agentpluginsdirectory
Arize-ai avatar

arize-phoenix

v0.1.0

by Arize-ai · author: Arize AI

Connect to your Phoenix instance to debug, evaluate, and improve LLM applications.

What arize-phoenix does, in the publisher's words

A Codex plugin in the portable Agent Plugins format. It registers the Phoenix remote MCP server so Codex can explore traces, sessions, datasets, experiments, and evaluations in your Phoenix instance.

Plugin MCP URLs cannot contain environment variables, so the plugin registers a small stdio launcher, scripts/phoenix-mcp, instead of a fixed URL. The launcher reads your environment and bridges to /mcp with mcp-remote via npx.

These are the same variables the px CLI reads. Export them in the shell you launch Codex from. Codex forwards only the variables the plugin declares, which is why both are listed in mcp.json and.mcp.json.

From the project README, punctuation lightly normalized · Open the README on GitHub

Skills
0
MCP servers
1
Stars
11,415
License
Apache-2.0
Repo created
2022-11-09
Last pushed
2026-09-11
Publisher type
Organization
Version
0.1.0

Links

MCP servers · 1

phoenixstdio
./scripts/phoenix-mcp
env vars: PHOENIX_ENDPOINT · PHOENIX_API_KEY

Read from the plugin's own mcp.json. We list environment variable names, never values.

Category

Other. Assigned by this directory. Agent Plugins 1.0.0 has no category field, so no manifest declares one.

Keywords

phoenix · arize · observability · tracing · evals · llm · mcp

Related by publisher and keywords

  • signozSigNoz

    Official SigNoz plugin for MCP setup, docs, queries, dashboards, and alerts

  • aws-agentsaws

    Build, deploy, and operate AI agents on AWS. Skills for scaffolding agents with Amazon Bedrock AgentCore (Strands, LangGraph), connecting tools via Gateway and MCP, multi-agent and A2A orchestration, memory, Cedar policies, evaluation, observability, debugging traces and logs, and production hardening.

  • aws-agents-for-devsecopsaws

    Investigate incidents, review code and execute UAT for release readiness, scan code for vulnerabilities, and run penetration tests with AWS DevOps Agent and AWS Security Agent.

  • everrunseverruns

    Interact with the Everruns managed harnesses platform. Manage harnesses, agents, capabilities, sessions, and applications.

  • everruns-deveverruns

    Interact with the Everruns(Dev) managed harnesses platform. Manage harnesses, agents, capabilities, sessions, and applications.

  • gitlab-mcp-serverjmrplens

    GitLab MCP server exposing up to 1085 self-managed GitLab REST/GraphQL MCP tools, or 1091 on GitLab.com Ultimate with Orbit. Includes a default 2-tool dynamic surface, 34 base / 51 self-managed Ultimate / 52 GitLab.com Ultimate meta-tools, 45 resources, 37 prompts, 18 completion types, and 4 MCP capabilities (completions, progress, elicitation, resource subscriptions).

Add the verified badge to your README[![Verified by AgentPluginsDirectory.com against Schema 1.0.0](https://agentpluginsdirectory.com/badge.svg)](https://agentpluginsdirectory.com/plugins/arize-phoenix)

✓ Verified . We fetched the manifest from GitHub and checked it against the official Agent Plugins 1.0.0 schema at agent-plugins.org.