How to Use the Arize AI MCP in LlamaIndex

Q: How do I use the Arize AI tools with a LlamaIndex agent?

First, install llama-index-tools-mcp. Then, you'll create a BasicMCPClient pointing to your endpoint and pass it to an McpToolSpec. Calling totoollistasync() on the spec gives you the tools for your agent.

Index your Arize AI model data. Build RAG apps with LlamaIndex that answer questions about your model performance.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Arize AI MCP to LlamaIndex

Create your Vinkius account to connect Arize AI to LlamaIndex and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup Arize AI with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Create a Model Observability Index

LlamaIndex doesn't just call the Arize tools; it indexes their output. Your agent can use this MCP Server to run `list_models` and `get_metrics` for everything you're tracking. LlamaIndex then feeds that raw data directly into a vector store, creating a searchable knowledge base of your model's performance. This is where it gets good. You can now ask plain-English questions like, "Which models in the production space have a data drift score above 0.6?" Your RAG application queries the index—built from your live Arize data—and gives you a grounded answer, not a guess.

Query Your Evaluation History

Stop digging through dashboards to find old test results. Set up a LlamaIndex agent to periodically call `list_evals` and index the output. This builds a complete, searchable history of every toxicity, PII, and hallucination check you've run. Now you can just ask your agent, "Show me all failed PII evaluations for the 'billing-summarizer' model this quarter." Your agent finds the answer by doing a semantic search over the indexed data from the Arize AI tools. It's faster and a lot more direct.

Turn Arize AI Config into a Knowledge Base

This isn't just for performance metrics. Use the `list_spaces`, `list_environments`, and `list_datasets` tools to build an index of your entire Arize AI configuration. It turns your setup into documentation that never gets stale. When a new developer joins, they don't have to ask you basic questions. They can ask the LlamaIndex agent, "What evaluation datasets are registered for the training environment?" The agent queries its index of your live Arize setup and gives them the answer instantly.

Setup guide

Set up Arize AI MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all Arize AI MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to Arize AI tools.",
)
response = await agent.run("List recent Arize AI data")

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by Arize AI. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect Arize AI now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about Arize AI MCP in LlamaIndex

First, install `llama-index-tools-mcp`. Then, you'll create a `BasicMCPClient` pointing to your endpoint and pass it to an `McpToolSpec`. Calling `to_tool_list_async()` on the spec gives you the tools for your agent.

Yes, that's the primary use case. Your LlamaIndex agent calls tools like `get_metrics` and `list_evals` from the Arize AI MCP Server. It then indexes the JSON responses into a vector store, making your model observability data queryable in natural language.

LlamaIndex takes the structured JSON output from the Arize AI tools, like a list of models or their metrics. It breaks this data down into chunks, converts them into vector embeddings, and stores them in a vector database. This allows for fast semantic search over your observability data.

Calling the tools directly gets you raw data for immediate use. With LlamaIndex, you're building a long-term, searchable knowledge base from that data. It's about answering future questions, not just the one you have right now.

This MCP server interacts with your Arize AI model metadata, telemetry logs, and evaluation reports. Your Vinkius endpoint token ensures that only your authenticated agent can access this data, and the connection is always encrypted.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript