# Arize AX — MCP server on 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.

By: mcp.ai · official
Page: https://mcp.ai/arize_ax

## Connect (MCP protocol)
Remote MCP endpoint (HTTP, streamable): https://api.mcp.ai/p_arize_ax?ms=1787291340000
Add it as a custom/remote MCP connector, then authenticate when prompted.

## REST API (no MCP client required)
Every tool is also a REST endpoint, authed with a workspace API key.
Discover: GET https://api.mcp.ai/api/arize_ax/_endpoints   # public; lists every endpoint
Call:     POST https://api.mcp.ai/api/arize_ax/<endpoint>
  Authorization: Bearer sk_live_…   # create one at https://mcp.ai/settings/api-keys
  Content-Type: application/json
  Body: { …args }   →   { "ok": true, "tool": "<id>", "result": { … } }

## Developer docs
How to use (MCP or REST), markdown: https://mcp.ai/arize_ax/skill.md
Postman collection (v2.1): https://mcp.ai/arize_ax/postman.json

## Tools
- arize_ax_add_dataset_examples(examples: object[], dataset_id: string, dataset_version_id?: string) — Append arbitrary-field examples to an Arize dataset or a specified dataset version.
- arize_ax_add_experiment_runs(experiment_id: string, experiment_runs: object[]) — Append one or more runs to an existing Arize experiment.
- arize_ax_create_dataset(name: string, examples: object[], space_id: string) — Create an Arize dataset in a space with an explicit initial array of examples.
- arize_ax_create_experiment(name: string, space_id?: string, dataset_id?: string, experiment_runs: object[]) — Create an Arize experiment with initial runs, associated with exactly one dataset or space.
- arize_ax_create_prompt(name: string, version: object, space_id: string, description?: string) — Create an Arize prompt and its initial version in a space.
- arize_ax_create_prompt_version(model?: string, messages: object[], provider: string, prompt_id: string, commit_message: string, provider_params?: object, invocation_params?: object, input_variable_format?: string) — Create a new immutable version of an existing Arize prompt.
- arize_ax_get_dataset(dataset_id: string) — Get one Arize dataset and its versions by dataset ID.
- arize_ax_get_experiment(experiment_id: string) — Get one Arize experiment by its ID, without its experiment runs.
- arize_ax_get_project(project_id: string) — Get one accessible Arize project by its ID.
- arize_ax_get_prompt(label?: string, prompt_id: string, version_id?: string) — Get an Arize prompt with its current, explicitly selected, or labeled version.
- arize_ax_get_space(space_id: string) — Get one accessible Arize space by its ID.
- arize_ax_list_dataset_examples(limit?: integer, cursor?: string, dataset_id: string, dataset_version_id?: string) — List one page of examples from an Arize dataset or a specific dataset version, preserving user-defined example fields.
- arize_ax_list_datasets(name?: string, limit?: integer, cursor?: string, space_id?: string, space_name?: string) — List one page of Arize datasets, optionally filtered by space or dataset name.
- arize_ax_list_experiment_runs(limit?: integer, cursor?: string, experiment_id: string) — List one page of runs and outputs for an Arize experiment, preserving additional run fields.
- arize_ax_list_experiments(name?: string, limit?: integer, cursor?: string, space_id?: string, dataset_id?: string) — List one page of Arize experiments, optionally filtered by dataset, space, or name.
- arize_ax_list_projects(name?: string, limit?: integer, cursor?: string, space_id?: string, space_name?: string) — List one page of accessible Arize projects, optionally filtered by space or project name.
- arize_ax_list_prompt_versions(limit?: integer, cursor?: string, prompt_id: string) — List one page of versions for an Arize prompt, newest first.
- arize_ax_list_prompts(name?: string, limit?: integer, cursor?: string, space_id?: string, space_name?: string) — List one page of Arize prompts, optionally filtered by space or prompt name.
- arize_ax_list_spaces(name?: string, limit?: integer, cursor?: string, org_id?: string) — List one page of Arize spaces accessible to the connected API key, optionally filtered by organization or name.
- arize_ax_list_spans(limit?: integer, cursor?: string, filter?: string, end_time?: string, project_id: string, start_time?: string) — Read one bounded page of spans for an Arize project using optional time and filter constraints.
- arize_ax_list_traces(limit?: integer, cursor?: string, filter?: string, end_time?: string, project_id: string, start_time?: string) — 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.
- arize_ax_update_dataset(name: string, dataset_id: string) — Rename an existing Arize dataset.
- arize_ax_update_dataset_examples(examples: object[], dataset_id: string, new_version?: string, dataset_version_id?: string) — Update existing Arize dataset examples by ID, optionally creating a named dataset version. IDs that do not match existing examples are ignored.
- arize_ax_update_prompt(prompt_id: string, description: string) — Update or clear an Arize prompt's description.

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

## Links
Docs: https://mcp.ai/docs/mcps/arize_ax
Website: https://mcp.ai/mcps/arize_ax