Search documentation

Search the Fumadocs-backed documentation index.

MCP Install

Connect the AXP MCP server to Cursor, Claude, ChatGPT, Codex, or another MCP host.

The AXP MCP server lets agents query and share results, manage experiments and runs, create guided trace analyses and findings, manage org-scoped secrets, switch org context, and authorize the local ax CLI with ax auth connect.

Use the install instructions for your agent host:

Install the AXP MCP server directly in Cursor. If Cursor opens MCP settings without an install prompt, add this same server config manually.

{
  "mcpServers": {
    "AX": {
      "url": "https://app.514.ax/mcp"
    }
  }
}

After connecting the MCP server, follow any sign-in prompt from Cursor, Claude, ChatGPT, Codex, or your MCP host. Then verify AXP tools are available in your agent session.

Except for org-context tools and the CLI auth bootstrap, org-scoped tools use the current MCP org unless you pass an org_id override.

Tool catalog

GroupToolPurposeCLI equivalent
experimentexperiment_listList experiments the current org can access.ax experiment list
experimentexperiment_viewShow one experiment's metadata, latest version, axes, and run counts.ax experiment view
experimentexperiment_versionsList stored YAML version fingerprints for an experiment.ax experiment versions
experimentexperiment_pullReturn the stored YAML for the latest or selected experiment version.ax experiment pull
experimentexperiment_pushValidate and push a new experiment YAML version without starting runs.ax experiment push
experimentexperiment_runSubmit runs for the latest pushed version of an experiment.ax experiment run <experiment-id>
runrun_listList individual runs with optional experiment, version, dimension, status, and limit filters.ax run list
runrun_viewView a run request roll-up or one composite run id.ax run view
runrun_cancelCancel queued or running work for a run request, optionally limited to specific run UUIDs.ax run cancel
resultsresults_viewView modeled experiment metrics with experiment_id, or one run's metrics with run_id.ax results view --experiment <id> / ax run view <run-id>
resultsresults_queryRun read-only SQL against uploaded AXP Source/Facts tables for novel questions.ax results query
resultsresults_shareMint or reuse a public results-explorer share URL for an experiment.ax results share
resultsresults_dimensionsList valid results filter and group-by dimensions and values for an experiment.ax results dimensions
resultsresults_scatterReturn a deterministic sample of run cost/time scatter points for an experiment.ax results scatter --experiment <id>
secretsecret_setCreate or overwrite one org secret; returns metadata only, never the value.ax secret set
secretsecret_listList secret slugs and audit metadata; never returns values.ax secret list
secretsecret_deleteDelete one secret by slug.ax secret delete
analyzeanalyze_suggestSuggest guided trace-analysis questions for failed or error runs.ax analyze suggest
analyzeanalyze_promptBuild a copy/paste prompt for the full trace-analysis workflow.ax analyze prompt
analyzeanalyze_createValidate and persist caller-supplied trace analysis output.ax analyze create
analyzeanalyze_getRead one persisted trace analysis.ax analyze get
analyzeanalyze_listList persisted trace analyses.ax analyze list
findingsfindings_resolveResolve run, tool call, timeline entry, span, or prompt anchors into trace evidence.ax findings resolve
findingsfindings_create_analysisCreate the analysis record used by a saved findings result.ax findings create --question --result
findingsfindings_createCreate a persisted finding with quoted evidence links.ax findings create
findingsfindings_listList persisted findings for a saved result.ax findings list
findingsfindings_getRead one persisted finding with evidence links.ax findings get
mcp_orgmcp_org_listList organizations available to the authenticated MCP user and show the selected org.ax auth orgs --list
mcp_orgmcp_org_get_currentGet the current organization context used by org-scoped MCP tools.ax auth orgs
mcp_orgmcp_org_set_currentSet the organization context used by org-scoped MCP tools.ax auth orgs --switch <org-id>
cli_authcli_auth_startCreate a short-lived one-time command that authenticates the local ax CLI.ax auth connect --code <code>

Start trace work with analyze_suggest for a failed/error run batch; it returns the structured prompt, ax results query calls, and create-request skeleton to use before persisting with analyze_create.

Results scatter tool

results_scatter is read-only. Pass required experiment_id; pass optional org_id only when you want to override the current MCP org for that call. The tool returns both text and structured data channels: text for a compact human summary, and structured JSON for clients that render charts. MCP hosts that support interactive MCP-Apps widgets can show the same points as an embedded scatter plot widget; hosts without widget support still receive the text and structured data.

The point sample is deterministic and capped at 2,000 runs. The response includes totalPoints and truncated so callers can disclose when the widget or JSON is showing a sample instead of every matching run.