How to Use the LlamaIndex (AI Data Framework & RAG) MCP in OpenAI Agents SDK

Q: How do I inspect active pipelines using LlamaIndex (AI Data Framework & RAG) and OpenAI Agents SDK?

Your OpenAI agent uses the listpipelines tool to fetch all deployed LlamaIndex data pipelines. The agent can then call getpipeline to inspect the configuration of a specific pipeline before running search queries.

Build production-grade OpenAI Agents SDK workflows that query and audit your live LlamaIndex RAG pipelines with zero configuration.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect LlamaIndex (AI Data Framework & RAG) MCP to OpenAI Agents SDK

Create your Vinkius account to connect LlamaIndex (AI Data Framework & RAG) to OpenAI Agents SDK 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 LlamaIndex (AI Data Framework & RAG) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query LlamaIndex pipelines directly from OpenAI Agents SDK

The `query_pipeline` tool lets your OpenAI agent query your LlamaIndex RAG pipelines directly using natural language. It returns raw semantic search results inside the OpenAI execution loop, allowing your agent to make decisions based on up-to-date documentation. You register this tool by passing the HTTP parameters to the OpenAI Agents SDK constructor, which automatically discovers your LlamaIndex pipelines. This setup means your OpenAI agent doesn't need custom code to fetch context from your vector indexes.

Audit source files inside the MCP Server sandbox

The `list_files` tool exposes the raw source documents ingested by your LlamaIndex pipeline directly to your OpenAI agent. This lets your OpenAI agent check if a specific document is already indexed before it attempts to answer a user's query. Combining this tool with the OpenAI dashboard gives you a complete audit trail of which LlamaIndex files your agent inspected. You can verify that your OpenAI agent is reading from the correct sources within the secure MCP Server sandbox.

Discover active projects and LlamaCloud indexes

The `list_projects` and `list_indexes` tools allow your OpenAI agent to scan your active LlamaCloud configurations dynamically. Your OpenAI agent can switch between different project contexts based on the user's specific request. This metadata discovery happens entirely within the Vinkius MCP Server sandbox, letting your OpenAI agent read the available LlamaIndex configurations. Your agent selects the correct pipeline to target, avoiding hardcoded database IDs in your Python codebase.

Setup guide

Set up LlamaIndex (AI Data Framework & RAG) MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all LlamaIndex (AI Data Framework & RAG) tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives LlamaIndex (AI Data Framework & RAG) tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate LlamaIndex (AI Data Framework & RAG) tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="LlamaIndex (AI Data Framework & RAG) Agent",
            instructions="You have access to LlamaIndex (AI Data Framework & RAG) tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 LlamaIndex. 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 LlamaIndex (AI Data Framework & RAG) 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 LlamaIndex (AI Data Framework & RAG) MCP in OpenAI Agents SDK

Install the OpenAI Agents SDK and instantiate the MCP server using `MCPServerStreamableHttp` to connect your LlamaIndex pipelines. Pass this server instance in the `mcp_servers` list when creating your OpenAI agent to discover the six available tools automatically.

Yes, you can run parallel LlamaIndex queries using the OpenAI Agents SDK. Set `cacheToolsList=True` in the server parameters to prevent the OpenAI agent from re-fetching tool definitions, keeping latency low when executing `query_pipeline` across multiple concurrent runs.

Your OpenAI agent uses the `list_pipelines` tool to fetch all deployed LlamaIndex data pipelines. The agent can then call `get_pipeline` to inspect the configuration of a specific pipeline before running search queries.

The OpenAI Agents SDK catches execution errors from the LlamaIndex MCP server and reports them back to the agent. If `query_pipeline` encounters an issue, you can inspect the error trace in the OpenAI dashboard to debug the failure.

Your LlamaIndex source files, indexes, and pipeline metadata remain inside the secure Vinkius sandbox. No raw data is stored on Vinkius servers, and the OpenAI Agents SDK connects using ephemeral, single-endpoint authentication to prevent exposure.

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