How to Use the Arize AI MCP in LlamaIndex

Ground your LlamaIndex RAG system in real-time model performance data from Arize AI. Ask questions, get answers from your MLOps stack.

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

Index Your Model's History

Turn your Arize AI monitoring data into a searchable knowledge base. Your LlamaIndex agent can periodically call `list_projects`, `list_experiments`, and `list_spans`, then index the results. Now your model's entire history is queryable. When you ask, "Which models had performance dips last quarter?", your agent doesn't hallucinate. It performs a vector search over the indexed logs and gives you an answer grounded in actual data from Arize AI.

Build a Self-Aware MLOps RAG Agent with LlamaIndex

This isn't just about calling tools; it's about remembering the answers. A LlamaIndex agent can use `get_model` to fetch the current production model's configuration and performance, then index that state. Later, if you ask "Why did we choose this model version?", the agent can retrieve the indexed context and explain the decision based on the metrics it recorded. It builds institutional knowledge automatically. This MCP Server gives it the raw data to do that.

Query Arize AI with Natural Language

Stop writing scripts to check model health. Just ask your LlamaIndex agent a question. It will translate your query into the right sequence of tool calls, like using `list_datasets` to find a dataset ID and then `create_dataset` to make a copy. The real power comes from combining this with other data sources. Your agent can correlate a model issue found in Arize AI with a support ticket from another system, all because LlamaIndex unifies them into a single, queryable index.

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

The MCP server exposes Arize AI operations as tools. LlamaIndex can call these tools (`get_model`, `list_experiments`) to fetch live data, and then it indexes that data into a vector store. This makes your model's operational data queryable with natural language.

Absolutely. You can ask your agent, "Compare the input data distribution for the last two experiments." It would use `list_experiments` to get IDs, then `list_spans` or `list_datasets` to fetch the data, index it, and provide a summary of the drift.

It creates a memory for your MLOps. Instead of one-off checks, LlamaIndex builds a searchable history of your model's performance, configuration, and issues from Arize AI. You can query the past to understand the present.

Yes. You can set up a recurring query with LlamaIndex that asks the agent to summarize model performance for the week. The agent will call the necessary Arize AI tools, synthesize the information, and generate a report for you.

Your project and model information is handled securely. All requests from your LlamaIndex agent to the MCP Server are encrypted and authenticated with a private token. The server environment on Vinkius is isolated and stateless, meaning your data is only processed for the immediate request.

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