Trace And Evaluate Agent Runs With Phoenix

Name: Trace And Evaluate Agent Runs With Phoenix
Author: agentskillexchange

ASecurity

Use Phoenix to trace LLM and agent calls, run evaluations, replay prompts, inspect datasets, and expose observability workflows through MCP.

36 stars
0 votes
0 copies
1 view
Added June 8, 2026

ai-agentsgoshelldockergitsecuritydocumentation

Works with

Security analysis

A92/100

mediumInstalls packages at runtime which could introduce malicious dependencies

Pro shows the line behind each finding and how to fix it

Scanned June 8, 2026

npx -y skills add agentskillexchange/skills --skill trace-and-evaluate-agent-runs-with-phoenix --agent claude-code

Installs into .claude/skills of the current project.

Are you the author of Trace And Evaluate Agent Runs With Phoenix?

Add the live security badge to your README. It updates with every re-scan.

Security grade badge for Trace And Evaluate Agent Runs With Phoenix

[![Security: A — Skills Directory](https://www.skillsdirectory.com/api/skills/agentskillexchange-trace-and-evaluate-agent-runs-with-phoenix/badge)](https://www.skillsdirectory.com/skills/agentskillexchange-trace-and-evaluate-agent-runs-with-phoenix)

More formats (shields.io, HTML) on the badges page. Keep it an A: scan every change in CI with Pro.

Download with Pro

SKILL.md

---
name: "Trace and evaluate agent runs with Phoenix"
slug: "trace-and-evaluate-agent-runs-with-phoenix"
description: "Use Phoenix to trace LLM and agent calls, run evaluations, replay prompts, inspect datasets, and expose observability workflows through MCP."
github_stars: 9750
verification: "security_reviewed"
source: "https://github.com/Arize-ai/phoenix"
author: "Arize AI"
publisher_type: "organization"
category: "Monitoring & Alerts"
framework: "Multi-Framework"
tool_ecosystem:
  github_repo: "Arize-ai/phoenix"
  github_stars: 9750
  npm_package: "@arizeai/phoenix-mcp"
  npm_weekly_downloads: 893
---

# Trace and evaluate agent runs with Phoenix

Use Phoenix to trace LLM and agent calls, run evaluations, replay prompts, inspect datasets, and expose observability workflows through MCP.

## Prerequisites

Phoenix server, OpenTelemetry or supported framework integration, LLM or agent application, model provider credentials, optional MCP client

## Installation

Use the upstream install or setup path that matches your environment:
- pip install arize-phoenix

Requirements and caveats from upstream:
- <a target="_blank" href="https://hub.docker.com/r/arizephoenix/phoenix/tags">
- <img src="https://img.shields.io/docker/v/arizephoenix/phoenix?sort=semver&logo=docker&label=image&color=blue">
- <a target="_blank" href="https://hub.docker.com/r/arizephoenix/phoenix-helm">

Basic usage or getting-started notes:
- Phoenix is vendor and language agnostic with out-of-the-box support for popular frameworks ([OpenAI Agents SDK](https://arize.com/docs/phoenix/tracing/integrations-tracing/openai-agents-sdk), [Claude Agent SDK](https:...
- shell
- ## Packages

- Source: https://github.com/Arize-ai/phoenix
- Extracted from upstream docs: https://raw.githubusercontent.com/Arize-ai/phoenix/HEAD/README.md

## Documentation

- https://arize.com/docs/phoenix

## Source

- [Agent Skill Exchange](https://agentskillexchange.com/skills/trace-and-evaluate-agent-runs-with-phoenix/)