# Arize AX — how to use (mcp.ai)

Connect your Arize AX account and use 24 tools for artificial intelligence straight from your AI agent. Connect with your own API key. Arize AX is an AI engineering platform for tracing, evaluating, and improving AI applications through projects, datasets, prompts, experiments, traces, and spans.

## Option A — via MCP (recommended)
Remote MCP endpoint (HTTP, streamable): `https://api.mcp.ai/p_arize_ax?ms=1787291280000`
Add it as a custom/remote MCP connector in your client (Claude, Cursor, VS Code…), then authenticate when prompted. Once connected, ask the agent to use the server's tools (e.g. `arize_ax_add_dataset_examples`).

## Option B — via direct REST API
Base URL: `https://api.mcp.ai/api/arize_ax`
Auth: `Authorization: Bearer sk_live_…` — create a workspace API key at https://mcp.ai/settings/api-keys
Discover endpoints: `GET https://api.mcp.ai/api/arize_ax/_endpoints`

### Endpoints
- `POST https://api.mcp.ai/api/arize_ax/add/dataset/examples` — Append arbitrary-field examples to an Arize dataset or a specified dataset version.
  - body: { examples: object[], dataset_id: string, dataset_version_id?: string }
- `POST https://api.mcp.ai/api/arize_ax/add/experiment/runs` — Append one or more runs to an existing Arize experiment.
  - body: { experiment_id: string, experiment_runs: object[] }
- `POST https://api.mcp.ai/api/arize_ax/create/dataset` — Create an Arize dataset in a space with an explicit initial array of examples.
  - body: { name: string, examples: object[], space_id: string }
- `POST https://api.mcp.ai/api/arize_ax/create/experiment` — Create an Arize experiment with initial runs, associated with exactly one dataset or space.
  - body: { name: string, space_id?: string, dataset_id?: string, experiment_runs: object[] }
- `POST https://api.mcp.ai/api/arize_ax/create/prompt` — Create an Arize prompt and its initial version in a space.
  - body: { name: string, version: object, space_id: string, description?: string }
- `POST https://api.mcp.ai/api/arize_ax/create/prompt/version` — Create a new immutable version of an existing Arize prompt.
  - body: { model?: string, messages: object[], provider: string, prompt_id: string, commit_message: string, provider_params?: object, invocation_params?: object, input_variable_format?: string }
- `POST https://api.mcp.ai/api/arize_ax/get/dataset` — Get one Arize dataset and its versions by dataset ID.
  - body: { dataset_id: string }
- `POST https://api.mcp.ai/api/arize_ax/get/experiment` — Get one Arize experiment by its ID, without its experiment runs.
  - body: { experiment_id: string }
- `POST https://api.mcp.ai/api/arize_ax/get/project` — Get one accessible Arize project by its ID.
  - body: { project_id: string }
- `POST https://api.mcp.ai/api/arize_ax/get/prompt` — Get an Arize prompt with its current, explicitly selected, or labeled version.
  - body: { label?: string, prompt_id: string, version_id?: string }
- `POST https://api.mcp.ai/api/arize_ax/get/space` — Get one accessible Arize space by its ID.
  - body: { space_id: string }
- `POST https://api.mcp.ai/api/arize_ax/list/dataset/examples` — List one page of examples from an Arize dataset or a specific dataset version, preserving user-defined example fields.
  - body: { limit?: integer, cursor?: string, dataset_id: string, dataset_version_id?: string }
- `POST https://api.mcp.ai/api/arize_ax/list/datasets` — List one page of Arize datasets, optionally filtered by space or dataset name.
  - body: { name?: string, limit?: integer, cursor?: string, space_id?: string, space_name?: string }
- `POST https://api.mcp.ai/api/arize_ax/list/experiment/runs` — List one page of runs and outputs for an Arize experiment, preserving additional run fields.
  - body: { limit?: integer, cursor?: string, experiment_id: string }
- `POST https://api.mcp.ai/api/arize_ax/list/experiments` — List one page of Arize experiments, optionally filtered by dataset, space, or name.
  - body: { name?: string, limit?: integer, cursor?: string, space_id?: string, dataset_id?: string }
- `POST https://api.mcp.ai/api/arize_ax/list/projects` — List one page of accessible Arize projects, optionally filtered by space or project name.
  - body: { name?: string, limit?: integer, cursor?: string, space_id?: string, space_name?: string }
- `POST https://api.mcp.ai/api/arize_ax/list/prompt/versions` — List one page of versions for an Arize prompt, newest first.
  - body: { limit?: integer, cursor?: string, prompt_id: string }
- `POST https://api.mcp.ai/api/arize_ax/list/prompts` — List one page of Arize prompts, optionally filtered by space or prompt name.
  - body: { name?: string, limit?: integer, cursor?: string, space_id?: string, space_name?: string }
- `POST https://api.mcp.ai/api/arize_ax/list/spaces` — List one page of Arize spaces accessible to the connected API key, optionally filtered by organization or name.
  - body: { name?: string, limit?: integer, cursor?: string, org_id?: string }
- `POST https://api.mcp.ai/api/arize_ax/list/spans` — Read one bounded page of spans for an Arize project using optional time and filter constraints.
  - body: { limit?: integer, cursor?: string, filter?: string, end_time?: string, project_id: string, start_time?: string }
- `POST https://api.mcp.ai/api/arize_ax/list/traces` — Read one bounded page of traces and nested spans for an Arize project using optional time and filter constraints; nested spans may be truncated per trace.
  - body: { limit?: integer, cursor?: string, filter?: string, end_time?: string, project_id: string, start_time?: string }
- `POST https://api.mcp.ai/api/arize_ax/update/dataset` — Rename an existing Arize dataset.
  - body: { name: string, dataset_id: string }
- `POST https://api.mcp.ai/api/arize_ax/update/dataset/examples` — Update existing Arize dataset examples by ID, optionally creating a named dataset version. IDs that do not match existing examples are ignored.
  - body: { examples: object[], dataset_id: string, new_version?: string, dataset_version_id?: string }
- `POST https://api.mcp.ai/api/arize_ax/update/prompt` — Update or clear an Arize prompt's description.
  - body: { prompt_id: string, description: string }

## Example prompts
- "What can I do in Arize AX?"
- "Show me a summary of my Arize AX account"

## More
- Page: https://mcp.ai/arize_ax
- Agent spec (llms.txt): https://mcp.ai/arize_ax/llms.txt
- Postman collection: https://mcp.ai/arize_ax/postman.json