Skip to main content
You’re using a coding agent — Cursor, Claude Code, Copilot, Windsurf, or something else — and you want it to know how to work with Arize AX. Here’s how:
  • One command — run npx evals and your agent handles the account, tooling, and instrumentation
  • Paste-and-Go — paste a single URL, agent does the rest
  • Skills — teach your agent the full Arize workflow: tracing, datasets, experiments, evals, prompt optimization, and more
  • MCP Servers — persistent IDE integration for instrumentation help and doc lookups
  • Copy Docs — paste any docs page as markdown into your agent for context

​
One Command Setup

The shortest path from zero to your first traces.
Select your coding agent. From there your agent:
  1. Installs the AX CLI and the Arize Skills.
  2. Creates a free Arize AX account or signs you in to an existing account.
  3. Instruments what you choose: an app in the current folder, an existing app at a path you provide, a starter app it creates for you, or the coding agent itself.
  4. Runs your app and confirms the first spans reached your project.
No Node.js? Use the installer for your OS:
Already have an account and credentials? Use Paste-and-Go to instrument without the account and tooling steps, or install the skills directly.

​
Paste-and-Go Tracing Setup

Instrumentation only, for when you already have an Arize AX account and credentials. Paste this into your coding agent and it handles dependency installation, instrumentation, and configuration:
Paste this into your coding agent:
The agent scans your codebase, detects your language and frameworks, proposes an instrumentation plan, and implements it once you approve. Supports Python, TypeScript/JavaScript, and Java across 30+ integrations. This prompt covers instrumentation only — it assumes you already have an account, credentials, and any tooling you want. If you need those too, use one command setup. For more control, use the arize-instrumentation skill instead.

​
Skills

Arize Skills teach your agent the full Arize AX workflow — add tracing, export traces, create datasets, run experiments, set up evaluators, manage annotations, optimize prompts — all through natural language. They work with Cursor, Claude Code, Codex, Windsurf, and 40+ other agents.

Overview

What skills are and when to reach for them.

Install & authenticate

CLI, credentials, and the four install paths.

Skill catalog

Every skill and what it does.

​
MCP Servers

Two MCP servers you can plug into your IDE for persistent access to instrumentation guidance and documentation.

​
Install uv

The Tracing Assistant requires uv (a fast Python package manager). The Docs Server needs no installation.

​
Add to Your IDE

​
Cursor

Navigate to Settings → MCP → Add new global MCP server, then add the JSON config:

​
Claude Code

Verify with claude mcp list.

​
Gemini CLI

​
Antigravity (Google)

Open the MCP Store panel (from the ... dropdown in the editor’s side panel), search “Arize”, and click Install. Alternatively, add the Tracing Assistant JSON config manually via Manage MCP Servers → View raw config.

​
Claude Desktop / Manual Config

Add to your mcpServers JSON config (Settings → Developer → Edit Config in Claude Desktop):
Troubleshooting: Run uv cache clean to reset cached versions, or start the server manually with uvx arize-tracing-assistant@latest to see errors. Debug with npx @modelcontextprotocol/inspector uvx arize-tracing-assistant@latest.

​
Copy Docs to Your Agent

Every page in these docs has a copy as markdown button — paste it directly into ChatGPT, Claude, or any coding agent for accurate, up-to-date context.
Copy page button