Provider REST API

15 actions

Connect Claude to Axiom

Query logs, traces and events with APL, and read datasets, monitors, dashboards and annotations in Axiom. Toolspoke puts 15 of its actions behind one MCP endpoint that Claude, Cursor, and Codex all speak.

Connect View pricing

Connection: Provider REST API
Authentication: API token
Actions exposed: 15
What a call bills: Nothing
Adapter: Maintained by Toolspoke

Connected in three steps

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

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.

API tokenRequired: Axiom → Settings → API tokens → New API token. Give it Query and read access on the datasets it should see, plus read on monitors, notifiers, dashboards and annotations. Add Ingest only if agents should send events, and annotation create and delete only if they should mark deployments.; xaat-…

What Claude can do in Axiom

15 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: 12Reads
Writes: 2Writes
Destructive: 1Destructive

Reads

Fetches data and changes nothing.

list_datasets
List the datasets this token can see, with their kind (events, otel traces, otel metrics), description and retention. Start here to find the dataset name a query needs. It is also the install's health check, because a token with no dataset access returns nothing useful anywhere else.
get_dataset
Fetch one dataset's settings by name.
list_dataset_fields
List the fields in a dataset with their types. Read this before writing APL against a dataset you have not queried, so the query names real fields.
query_apl
Run an APL query and get tabular results. The dataset is named inside the query, e.g. ['http-logs'] | where status >= 500 | summarize count() by bin_auto(_time). Always set a time window and end with a limit or summarize. Results are your users' log lines. For a large result, set include_cursor and pass the returned cursor back to read the next page.
list_starred_queries
List saved (starred) APL queries - the queries a team already trusts. Filter by dataset.
list_monitors
List monitors with their APL query, threshold, schedule and notifiers. Use get_monitor_history to see which ones fired.
get_monitor
Fetch one monitor's full definition, including its query text.
get_monitor_history
Read when a monitor triggered and resolved over a time range.
list_notifiers
List notifiers - where monitor alerts go (Slack, email, PagerDuty, Opsgenie, webhooks). Webhook URLs, routing keys and tokens are masked.
list_dashboards
List dashboards by uid and name.
get_dashboard
Fetch one dashboard with its charts and the APL behind each one.
list_annotations
List annotations - the deployment and incident markers shown on charts - optionally for some datasets and a time range.

Writes

Creates or updates something on the other side.

create_annotation
Mark an event, such as a deployment, on the charts of one or more datasets.
ingest_events
Send events to a dataset as a JSON array of objects. Each object becomes one event; a _time field sets its timestamp. Ingested data cannot be edited afterwards, only trimmed by age, so send test events to a test dataset. Uses Axiom's ingest endpoint on api.axiom.co.

Destructive

Deletes or permanently alters something. Worth granting on purpose.

delete_annotation
Delete one annotation permanently.

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 15 actions above are the whole of it. A call to any other name is refused before it reaches Axiom 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 Axiom 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 Axiom: 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 Axiom. An agent has to ask.
It does not smooth over provider limits: Toolspoke does not retry, queue or back off around Axiom's own rate limits. A call that Axiom refuses comes back to the agent as a failed call.

Before you connect it

What can Claude do in Axiom?

15 named actions: 12 that only read, 2 that write and 1 that delete or permanently alter something. They include list_datasets, get_dataset and list_dataset_fields. 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 Axiom connector need?

API token. The connector asks for api token. 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 Axiom connector work with Cursor and Codex, or only Claude?

Any client that speaks MCP, and every one of them gets the same 15 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 Axiom connector not do?

The 15 actions above are the whole of it. A call to any other name is refused before it reaches Axiom 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 Axiom 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 Axiom. An agent has to ask. Toolspoke does not retry, queue or back off around Axiom's own rate limits. A call that Axiom 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 Axiom'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 Axiom?

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