Connect Claude to SigNoz

Query logs, metrics, traces, alerts, and dashboards. Toolspoke puts 10 of its actions behind one MCP endpoint that Claude, Cursor, and Codex all speak.

Connect View pricing

Connection: Provider REST API
Authentication: API key
Actions exposed: 10
Cost per call (typical): 1 credit
Adapter: Maintained by Toolspoke

Connected in three steps

1
Install SigNoz
Open the marketplace in your workspace, add SigNoz to the project your agents work in, and it appears on the gateway immediately.
2
Connect the credential
Authenticate with api key. 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. SigNoz 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 SigNoz asks for

API key. 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.

API keyRequired: SigNoz → Settings → Service Accounts → create an account, then generate a key on its Keys tab. Requires the Admin role.; …
Instance URLRequired: Your SigNoz Cloud URL, or the base URL of your self-hosted install.; https://your-org.us.signoz.cloud

What Claude can do in SigNoz

10 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: 10Reads
Writes: 0Writes
Destructive: 0Destructive

Reads

Fetches data and changes nothing.

query_logs
Fetch raw log records matching a filter, newest first. Use this to read the actual log lines around an incident; use aggregate_logs when you want counts or rates instead.
aggregate_logs
Aggregate logs into counts or percentiles, optionally grouped by attribute. Use this for questions like "how many errors per service in the last hour" rather than pulling raw lines.
query_traces
Fetch raw spans matching a filter, newest first. Use this to find slow or failing requests; filter on has_error = true for errors, or parent_span_id = '' for root spans only.
aggregate_traces
Aggregate spans into latency percentiles, call counts or error counts, optionally grouped by attribute. Use expressions like p99(duration_nano) or count() with group_by ["service.name"] to build a service overview.
query_metrics
Query a named metric as a time series or a single value. timeAggregation collapses points within one series, spaceAggregation merges series together - for a counter use rate + sum, for a gauge use avg + avg.
query_promql
Run a raw PromQL expression against SigNoz's metrics store and return the time series. Use this when a query is easier to express in PromQL than through query_metrics, e.g. rate() over a counter joined with a recording rule.
list_field_keys
Discover the attribute names available for a signal, optionally matching a search string. Call this before writing a filter expression so you use attribute names that actually exist in this instance.
list_services
List the service names SigNoz has trace data for. Use this to get the exact service.name values to filter traces and logs on.
list_alerts
List the configured alert rules with their current firing state. Use this to check what is alerting right now, or to find a rule's id before inspecting it.
list_dashboards
List the dashboards defined in this SigNoz instance with their ids. Use this to find a dashboard id, then open it in the UI - the full panel definitions are not returned.

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 10 actions above are the whole of it. A call to any other name is refused before it reaches SigNoz 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 only reads: Every action here reads. Nothing this connector can do changes anything in SigNoz.
It reaches no further than your credential: Toolspoke holds no access to SigNoz 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 SigNoz: 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 SigNoz. An agent has to ask.
It does not smooth over provider limits: Toolspoke does not retry, queue or back off around SigNoz's own rate limits. A call that SigNoz refuses comes back to the agent as a failed call.

Before you connect it

What can Claude do in SigNoz?

10 named actions: 10 that only read. They include query_logs, aggregate_logs and query_traces. 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 SigNoz connector need?

API key. The connector asks for api key and instance 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 SigNoz connector work with Cursor and Codex, or only Claude?

Any client that speaks MCP, and every one of them gets the same 10 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 SigNoz connector not do?

The 10 actions above are the whole of it. A call to any other name is refused before it reaches SigNoz 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. Every action here reads. Nothing this connector can do changes anything in SigNoz. Toolspoke holds no access to SigNoz 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 SigNoz. An agent has to ask. Toolspoke does not retry, queue or back off around SigNoz's own rate limits. A call that SigNoz 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 SigNoz'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 SigNoz?

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 the credits spent. 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