How to Use the Marketaux MCP in LlamaIndex

Q: How do I configure LlamaIndex with Marketaux?

Install llama-index-tools-mcp. Use BasicMCPClient to connect to the Marketaux endpoint, then wrap it in McpToolSpec to expose the endpoints to your agent.

Q: Can LlamaIndex embed Marketaux news articles?

Yes. You call searchnews, parse the JSON response, and push the text directly into your vector index. You can then run semantic searches against live financial reporting.

Q: Does Marketaux support filtering in LlamaIndex?

You control access using the allowedtools filter. If you only want your agent to read reference data, restrict it to getindices and getstockmarketstatus.

Q: How often should I refresh the index?

News moves fast. You should run getlatestnews on a cron job and update your vector store every five minutes during active trading hours.

Q: How does the system handle my financial queries?

Your RAG prompts and the resulting searchnews article payloads process through a zero-trust architecture. Vinkius requires a single endpoint token and isolates every request. Your proprietary search terms never leak into shared memory.

Index Marketaux data with LlamaIndex. Turn live financial news and sentiment scores into a searchable vector database.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Marketaux MCP to LlamaIndex

Create your Vinkius account to connect Marketaux 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 Marketaux with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Marketaux MCP Server Integration

This MCP Server connects your LlamaIndex pipelines to live market intelligence. You run `get_latest_news` and index the raw article data straight into your vector store. Your applications query actual financial facts instead of hallucinating answers. Pass the tools using `McpToolSpec`. Your FunctionAgent pulls allowed tools and fetches data automatically. When a user asks about tech stocks, the agent hits the API, embeds the response, and grounds the final answer in real-time reporting.

Index trending sentiment data

The `get_sentiment_analysis` tool delivers hard numbers on market mood. You pull these scores and store them alongside historical price data in your RAG setup. Your queries now cross-reference quantitative sentiment against qualitative news. Add `get_trending_news` to capture momentum shifts. The system embeds high-velocity articles as they break. You search your index later and find exactly when the narrative changed for a specific asset class.

Map exchange and entity structures

Use `search_exchanges` and `list_industries` to build a structural map of the market. LlamaIndex ingests this reference data to understand relationships between sectors. When you query an obscure ticker, the system knows exactly where it trades. The `get_symbols` and `get_entities` endpoints keep your knowledge base accurate. You refresh your vector store with the latest supported symbols daily. Your RAG application never fails because of outdated ticker references.

Setup guide

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

Install `llama-index-tools-mcp`. Use `BasicMCPClient` to connect to the Marketaux endpoint, then wrap it in `McpToolSpec` to expose the endpoints to your agent.

Yes. You call `search_news`, parse the JSON response, and push the text directly into your vector index. You can then run semantic searches against live financial reporting.

You control access using the `allowed_tools` filter. If you only want your agent to read reference data, restrict it to `get_indices` and `get_stock_market_status`.

News moves fast. You should run `get_latest_news` on a cron job and update your vector store every five minutes during active trading hours.

Your RAG prompts and the resulting `search_news` article payloads process through a zero-trust architecture. Vinkius requires a single endpoint token and isolates every request. Your proprietary search terms never leak into shared memory.

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