Connect Netdata to Claude Code

Query metrics, find anomalies and correlations, and review alert configuration across the nodes in a Netdata Cloud space. Add Toolspoke to Claude Code once and it can use 9 Netdata actions. Your Netdata credential stays in Toolspoke, and you choose which actions Claude Code may call.

Set it up in Claude Code

Three steps, the first one once for every toolkit you will ever add.

  1. Add Toolspoke to Claude Code

    Run it in your project, then /mcp to sign in

    claude mcp add --transport http toolspoke https://toolspoke.com/mcp

    The sign-in opens in your browser, and Toolspoke asks you to approve it.

  2. Install Netdata and connect it

    Add Netdata to a project in your Toolspoke workspace.

    Cloud API token. You provide it once, when you install the connector. Toolspoke encrypts it at rest and decrypts it only for the length of a single call, and the gateway attaches it to the outbound request itself, so it is never part of the arguments an agent sends.

    Cloud API token
    Netdata Cloud → your profile picture (bottom left) → User Settings → API Tokens → create a token with scope:all. It is shown once. It has the same permissions as your own account.
  3. Choose what Claude Code may do

    All 9 actions start on. Switch off any of the 2 actions that change something in Netdata, and Claude Code gets a refusal if it tries.

What you can ask Claude Code for

A few of the Netdata actions that only read, so they are safe to try first.

  • List the Netdata Cloud spaces this token's user belongs to, with their ids
  • List the rooms in a space, with their ids
  • Rank the metrics in a room by how much they changed in a window compared with a baseline

What Claude Code can do in Netdata

7 actions read, one writes and one deletes or permanently changes something.

Reads

  • List spaces

    List the Netdata Cloud spaces this token's user belongs to, with their ids. Every other call takes a space id, and a token without API access fails here, which is why an install tests itself with it.

  • List rooms

    List the rooms in a space, with their ids. Rooms group nodes; data, node and alert calls are scoped to one room.

  • List room nodes

    List every node in a room with its id, hostname, state (live, stale, offline), Netdata version and host details.

  • Query data

    Query time-series data for one or more metric contexts (e.g. system.cpu, disk.io) across a room's nodes, aggregated over time and grouped by dimension, instance, node or label. after and before are seconds, negative means relative to now, e.g. after -3600 for the last hour. Returns Netdata's json2 format.

  • Find correlated metrics

    Rank the metrics in a room by how much they changed in a window compared with a baseline. Netdata's metric correlations. Use it to answer 'what else changed when this spiked'. method volume is fast; ks2 compares distributions and is slower.

  • List misconfigured alerts

    List a room's alerts that are badly tuned, firing too often, stuck raised, silenced too long, or never dispatched to anyone. A good starting point for cleaning up alert noise.

  • List silencing rules

    List a space's alert notification silencing rules, which alerts, nodes or rooms are muted, when, and until when.

Writes

  • Create silencing rule

    Mute alert notifications for a time window, for maintenance, say, scoped by alert name, context, node, room or host label. Alerts still evaluate; only the notifications stop. A write rather than destructive because it expires at lasts_until and delete_silencing_rules removes it, but while it is active nobody is paged, so scope it narrowly.

Deletes or permanently changes

  • Delete silencing rules

    Delete silencing rules by id. Notifications they muted resume at once, and the rules cannot be restored, create them again if needed.

Netdata in Claude Code: questions

Does Claude Code see my Netdata credential?

No. The credential is stored encrypted in Toolspoke, and the gateway adds it to each call. Claude Code only ever talks to Toolspoke, and the dashboard shows the last four characters of the credential and nothing more.

Can I stop Claude Code from changing things in Netdata?

Yes. Each of the 9 actions can be switched off for a project. Turn off the 2 that change something and Claude Code can only read.

Will 9 actions crowd Claude Code's context?

No. Toolspoke shows Claude Code five bridge tools, plus a guide where a toolkit has one, and Claude Code searches for the Netdata action it needs when it needs it. Adding more toolkits does not add more tools to its list.

Can I add it once for every project?

Yes. Add --scope user to the command and Claude Code keeps Toolspoke in every project on this machine. Without it, the server is added to the project you ran the command in.

What does it cost?

Tool calls are free on every plan, and a Netdata call does not run in a sandbox, so it bills nothing.

Try Netdata in Claude Code

Free to start, and tool calls cost nothing on any plan.