InfraNest

Find anything by name

search

Read-onlyIdempotent

Up to five matches per kind for q (at least 2 characters): domains, servers, DNS zones, monitors (by name or target), certificates, contacts, status pages, watched domains, load balancers, volumes, firewalls and dynamic IP sources. Each match has its id, a label, sometimes a sublabel (an address or target) and the url of its page in the app. A kind your token or role may not read is left out. related, when q is exactly one of your domains, lists what that domain is connected to. Start here when the person names something: each hit's id (kind:number, e.g. monitor:12) goes to fetch, and its number to the named tools. It also finds InfraNest's help articles (help:): search for how something is done in InfraNest, and fetch the article.

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": "search"
  }
}

Input Schema

Name	Required	Description	Default
`query`	No	Part of a name, a domain, an address or a monitor target (at least 2 characters).
`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

A4.6/5.0

Behavior4/5

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

Beyond the readOnly/idempotent annotations it discloses real behavior: a hard cap of five matches per kind, permission-based omission ('A kind your token or role may not read is left out'), and the conditional `related` block that only appears when `q` exactly equals one of your domains. It also describes the per-hit shape (id, label, optional sublabel, url). The only gap is pagination/truncation behavior when many kinds match.

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 cap and query rule, then the kind enumeration, then the routing advice — no filler sentences. The twelve-kind enumeration is long but each item is load-bearing for matching decisions; the paragraph is dense rather than padded, though breaking the routing sentence out would improve scanability.

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?

There is no output schema, and the description compensates fully by describing the return shape, the per-kind cap, the permission-driven omissions, and the id/number convention needed to chain into `fetch` or the named tools. Nothing an agent needs in order to call this correctly and act on the results is missing.

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 100%, so the baseline is 3, but the description adds semantics the schema does not: the 2-character minimum is repeated as a hard rule, the `related` block is triggered only by an exact domain match, and the id format (kind:number, e.g. monitor:12) tells the agent what the parameter value produces. It does not explain `organization_id`, though the 'token or role' language partially covers multi-org scoping.

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?

Names the resource and the exact scope: 'Up to five matches per kind for `q`' across an enumerated set of kinds (domains, servers, DNS zones, monitors, certificates, contacts, status pages, etc.). It also states the cross-cutting case ('It also finds InfraNest's help articles') so an agent can distinguish this from list_* and search_dns/search_audit_log siblings without opening a schema.

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?

Gives an explicit entry rule — 'Start here when the person names something' — plus the follow-up path: each hit's id goes to `fetch` and its number to the named tools. It also carves out a second use case (how-to questions → search, then fetch the help article), so both when-to-use branches and the alternative tool are stated.

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.