Arize Phoenix logo

Arize Phoenix

OrganizationPopular
Arize-ai

AI Observability & Evaluation

PublisherArize-ai
Repositoryphoenix
LanguagePython
Forks
1.1K
Stars
11.6K
Available tools
0
Transport typestdio
Categories
AI MlDeveloper Tools
Links
GitHubHomepage
  • Connect tools to AI workflows

    Arize Phoenix exposes MCP capabilities that can be used by compatible AI clients and agents.

  • 0 available tools

    Browse the callable actions below, including names and descriptions when provided by the server.

  • Ready-to-copy setup

    Use the installation snippets to configure this server in your preferred MCP client.

  • Open source signals

    11.6K stars and 1.1K forks from the linked repository.

Arize Phoenix is Arize's open-source AI observability platform designed for experimentation, evaluation, and troubleshooting. For managed production workflows, Arize also offers Arize AX. Phoenix provides:

  • Tracing - Trace your LLM application's runtime using OpenTelemetry-based instrumentation.
  • Evaluation - Leverage LLMs to benchmark your application's performance using response and retrieval evals.
  • Datasets - Create versioned datasets of examples for experimentation, evaluation, and fine-tuning.
  • Experiments - Track and evaluate changes to prompts, LLMs, and retrieval.
  • Playground- Optimize prompts, compare models, adjust parameters, and replay traced LLM calls.
  • Prompt Management- Manage and test prompt changes systematically using version control, tagging, and experimentation.
  • PXI (Phoenix Intelligence) - An AI engineering agent built into Phoenix for debugging traces, iterating on prompts, and navigating the product.
  • Remote MCP Server - Connect Claude Code, Cursor, and other MCP clients directly to your Phoenix instance's /mcp endpoint to query traces, datasets, experiments, and more.

Phoenix is vendor and language agnostic with out-of-the-box support for popular frameworks (OpenAI Agents SDK, Claude Agent SDK, LangGraph, Vercel AI SDK, Mastra, CrewAI, LlamaIndex, DSPy) and LLM providers (OpenAI, Anthropic, Google GenAI, Google ADK, AWS Bedrock, OpenRouter, LiteLLM, and more). For details on auto-instrumentation, check out the OpenInference project.

Phoenix runs practically anywhere, including your local machine, a containerized deployment, or in the cloud. See Environments for a walkthrough of each option, or jump straight into the Tracing Quickstart.

[!NOTE] Phoenix is open-source and self-hosted. For a managed platform, Arize offers Arize AX — the same OpenTelemetry/OpenInference instrumentation works with both. See the full comparison.

Table of Contents

Run Locally

Install Phoenix via pip or conda and have a fully functional Phoenix. For all installation and hosting options, see the install guide.

shell
pip install arize-phoenix
phoenix serve

Or run it with no install using uvx:

shell
uvx arize-phoenix serve

Trace Your Application

The fastest way to send traces is to let your coding agent (Claude Code, Codex, Cursor, and others) instrument your app. From your project directory, run:

shell
npx @arizeai/phoenix-cli setup
# or, with Phoenix installed: px setup

Setup detects your framework and LLM provider, installs the right OpenInference instrumentation, and wires up trace export. Prefer to wire it up in code? See the tracing documentation.

Deploy

Phoenix container images are available via Docker Hub and can be deployed using Docker or Kubernetes via the Helm chart.

For Docker Compose, Kubernetes/Helm, and other deployment options, see the self-hosting documentation.

[!NOTE] The Google Cloud button builds Phoenix from source in Cloud Shell rather than deploying the prebuilt Docker Hub image. The Azure template serves plain HTTP (Azure Container Instances does not terminate TLS) — front it with a TLS proxy such as an Application Gateway before production use.

Packages

The arize-phoenix package includes the entire Phoenix platform. However, if you have deployed the Phoenix platform, there are lightweight Python sub-packages and TypeScript packages that can be used in conjunction with the platform.

Python Subpackages

PackageVersion & DocsDescription
arize-phoenix-otelPyPI Version DocsProvides a lightweight wrapper around OpenTelemetry primitives with Phoenix-aware defaults
arize-phoenix-clientPyPI Version DocsLightweight client for interacting with the Phoenix server via its OpenAPI REST interface
arize-phoenix-evalsPyPI Version DocsTooling to evaluate LLM applications including RAG relevance, answer relevance, and more

TypeScript Subpackages

PackageVersion & DocsDescription
@arizeai/phoenix-otelNPM Version DocsProvides a lightweight wrapper around OpenTelemetry primitives with Phoenix-aware defaults
@arizeai/phoenix-clientNPM Version DocsClient for the Arize Phoenix API
@arizeai/phoenix-evalsNPM Version DocsTypeScript evaluation library for LLM applications (alpha release)
@arizeai/phoenix-mcpNPM Version DocsStandalone stdio MCP server for older Phoenix versions (maintenance mode — superseded by the remote MCP server built into Phoenix)
@arizeai/phoenix-cliNPM Version DocsCLI for fetching traces, datasets, and experiments for use with Claude Code, Cursor, and other coding agents

Tracing Integrations

Phoenix is built on top of OpenTelemetry and is vendor, language, and framework agnostic. For details about tracing integrations and example applications, see the OpenInference project and the integrations documentation.

Python Integrations

IntegrationPackageVersion
OpenAIopeninference-instrumentation-openaiPyPI Version
OpenAI Agentsopeninference-instrumentation-openai-agentsPyPI Version
LlamaIndexopeninference-instrumentation-llama-indexPyPI Version
DSPyopeninference-instrumentation-dspyPyPI Version
AWS Bedrockopeninference-instrumentation-bedrockPyPI Version
LangChainopeninference-instrumentation-langchainPyPI Version
LangGraphopeninference-instrumentation-langchainPyPI Version
MistralAIopeninference-instrumentation-mistralaiPyPI Version
Cohereopeninference-instrumentation-coherePyPI Version
Together AIopeninference-instrumentation-togetherPyPI Version
Ollamaopeninference-instrumentation-ollamaPyPI Version
Google GenAIopeninference-instrumentation-google-genaiPyPI Version
Google ADKopeninference-instrumentation-google-adkPyPI Version
Guardrailsopeninference-instrumentation-guardrailsPyPI Version
VertexAIopeninference-instrumentation-vertexaiPyPI Version
CrewAIopeninference-instrumentation-crewaiPyPI Version
Haystackopeninference-instrumentation-haystackPyPI Version
LiteLLMopeninference-instrumentation-litellmPyPI Version
OpenRouteropeninference-instrumentation-openaiPyPI Version
OrcaRouteropeninference-instrumentation-openaiPyPI Version
Groqopeninference-instrumentation-groqPyPI Version
Instructoropeninference-instrumentation-instructorPyPI Version
Anthropicopeninference-instrumentation-anthropicPyPI Version
Smolagentsopeninference-instrumentation-smolagentsPyPI Version
Agnoopeninference-instrumentation-agnoPyPI Version
BeeAIopeninference-instrumentation-beeaiPyPI Version
Strands Agentsopeninference-instrumentation-strands-agentsPyPI Version
Restateopeninference-instrumentation-openai-agentsPyPI Version
MCPopeninference-instrumentation-mcpPyPI Version
Pydantic AIopeninference-instrumentation-pydantic-aiPyPI Version
AG2openinference-instrumentation-ag2PyPI Version
Autogen AgentChatopeninference-instrumentation-autogen-agentchatPyPI Version
Portkeyopeninference-instrumentation-portkeyPyPI Version
Agent Specopeninference-instrumentation-agentspecPyPI Version
Claude Agent SDKopeninference-instrumentation-claude-agent-sdkPyPI Version
TypeSafe AIopeninference-instrumentation-typesafePyPI Version

Span Processors

Normalize and convert data across other instrumentation libraries by adding span processors that unify data.

PackageDescriptionVersion
openinference-instrumentation-openlitOpenInference Span Processor for OpenLIT traces.PyPI Version
openinference-instrumentation-openllmetryOpenInference Span Processor for OpenLLMetry (Traceloop) traces.PyPI Version

JavaScript Integrations

IntegrationPackageVersion
OpenAI@arizeai/openinference-instrumentation-openaiNPM Version
OpenAI Agents@arizeai/openinference-instrumentation-openai-agentsNPM Version
LangChain.js@arizeai/openinference-instrumentation-langchainNPM Version
TanStack AI@arizeai/openinference-tanstack-aiNPM Version
Vercel AI SDK@arizeai/openinference-vercelNPM Version
BeeAI@arizeai/openinference-instrumentation-beeaiNPM Version
Claude Agent SDK@arizeai/openinference-instrumentation-claude-agent-sdkNPM Version
Mastra@mastra/arizeNPM Version
MCP@arizeai/openinference-instrumentation-mcpNPM Version
TypeSafe AI@arizeai/openinference-instrumentation-typesafeNPM Version

Java Integrations

IntegrationPackageVersion
LangChain4jopeninference-instrumentation-langchain4jMaven Central
SpringAIopeninference-instrumentation-springAIMaven Central
Arconia for Spring AIio.arconia:arconia-openinference-semantic-conventionsMaven Central
Google ADKopeninference-instrumentation-adk-javaMaven Central

Go Integrations

IntegrationPackageVersion
OpenAIgithub.com/Arize-ai/openinference/go/openinference-instrumentation-openai-goGo Reference
Anthropicgithub.com/Arize-ai/openinference/go/openinference-instrumentation-anthropic-sdk-goGo Reference

Platforms

PlatformDescriptionDocs
BeeAIAI agent framework with built-in observabilityIntegration Guide
DifyOpen-source LLM app development platformIntegration Guide
Envoy AI GatewayAI Gateway built on Envoy Proxy for AI workloadsIntegration Guide
LangFlowVisual framework for building multi-agent and RAG applicationsIntegration Guide
LiteLLM ProxyProxy server for LLMsIntegration Guide
[Flowise](https://arize.com/docs/phoenix/integrations/platforms/flowis

Installation

TypingMind
Prerequisites:

Node.js 18+

{
  "mcpServers": {
    "phoenix": {
      "command": "npx",
      "args": [
        "-y",
        "@arizeai/phoenix-mcp@latest"
      ],
      "env": {
        "PHOENIX_API_KEY": "your-api-key",
        "PHOENIX_BASE_URL": "https://my-phoenix.com"
      }
    }
  }
}

Use Arize Phoenix MCP with multiple AI models

TypingMind connects MCP tools at the workspace level, so once Arize Phoenix is connected, you can use it with different AI models in TypingMind instead of setting it up separately for each model. This MCP runs locally through the TypingMind MCP connector on your device.

Setup guide to use the local connector

Use this when the MCP server needs access to local files, apps, or private resources on your computer.

1

Open the MCP settings

In TypingMind, go to Settings, Advanced Settings, then Model Context Protocol and choose Setup Connector.

  1. Open TypingMind in your browser.
  2. Click the Settings icon.
  3. Go to Advanced Settings.
  4. Open the Model Context Protocol section.
  5. Click Setup Connector and choose This Device.
TypingMind MCP connector setup screen with This Device selected
2

Run the connector command

Choose This Device, copy the command from TypingMind, and run it in Terminal. Keep the process running while you use MCP.

  1. Copy the setup command shown by TypingMind.
  2. Open Terminal on macOS or Windows Terminal on Windows.
  3. Paste and run the command.
  4. Approve the package install if Terminal asks you to proceed.
  5. Keep the Terminal window running while using MCP tools.
3

Add Arize Phoenix as a server

When the connector status is Ready, click Edit Servers and paste the MCP server configuration.

  1. Wait until the connector status shows Ready.
  2. Click Edit Servers.
  3. Paste the Arize Phoenix MCP server configuration.
  4. Save the server list.
  5. Refresh if you want to confirm the connector is still ready.
TypingMind MCP settings showing active server and Edit Servers button
{
  "mcpServers": {
    "arize-phoenix": {
      "command": "npx",
      "args": [
        "-y",
        "@arizeai/phoenix-mcp"
      ]
    }
  }
}
4

Use it across models

Save the server list, open Plugins, enable the Arize Phoenix MCP tools, then select any supported AI model in TypingMind and use the tools in chat or assign them to an AI agent.

  1. Open the Plugins page in TypingMind.
  2. Enable the Arize Phoenix MCP tools.
  3. Start a chat and choose the AI model you want to use.
  4. Use the MCP tools in chat or assign them to an AI agent.
  5. Switch to another AI model whenever needed without reconnecting MCP.
TypingMind chat using enabled MCP tools with a selected AI model
Can you use Arize Phoenix to help me with this task?
Arize Phoenix
Sure. I read it.
Here is what I found using Arize Phoenix.

Frequently asked questions

What is the Arize Phoenix MCP server used for?

Arize Phoenix is an MCP server that lets compatible AI clients connect to external tools and context. In TypingMind, you can add this MCP server once and make its tools available in your AI workspace.

Can I use Arize Phoenix MCP with multiple AI models in TypingMind?

Yes. TypingMind connects MCP tools at the workspace level, so you can use Arize Phoenix with different AI models such as Claude, ChatGPT, Gemini, or other models you have configured in TypingMind without setting up the MCP server separately for each model.

Why use Arize Phoenix MCP with TypingMind?

TypingMind is one of the best frontends for LLM chat because it brings multiple AI models, prompts, plugins, AI agents, API keys, and MCP tools into one workspace. With Arize Phoenix connected, you can use its MCP tools across your preferred models while keeping your chat workflow organized in TypingMind.

How do I connect Arize Phoenix MCP to TypingMind?

Arize Phoenix runs through the TypingMind local MCP connector. This is best when the MCP server needs access to local files, desktop apps, command-line tools, or private resources on your computer.

What tools does Arize Phoenix MCP provide in TypingMind?

Arize Phoenix exposes MCP capabilities that can be enabled from the TypingMind Plugins page and used in chat or assigned to AI agents.

Do I need to share my API keys with TypingMind to use Arize Phoenix MCP?

No. TypingMind is local-first and lets you keep your model providers, API keys, prompts, and MCP configuration under your control. If Arize Phoenix requires authentication, add the required headers, OAuth settings, or local configuration for that MCP server when you create the connection.

Related MCP Servers

View all
modelcontextprotocol logo

Knowledge Graph Memory

modelcontextprotocol
OrganizationPopular

Model Context Protocol Servers

11.7K
90.5K
9 tools
View details
upstash logo

Context7

upstash
OrganizationPopular

Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

3K
62.3K
2 tools
View details
ahujasid logo

Blender

ahujasid
CommunityPopular

Community plugin to control Blender 3D with any LLM of your choice

2.7K
29.1K
22 tools
View details
googleapis logo

Google GenAI Toolbox

googleapis
OrganizationPopular

MCP Toolbox for Databases is an open source MCP server for databases.

1.7K
16.5K
0 tools
View details

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇