How to Use the Marqo AI (Vector Search & Embeddings) MCP in LlamaIndex

Q: Can I use LlamaIndex to keep track of my Marqo indexes?

Yes. You can build a simple agent that runs listindexes and getindexstats on a schedule. You then use LlamaIndex to index the text output of those commands, creating a searchable log of your index configurations and sizes.

Q: When should my agent use adddocuments with Marqo AI (Vector Search & Embeddings) in a LlamaIndex app?

Use adddocuments when your agent needs to update the underlying knowledge in Marqo. For example, if your application ingests new articles, the agent can call this tool to make sure they are immediately available for future tensorsearch queries.

Q: What data privacy measures are in place for the Marqo AI (Vector Search & Embeddings) MCP Server when used with LlamaIndex?

The server processes the JSON documents you send via adddocuments and the document IDs for deletedocuments. All operations run within a zero-trust environment on Vinkius. The connection is secured, and the server instance handling your request is temporary.

Turn your Marqo indexes into a queryable knowledge base that your LlamaIndex RAG application can search.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Marqo AI (Vector Search & Embeddings) MCP to LlamaIndex

Create your Vinkius account to connect Marqo AI (Vector Search & Embeddings) 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 Marqo AI (Vector Search & Embeddings) with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a RAG system on your Marqo data

Use Marqo for what it's good at: fast, scalable vector search. Your LlamaIndex application can call `tensor_search` to get a set of relevant documents. Then, it uses that output as the context to generate a precise, grounded answer to the user's question. This combines live data retrieval with generative AI. Instead of just getting a list of search results, the user gets a synthesized answer based on the content found by `tensor_search`. It's the core of any modern RAG setup.

Index your infrastructure's metadata

Don't just index your content; index the state of your indexes. You can have your LlamaIndex app periodically call `list_indexes` and `get_index_stats`, then feed that output into a separate vector store. This creates a searchable knowledge base of your Marqo infrastructure. Now you can ask questions like, "How many documents are in the 'products-v3' index?" or "Which indexes were created last week?" Your agent finds the answer from the indexed output of this MCP Server, giving you an easy way to monitor your setup.

Augment queries with live data using LlamaIndex

LlamaIndex agents can make smart decisions about when to use stored knowledge versus fetching new data. An agent can first try to answer a question from its existing index. If the data seems stale or insufficient, it can decide to run a fresh `tensor_search` against Marqo for the latest information. This hybrid approach gives you both speed and accuracy. You get fast responses from the LlamaIndex knowledge base for common queries, with the ability to get live results from Marqo for anything time-sensitive.

Setup guide

Set up Marqo AI (Vector Search & Embeddings) 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 Marqo AI (Vector Search & Embeddings) 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 Marqo AI (Vector Search & Embeddings) tools.",
)
response = await agent.run("List recent Marqo AI (Vector Search & Embeddings) 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 Marqo 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 Marqo AI (Vector Search & Embeddings) 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 Marqo AI (Vector Search & Embeddings) MCP in LlamaIndex

Your LlamaIndex agent takes a user's question and calls the `tensor_search` tool to find relevant documents in your Marqo index. It then feeds the content of those documents into an LLM prompt as context to generate a detailed, accurate answer.

Yes. You can build a simple agent that runs `list_indexes` and `get_index_stats` on a schedule. You then use LlamaIndex to index the text output of those commands, creating a searchable log of your index configurations and sizes.

Use `add_documents` when your agent needs to update the underlying knowledge in Marqo. For example, if your application ingests new articles, the agent can call this tool to make sure they are immediately available for future `tensor_search` queries.

LlamaIndex itself doesn't, but you can configure it to. You can use the output from tools like `tensor_search` or `get_index_stats` and explicitly index it into a separate vector store managed by LlamaIndex for later retrieval.

The server processes the JSON documents you send via `add_documents` and the document IDs for `delete_documents`. All operations run within a zero-trust environment on Vinkius. The connection is secured, and the server instance handling your request is temporary.

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