_HOST: the hosting account the sites share.
`notificationChannelIds`	No	Alert channel ids for this server's alerts.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 25, 2026

TDQS

A3.8/5.0

Behavior4/5

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

Annotations already declare non-read-only, non-destructive, non-idempotent, open-world, so the safety burden is partly carried. The description still adds non-obvious behavior: the response for AGENT servers includes the dashboard page with the install command, and a plan-based quota limits linking. It omits what happens on duplicate hostname or what the payload looks like for MANAGED_HOST servers.

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 short sentences, front-loaded with the action, then the notable output, then the quota constraint. Nothing is repeated from the schema and no sentence is filler.

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 14-parameter creation tool with no output schema, the description covers the key outcome of the call (dashboard page/install command for AGENT) and a gating constraint (plan server limit). Missing pieces are minor but real: failure modes for duplicate hostnames and the return shape for MANAGED_HOST servers.

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 86%, so nearly every parameter (including the AGENT/MANAGED_HOST and OS enums) is self-documenting and the baseline is 3. The description adds only the indirect signal that AGENT mode yields an install command, with no clarification of required field combinations for MANAGED_HOST.

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?

The description opens with a specific verb+resource ("Add a server") and scopes it with "to watch", making the create semantics clear against sibling vs_servers_update/get/list. It stops short of explicitly naming the create-vs-update boundary, but the verb "Add" carries that distinction.

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

Usage Guidelines3/5

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

Usage is implied (link a new server to monitor) and one real constraint is given: the plan caps how many servers can be linked. There is no explicit guidance on when to choose this over alternatives, or prerequisites such as which monitoringMode to pick for a given hosting situation.

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

All Visual Sentinel tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.