Overview
Arize AX offers two MCP servers that integrate directly into your IDE or LLM for persistent instrumentation guidance and documentation access.
Arize AX Tracing Assistant
Best for: Instrumentation guidance and implementation support📦 View on PyPIThe Arize Tracing Assistant provides hands-on help with adding tracing to your applications:- Instrumentation Guides: Step-by-step guides for adding Arize AX tracing to your codebase
- Curated Examples: Framework-specific tracing examples and best practices
- Direct Support Access: Natural language queries to Arize support directly from your development environment
- Code Analysis: Analyzes your codebase to identify instrumentation needs and propose implementation plans
Arize AX Docs MCP Server
Best for: Comprehensive documentation access and referenceThe AX Docs MCP Server provides searchable access to the entire Arize AX documentation knowledge base:- Full Documentation Access: Search across all Arize AX documentation, guides, and references
- Code Examples: Find relevant code examples and implementation patterns
- API References: Access API documentation and endpoint details
- Feature Guides: Understand how features work and locate implementation details
Usage
Using the AX Tracing Assistant
Once the Tracing Assistant MCP server is running, you can ask your IDE or LLM natural-language questions like:- “Instrument this app using Arize AX”
- “Can you use manual instrumentation so that I have more control over my traces?”
- “How can I redact sensitive information from my spans?”
- “Can you make sure the context of this trace is propagated across these tool calls?”
- “Where can I find my Arize keys?”
Using the AX Docs MCP Server
Once the AX Docs MCP server is running, you can ask your IDE or LLM to search the documentation:- “How do I set up evaluation for my RAG application?”
- “Show me examples of tracing with LangChain”
- “What are the available evaluators in Arize AX?”
- “How do I configure offline evaluations?”
Installation
Install uv (Required for Tracing Assistant only)
The Tracing Assistant is distributed via uv, a fast Python package manager. The Docs MCP Server does not require any installation.
- macOS
- Linux
- Windows
Claude Code Integration
- Tracing Assistant
- Docs MCP Server
You can add the Tracing Assistant directly from the command line:Alternatively, to add it via JSON:To verify the server was added correctly:
Gemini CLI Integration
- Tracing Assistant
- Docs MCP Server
Install using the Gemini CLI extension. (Gemini CLI homepage)
IDE Integration
- Tracing Assistant
- Docs MCP Server
Cursor IDE
-
Navigate to:
Settings→MCP - Click Add new global MCP server
-
Insert the following into your config JSON:
Claude Desktop
-
Open:
Settings→Developer→Edit Config -
Add the following config:
Manual MCP Config
Add this snippet to yourmcpServers config section:Troubleshooting
- Ensure your JSON configs are properly formatted
-
Run
uv cache cleanto reset any cached versions -
Confirm the
uvpath using: -
Start the server manually by running:
-
Use Anthropic’s MCP inspector:
Related
- Agent-Assisted Tracing Setup — Set up tracing by pasting a single URL into your coding agent.
- Arize Skills for Agents — Use the arize-instrumentation skill so your agent can set up and configure tracing with structured, step-by-step instructions.