How to Use the Exa AI MCP in LlamaIndex

Q: How does LlamaIndex index the raw text returned by Exa AI?

When your agent calls getcontents, the tool returns clean HTML and text. LlamaIndex wraps this string in a Document object, splits it into nodes, and embeds it directly into your configured vector store.

Q: Can I use Exa AI to find similar documents inside LlamaIndex?

Yes, your agent can pass any indexed URL to findsimilar to pull in related web content. This allows LlamaIndex to dynamically expand its knowledge base with semantically connected pages.

Q: Does this Exa AI integration support LlamaIndex MCP tool filtering?

Yes, you can use the allowedtools filter when setting up the McpToolSpec. This lets you restrict your agent to cheap operations like getsearchlinks while blocking heavy content downloads when necessary.

Q: How do I track how much data my RAG agent is consuming?

Have your agent query getapiusage at the start of a run. It can check your remaining crawl credits and adjust its indexing strategy to avoid hitting rate limits.

Index live semantic web content directly into your LlamaIndex vector stores with Exa AI's MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Exa AI MCP to LlamaIndex

Create your Vinkius account to connect Exa 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 Exa AI with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build real-time RAG pipelines with this MCP Server

Calling `search_with_contents` allows your LlamaIndex agent to fetch fresh, semantic web data on demand. The tool extracts clean text content, which the framework automatically indexes into your active vector store for immediate querying. This eliminates the lag between web events and your knowledge base. Your agent can run `get_contents` to pull down specific web pages, turn them into search nodes, and answer user queries with zero hallucinations.

Expand your vector index using semantic web relationships

Using `find_similar` lets your LlamaIndex agent discover related web resources when your local knowledge base lacks depth. This MCP tool lets your LlamaIndex agent discover related web resources and expand the semantic context of your queries without requiring manual curation. The agent takes the newly discovered URLs, runs them through the indexing pipeline, and updates your vector database. This creates a self-growing knowledge graph that adapts as new information is published online.

Filter and ingest high-value web links dynamically

Executing `get_search_links` lets your agent retrieve a clean list of top URLs first, evaluate their relevance, and only index high-priority documents. This selective ingestion keeps your vector stores lean and fast. If a link looks promising, the agent calls `get_contents` to parse the clean HTML. Your retrieval-augmented generation stays highly focused because you aren't bloating your vector index with useless web pages.

Setup guide

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

When your agent calls `get_contents`, the tool returns clean HTML and text. LlamaIndex wraps this string in a Document object, splits it into nodes, and embeds it directly into your configured vector store.

Yes, your agent can pass any indexed URL to `find_similar` to pull in related web content. This allows LlamaIndex to dynamically expand its knowledge base with semantically connected pages.

Yes, you can use the allowed_tools filter when setting up the McpToolSpec. This lets you restrict your agent to cheap operations like `get_search_links` while blocking heavy content downloads when necessary.

Have your agent query `get_api_usage` at the start of a run. It can check your remaining crawl credits and adjust its indexing strategy to avoid hitting rate limits.

The raw HTML and text content fetched from the web are processed entirely within a local, zero-trust sandbox. No external servers intercept your retrieved documents, ensuring your indexed data remains strictly confidential.

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