The server itself exposes 31 tools, and some of them can write to your Axiom account. Behind TrustGate an agent only sees the tools you allow, requests and responses are inspected, and every call is logged. Anything outside the allowlist is denied before it reaches Axiom.

How is this different from connecting Axiom MCP directly?

Connected directly, an agent sees every tool the server exposes and holds the credential itself. Through TrustGate you choose which tools each agent gets, and every call is logged against the agent that made it.

What if the Axiom MCP API changes?

We track the Axiom MCP schema, so the tool catalogue stays current. Tools you have already allowed keep working, and anything new stays denied until you enable it.

Can I give different agents different Axiom tools?

Yes. Access is set per agent: one can get a handful of read tools, another the full set. You grant the whole MCP or single tools within it.

Where can I see what my agents did in Axiom?

Every call is logged against the agent that made it, with the tool it used. Activity can be sent on to your own monitoring.

Do I need to run the Axiom MCP server myself?

No. TrustGate connects to the Axiom MCP server and sits in front of it. Your agent only talks to your TrustGate URL, never to Axiom directly.

Connect Axiom MCP to your AI agents, securely.

One secured endpoint for every Axiom call your AI agents make, scoped per user, inspected, and logged.

Get started for free

Get a demo

Try Axiom MCP now

What your agents can ask once Axiom MCP is connected.

Select the tools your AI agents can call

31 tools from the Axiom MCP schema.

Showing 31 tools

queryDatasetreadRuns an APL query against an events or traces dataset. Metrics datasets use queryMetrics instead.
getSavedQueriesreadLists the saved APL queries in the organization.
listDatasetsreadLists the available Axiom datasets.
getDatasetFieldsreadLists the fields in an events or traces dataset, including field names and types.
createDatasetwriteCreates a new dataset in the current organization.
listMetricsreadLists the available metric names in a dataset.
listMetricTagsreadLists the tags available for filtering metrics in a dataset.
getMetricTagValuesreadReturns the values for a specific metric tag in a dataset.
searchMetricsreadSearches for metrics that match a known tag value.
queryMetricsreadRuns an MPL query against an Axiom metrics dataset.
listDashboardsreadLists the dashboards in the organization.
getDashboardreadReturns the details for a dashboard by UID.
exportDashboardreadExports a dashboard as JSON, including the queries behind its charts.
createDashboardwriteCreates a dashboard from a JSON document.
updateDashboardwriteUpdates a dashboard by UID.
updateDashboardChartwritePatches a single chart in an existing dashboard by chart ID, rather than replacing the whole dashboard.
deleteDashboardhigh riskDeletes a dashboard by UID.
checkMonitorsreadChecks the monitors and their current statuses, including which are alerting.
getMonitorreadReturns a monitor's full definition by ID, including the complete query text.
getMonitorHistoryreadReturns the alert history for a specific monitor.
listNotifiersreadLists the configured notifiers, the delivery channels alerts go to.
createMonitorwriteCreates a new monitor.
updateMonitorhigh riskUpdates an existing monitor by ID, which can widen a threshold or window until the monitor stops firing.
deleteMonitorhigh riskDeletes a monitor by ID, ending the alerting it provided.
createNotifierhigh riskCreates a new notifier, which is an outbound delivery channel such as Slack, email, PagerDuty or a custom webhook.
updateNotifierhigh riskUpdates an existing notifier by ID, including pointing it at a different webhook URL.
deleteNotifierhigh riskDeletes a notifier by ID, so monitors bound to it stop delivering anywhere.
services-getMapreadReturns the service dependency graph, including call volume, errors and approximate latency.
services-getChangesreadReports what changed in the service dependency graph, such as new or missing dependencies and latency regressions.
services-getEdgeHistoryreadReturns time-series history for a service's dependency edges.
sendFeedbackwriteSends feedback to the Axiom team about MCP tool descriptions, results, errors or missing capabilities.

What Axiom MCP exposes

Axiom MCP groups its 31 tools into 7 categories, each with a suggested starting policy.

All 31 tools as JSON, ready to paste.

Category	Covers	Access	Suggested policy
Monitors & Notifiers	Checking monitors and their current statuses, a monitor's full definition including its complete query text, alert history, listing notifiers, and creating, updating and deleting both monitors and notifiers	Read / Write	updateNotifier can point a notifier at a different webhook URL, which redirects the alert stream. The delete tools end alerting silently, so gate all six write tools and log the notifier target
Dashboards	Listing dashboards, reading one by UID, exporting as JSON, creating from a JSON document, updating by UID, patching a single chart by chart ID, and deleting	Read / Write	updateDashboardChart patches one chart rather than replacing the whole dashboard, which makes it the safer edit. exportDashboard carries the chart queries out with it
Metrics	Listing metric names in a dataset, the tags available for filtering, values for a specific tag, searching metrics by a known tag value, and running MPL queries against a metrics dataset	Read	Entirely read-only. Metrics datasets use MPL and a different discovery path from events and traces, so the events tools do not apply here
Service Map	The service dependency graph with call volume, errors and approximate latency, what changed in that graph such as new or missing dependencies and latency regressions, and time-series history for a service's dependency edges	Read	Read-only, and only present when service map is enabled for the organization. The graph is a map of the production architecture, so treat the output as internal
Datasets	Listing available datasets, listing the fields in an events or traces dataset with their names and types, and creating a new dataset in the current organization	Read / Write	getDatasetFields is the prerequisite for writing a correct APL query. createDataset adds a new ingest target, which has a billing consequence
Query	Running an APL query against an events or traces dataset, and listing the saved APL queries in the organization	Read	queryDataset runs arbitrary APL against production telemetry, which routinely contains customer data in log lines. Axiom's query cost limits for AI agents are the control to pair with it
Feedback	Sending feedback to the Axiom team about tool descriptions, results, errors or missing capabilities	Write	Touches no account data, but it is still an outbound message from the organization to the vendor

Connect Axiom MCP to your AI agent

Four steps, under ten minutes.

01
Sign in to NeuralTrust
Open the NeuralTrust platform, sign in and go to Getting started, then Connect your tools.
02
Choose your agent
When asked which agent you use, pick Claude Code, Codex, Cursor, Windsurf, Copilot or your own code.
03
Connect Axiom
Find Axiom in the tool list and connect it.
04
Connect your agent
Follow the steps on screen to add the config to your agent, then send the test prompt.

Permissions down to the single tool

You do not allow Axiom MCP or block it. You allow the exact tools each agent can call, one by one.

Axiom MCP	31 TOOLS AVAILABLE
Code review agent	4 tools, read only
Issue triage bot	9 tools
Platform team assistant	all 31 tools

Tool by toolConnecting the server is not the unit of access. Each tool is granted on its own.
Default denyA tool you have not enabled is never exposed to the agent.
Approval on writesTools that change or delete things can require a human to confirm.

Is Axiom MCP secure?

One endpoint instead of raw credentials. Every call is checked against policy and logged.

AI agentsConnect through your MCP client configuration.	NeuralTrustApply controls based on your configuration.	Axiom MCP31 documented tools, which Axiom itself labels Read or Write. The server also ships seven prebuilt MCP prompts, which are not available in the local setup, and Axiom offers separate query cost limits for AI agents.
Coding assistants	Connection & credentialsper user	Monitors & Notifiers10 tools
Internal copilots	Tool access policiesdeny by default	Dashboards7 tools
Workflow automations	Request & response inspectioninline	Metrics5 tools
Compatible MCP clients	Activity monitoringalerts and logs	All other tools9 tools