Skip to main content
Glama

Get Node-RED info

nodered_get_info
Read-onlyIdempotent

Reads a Node-RED add-on's version, runtime settings, flow state, and installed palette modules so you can verify installed versions and integrations before building a flow.

Instructions

Read the Node-RED add-on's version, runtime settings, flow run state and installed palette modules.

Calls GET /settings (kept: version, httpNodeRoot, context, flowEncryptionType, flowFilePretty, externalModules), GET /flows/state and GET /nodes (grouped per npm module with version and type count). Changes nothing.

Use when: checking which Node-RED and palette versions run, e.g. whether node-red-contrib-home-assistant-websocket is installed, before building a flow. Not for: host, memory and OS details — use nodered_get_diagnostics; the add-on's own options — use supervisor_get_addon. Returns: {"addon_slug", "addon_version", "nodered_version", "settings", "flows_state", "modules": [{module, version, types, enabled, user_installed}]}; a section Node-RED answers with an HTTP error holds {"error": "HTTP <status>", ...} instead. Errors: the add-on lookup errors of nodered_list_flows.

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": "nodered_get_info"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.29.0

TDQS

A4.6/5.0
Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so 'Changes nothing' is largely redundant. The description nonetheless adds real value beyond annotations: it lists which /settings keys are retained, describes per-module grouping with version and type counts, and discloses partial-failure semantics where a section answered with an HTTP error instead holds an {"error": "HTTP <status>"} object.

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?

Purpose is front-loaded in the first sentence, followed by endpoint details and clearly labeled 'Use when', 'Not for', 'Returns' and 'Errors' sections. It is dense but every block is scannable; the enumeration of kept settings keys and the full return shape are the only mildly verbose parts.

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?

For a zero-parameter read tool this covers everything an agent needs: what is fetched, which endpoints, when to prefer it, which siblings to use instead, the return shape and error behavior. The return-shape restatement is somewhat redundant given an output schema exists, but the per-section error contract is not derivable from the schema alone.

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?

The tool takes zero parameters, so the baseline is 4 and there is no parameter meaning to add. The description correctly does not invent any inputs.

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?

The first sentence gives a specific verb ('Read') and enumerates exactly which resources are returned: add-on version, runtime settings, flow run state and installed palette modules. It then names the underlying endpoints (GET /settings, /flows/state, /nodes), so the agent knows precisely what data this covers and how it differs from the diagnostics sibling.

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?

Contains explicit 'Use when' guidance (checking Node-RED/palette versions before building a flow, e.g. verifying node-red-contrib-home-assistant-websocket is installed) and explicit 'Not for' exclusions that route to nodered_get_diagnostics for host/memory/OS and supervisor_get_addon for add-on options. Both the positive and negative selection conditions are stated, not inferred.

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