How to Use the Exa MCP in LlamaIndex

Q: How do I ingest Exa search results into a LlamaIndex vector store?

You can use searchwithcontents to get both the metadata and the full page text. Then, map these results into LlamaIndex Document objects to chunk and index them directly into your vector database.

Q: Can LlamaIndex query engines decide when to use Exa neural search?

Yes, you can register the searchneural MCP tool as a query engine tool. The router will analyze the user query and decide whether to search the web or stick to your local index.

Q: How does Exa help reduce hallucinations in LlamaIndex pipelines?

By using answer to get a direct response or getcontents to pull raw page data, you ground your engine in real-time web facts. This prevents the LLM from relying on outdated training data.

Q: Can I filter search results by domain before indexing them?

Yes, you can use searchdomain to restrict results to a specific list of websites. This keeps your indexed data clean by filtering out irrelevant domains before the text ever reaches your vector store.

Index live, context-aware web search results directly into your LlamaIndex vector stores for hallucination-free RAG.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Exa MCP to LlamaIndex

Create your Vinkius account to connect Exa 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 Exa with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ground your LlamaIndex RAG with neural search

The `search_neural` tool retrieves contextually relevant web pages to ground your LlamaIndex RAG pipelines. By exposing the MCP tools like `search_neural` to your indexer, you pull web pages that match the actual concept of your query, rather than just matching keywords. Once you find a high-quality page, you can use `get_contents` to extract the full text. This text is converted into document nodes, which LlamaIndex can chunk and index into your local vector store for immediate retrieval.

Build dynamic knowledge bases with Exa MCP Server tools

The `search_recent` tool pulls the latest updates on any topic to keep your LlamaIndex knowledge base fresh. This MCP integration lets your query engine run real-time searches to pull the latest updates on any topic and index them on the fly. If a specific source is highly relevant, the engine can use `find_similar_with_contents` to discover and index related pages in one go. This automates the entire research and indexing loop, keeping your vector database fresh without manual scraping.

Target domain-specific lookups for clean indexing

The `search_domain` tool limits your LlamaIndex indexing queries to high-quality, trusted web domains. This ensures the data entering your pipeline is clean and free of forum spam. For precise lookups, the query engine can fall back to `search_keyword` when it needs to index specific version numbers or code snippets. Having both options lets you build a hybrid indexing pipeline that handles both concepts and exact matches.

Setup guide

Set up Exa 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 Exa 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 Exa tools.",
)
response = await agent.run("List recent Exa 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 Exa. 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 Exa 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 Exa MCP in LlamaIndex

You can use `search_with_contents` to get both the metadata and the full page text. Then, map these results into LlamaIndex Document objects to chunk and index them directly into your vector database.

Yes, you can register the `search_neural` MCP tool as a query engine tool. The router will analyze the user query and decide whether to search the web or stick to your local index.

By using `answer` to get a direct response or `get_contents` to pull raw page data, you ground your engine in real-time web facts. This prevents the LLM from relying on outdated training data.

Yes, you can use `search_domain` to restrict results to a specific list of websites. This keeps your indexed data clean by filtering out irrelevant domains before the text ever reaches your vector store.

All retrieved page contents and web search queries are handled inside an ephemeral, zero-trust sandbox. Your connection credentials are encrypted, and no search data is cached or stored on our servers.

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