Integration

Arize integration

AI observability and LLM monitoring platform. Manage spaces, projects, datasets, experiments, prompts, spans, and annotation configs for evaluating and monitoring AI/ML models. Features cursor-based pagination, structured JSON responses, and a CRUDL design pattern across all resources.

Connect Arize How integrations work

Ask it in chat

Say what should happen.
The workflow builds itself.

When this happens, do that in Arize.Built from the 32 Arize tools below, on the connection you add once.

Common Arize use cases

Fetch the production-labeled prompt for deployment
Remove a test project after validation is complete
Upload a curated Q&A golden set for LLM evaluation
Verify a project exists before sending traces to it
Create a system prompt for a customer support chatbot
Discover all monitored AI applications in a workspace
Remove deprecated annotation schemas no longer in use
Set up a new project to monitor a chatbot application
Remove experimental prompts after a project is complete
Remove failed experiments that produced invalid results

What you can do with Arize

Each of these is one operation on one endpoint, available both as a workflow step and as a tool an AI agent can call on its own. Nothing bundles several operations into one action, so what a run did stays readable afterwards.

Most endpoints run on the free plan. A few, mainly the ones that publish on your behalf, need a paid plan.

Prompt, 5 operations

create_promptCreate promptPOSTCreates a new prompt with an initial version in an Arize space.
delete_promptDelete promptDELETEPermanently deletes an Arize prompt and all its versions by its ID.
get_promptGet promptGETRetrieves an Arize prompt by its ID with optional version or label.
list_promptsList promptsGETLists all prompts the user has access to in Arize.
update_promptUpdate promptPATCHUpdates an existing Arize prompt's description.

Annotation config, 4 operations

create_annotation_configCreate annotation configPOSTCreates a new annotation configuration in an Arize space.
delete_annotation_configDelete annotation configDELETEPermanently deletes an Arize annotation configuration by its ID.
get_annotation_configGet annotation configGETRetrieves a single Arize annotation configuration by its ID.
list_annotation_configsList annotation configsGETLists annotation configurations with optional filtering by space in Arize.

Dataset, 4 operations

create_datasetCreate datasetPOSTCreates a new dataset with examples in an Arize space.
delete_datasetDelete datasetDELETEPermanently deletes an Arize dataset by its ID.
get_datasetGet datasetGETRetrieves a single Arize dataset by its ID.
list_datasetsList datasetsGETLists all datasets the user has access to in Arize.

Experiment, 4 operations

create_experimentCreate experimentPOSTCreates a new experiment with runs against an Arize dataset.
delete_experimentDelete experimentDELETEPermanently deletes an Arize experiment by its ID.
get_experimentGet experimentGETRetrieves a single Arize experiment by its ID.
list_experimentsList experimentsGETLists experiments with optional filtering by dataset in Arize.

Project, 4 operations

create_projectCreate projectPOSTCreates a new project within an Arize space.
delete_projectDelete projectDELETEPermanently deletes an Arize project by its ID.
get_projectGet projectGETRetrieves a single Arize project by its ID.
list_projectsList projectsGETLists all projects the user has access to in Arize.

Space, 4 operations

create_spaceCreate spacePOSTCreates a new space within an Arize organization.
get_spaceGet spaceGETRetrieves a single Arize space by its ID.
list_spacesList spacesGETLists all spaces the user has access to in Arize.
update_spaceUpdate spacePATCHUpdates an existing Arize space's name or description.

Prompt version, 3 operations

create_prompt_versionCreate prompt versionPOSTCreates a new version of an existing Arize prompt.
get_prompt_versionGet prompt versionGETRetrieves a specific Arize prompt version by its version ID.
list_prompt_versionsList prompt versionsGETLists versions for a specific Arize prompt.

Example, 2 operations

add_dataset_examplesAdd dataset examplesPOSTAdds new examples to an existing Arize dataset, creating a new dataset version.
list_dataset_examplesList dataset examplesGETLists examples for a specific Arize dataset.

Experiment run, 1 operation

list_experiment_runsList experiment runsGETLists runs for a specific Arize experiment.

Span, 1 operation

list_spansList spansPOSTLists spans filtered by project, time range, and optional filters in Arize.

Use Arize from Claude Code, Cursor or Codex

Connect Arize in LiveContext, create an API key in Settings, then add the LiveContext MCP server to your client. Its Arize operations become tools the client can call, next to every other integration you connected.

Claude Code

claude mcp add --transport http livecontext https://livecontext.ai/mcp --header "X-API-Key: YOUR_API_KEY"

Codex (~/.codex/config.toml)

[mcp_servers.livecontext]
url = "https://livecontext.ai/mcp"

[mcp_servers.livecontext.http_headers]
"X-API-Key" = "YOUR_API_KEY"

Cursor, Claude Desktop and other JSON configs

{
  "mcpServers": {
    "livecontext": {
      "type": "http",
      "url": "https://livecontext.ai/mcp",
      "headers": {
        "X-API-Key": "YOUR_API_KEY"
      }
    }
  }
}

Set up the MCP server step by step

How to connect Arize

Create your workspace
Sign up free. Nothing to install.
Connect Arize once
Add your Arize connection in Settings. Every tool from this integration reuses it, and secrets are encrypted at rest and visible only to you.
Describe the job in chat
The workflow builds itself in front of you and picks the endpoints it needs. Drag the steps yourself on the canvas whenever you would rather be explicit.

Arize integration FAQ

What can you do with the Arize integration?

LiveContext exposes 32 operations on Arize, covering prompt, annotation config, dataset and experiment. Common uses include Fetch the production-labeled prompt for deployment, Remove a test project after validation is complete and Upload a curated Q&A golden set for LLM evaluation.