Provider REST API

9 actions

Connect Claude to Netdata

Query metrics, find anomalies and correlations, and review alert configuration across the nodes in a Netdata Cloud space. Toolspoke puts 9 of its actions behind one MCP endpoint that Claude, Cursor, and Codex all speak.

Connect View pricing

Connection: Provider REST API
Authentication: Cloud API token
Actions exposed: 9
What a call bills: Nothing
Adapter: Maintained by Toolspoke

Connected in three steps

1
Install Netdata
Open the marketplace in your workspace, add Netdata to the project your agents work in, and it appears on the gateway immediately.
2
Connect the credential
Authenticate with cloud api token. Where to get one, and what it has to be able to reach, is the next section.
3
Point your agent at the gateway
Give your client one address, https://toolspoke.com/mcp. Claude Code takes it as a command, Claude and Claude Desktop add it as a custom connector, and Cursor, Codex and VS Code each read it from a config file of their own.

.mcp.json

{
  "mcpServers": {
    "toolspoke": {
      "type": "http",
      "url": "https://toolspoke.com/mcp"
    }
  }
}

One block covers every tool you have installed. Netdata shows up in the client as soon as your policy allows it, and so does everything else you install later.

Where the address goes, per client

Claude Code: Run it in your project, then /mcp to sign in
claude mcp add --transport http toolspoke https://toolspoke.com/mcp
Claude and Claude Desktop: Settings, then Connectors, then Add custom connector
https://toolspoke.com/mcp
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json for one project
{ "mcpServers": { "toolspoke": { "url": "https://toolspoke.com/mcp" } } }
Codex: ~/.codex/config.toml
[mcp_servers.toolspoke] url = "https://toolspoke.com/mcp"
VS Code: .vscode/mcp.json, or the MCP: Add Server command
{ "servers": { "toolspoke": { "type": "http", "url": "https://toolspoke.com/mcp" } } }

What Netdata asks for

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 tokenRequired: 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.; ndc.…
Netdata Cloud URLOptional: Leave blank for Netdata Cloud. Set it only for a Netdata Cloud On-Prem installation; it has to be publicly reachable.; https://app.netdata.cloud

What Claude can do in Netdata

9 actions, each one declared and named by the connector rather than discovered at runtime. A workspace policy grants a person all of them, a hand-picked selection, everything on the read side, everything on the write side, or none.

Reads: 7Reads
Writes: 1Writes
Destructive: 1Destructive

Reads

Fetches data and changes nothing.

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

Creates or updates something on the other side.

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.

Destructive

Deletes or permanently alters something. Worth granting on purpose.

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.

What it will not do

Enforced by the gateway rather than left to convention, which is why each of these can be stated flatly.

It cannot call anything else: The 9 actions above are the whole of it. A call to any other name is refused before it reaches Netdata rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time.
It reaches no further than your credential: Toolspoke holds no access to Netdata of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either.
It never hears from Netdata: Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Netdata. An agent has to ask.
It does not smooth over provider limits: Toolspoke does not retry, queue or back off around Netdata's own rate limits. A call that Netdata refuses comes back to the agent as a failed call.

Before you connect it

What can Claude do in Netdata?

9 named actions: 7 that only read, 1 that write and 1 that delete or permanently alter something. They include list_spaces, list_rooms and list_room_nodes. Nothing outside that list is reachable: the connector declares each operation by name rather than proxying whatever an agent asks for.

What credentials does the Netdata connector need?

Cloud API token. The connector asks for cloud api token, and optionally netdata cloud url. Values are encrypted at rest and attached to the outbound request by the gateway, so they are never part of the arguments an agent sends and never reach the audit log.

Does the Netdata connector work with Cursor and Codex, or only Claude?

Any client that speaks MCP, and every one of them gets the same 9 actions. There is a single address, https://toolspoke.com/mcp. Claude Code adds it with claude mcp add --transport http, Claude and Claude Desktop take it as a custom connector in settings, Cursor reads it from .cursor/mcp.json, Codex from ~/.codex/config.toml, and VS Code from .vscode/mcp.json. Each of them signs in to the gateway itself, so there is no key to paste.

What does the Netdata connector not do?

The 9 actions above are the whole of it. A call to any other name is refused before it reaches Netdata rather than forwarded on, and connecting your account does not add to the list: it is fixed by the connector, not discovered at run time. Toolspoke holds no access to Netdata of its own. Every call carries the credential you stored and nothing besides, so whatever that credential cannot reach, this connector cannot reach either. Nothing is pushed to it. There is no webhook, no subscription and no polling, so this connector cannot notice by itself that something changed in Netdata. An agent has to ask. Toolspoke does not retry, queue or back off around Netdata's own rate limits. A call that Netdata refuses comes back to the agent as a failed call.

Can I limit which actions an agent can call?

Yes, in two places. The project switches Netdata's actions on and off one at a time, for everyone in the project at once, and the screen groups them by read, write and destructive so turning off everything that deletes is one click. An individual agent key can then be narrowed further, to particular toolkits in a project and to particular actions in a toolkit. Whatever it was granted, a key never reaches a project its owner cannot.

What gets recorded when an agent calls Netdata?

Every attempt, with the agent that made it and the person that agent belongs to, the full request payload, the response payload, the status, the duration, and what the call cost in sandbox time and model tokens. Values whose key names a secret are masked out before the record is shown to anyone. An operation the connector marks as not retained never has its response body written at all, so the gateway keeps no second copy of what was read.

More observability connectors

Browse all of them