InfraNest

Servers with their latest metrics

server_metrics

Read-onlyIdempotent

Every server in the organization with its latest CPU, memory, disk, load and network readings, its alert-rule counts and whether it is breaching, and roles: what each server is (see the server’s role), a page at a time. normal_now gives, for CPU, memory and load, the range the server normally sits in at this hour of the week (low, typical, high: its 10th, 50th and 90th percentile, and the weeks behind it); it is null until four weeks are learned, unless the range is borrowed from a peer named in borrowed_from. Monitored servers come first; filter with search, credential, tag or status (for example breaching, norules, notreporting, monitored). Each server's normal_now is the range its CPU, memory and load normally sit in at this hour of the week, so a reading can be called usual or unusual for this server.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "server_metrics"
  }
}

Input Schema

Name	Required	Description
`tag`	No	Only things with this tag id.
`page`	No	Page number, from 1.
`search`	No	Matches server name or IPv4 address.
`status`	No	breaching: over an alert threshold now; noagent / notreporting: no metrics coming in.
`per_page`	No	Rows per page, up to 200 (default 25).
`organization_id`	No	The organization to read. Leave it out when the token reaches only one.

Schema Changelog

Changes observed during successful MCP inspections.

First observedOct 30, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Annotations already declare this read-only, idempotent and non-destructive, so the safety burden is off the description. The text adds real behavioral detail beyond that: pagination defaults, the default ordering (monitored first), and the null/peer-borrowing semantics of normal_now.

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

Conciseness3/5

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

The opening sentence is well front-loaded and information-dense, but the final sentence restates the normal_now explanation already given earlier, and the mid-sentence parentheticals make it sprawling. Editing out the repetition would improve it noticeably.

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?

There is no output schema, so the description carries the return-value burden and does so reasonably: it names the reading fields, alert-rule counts, breaching flag, roles, and explains normal_now with percentiles, weeks and borrowed_from. The credential reference and the lack of sibling differentiation are the remaining gaps.

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 100%, so all six parameters are already documented in the schema, including the status enum. The description adds only light filtering context (example status values) and mentions a `credential` parameter that is not in the schema, which is mildly misleading rather than helpful.

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 clearly states it returns every server in the organization along with its latest CPU, memory, disk, load and network readings, plus alert-rule counts and role information. The resource and payload are unambiguous, but it never distinguishes itself from close siblings like list_servers or server_metric_history.

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?

It offers useful in-tool guidance ('Monitored servers come first; filter with search, credential, tag or status') and gives example status values. However, it never says when to pick this over list_servers or server_metric_history, and it references a `credential` filter that does not exist in the schema.

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

All InfraNest 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.