How to integrate Alpha vantage MCP with LlamaIndex

Trusted by
AWS
Glean
Zoom
Airtable
GET STARTED FOR FREEGET A DEMO

30 min · no commitment · see it on your stack

Alpha vantage logo
LlamaIndex logo
divider

Introduction

This guide walks you through connecting Alpha vantage to LlamaIndex using the Composio tool router. By the end, you'll have a working Alpha vantage agent that can get latest brent crude oil prices, show upcoming earnings calendar for tech stocks, fetch annual balance sheet for apple through natural language commands.

This guide will help you understand how to give your LlamaIndex agent real control over a Alpha vantage account through Composio's Alpha vantage MCP server.

Before we dive in, let's take a quick look at the key ideas and tools involved.

Also integrate Alpha vantage with

TL;DR

Here's what you'll learn:
  • Set your OpenAI and Composio API keys
  • Install LlamaIndex and Composio packages
  • Create a Composio Tool Router session for Alpha vantage
  • Connect LlamaIndex to the Alpha vantage MCP server
  • Build a Alpha vantage-powered agent using LlamaIndex
  • Interact with Alpha vantage through natural language

What is LlamaIndex?

LlamaIndex is a data framework for building LLM applications. It provides tools for connecting LLMs to external data sources and services through agents and tools.

Key features include:

  • ReAct Agent: Reasoning and acting pattern for tool-using agents
  • MCP Tools: Native support for Model Context Protocol
  • Context Management: Maintain conversation context across interactions
  • Async Support: Built for async/await patterns

What is the Alpha vantage MCP server, and what's possible with it?

The Alpha Vantage MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Alpha Vantage account. It provides structured and secure access to real-time and historical financial data, so your agent can fetch market prices, analyze commodities, review company financials, and retrieve earnings transcripts on your behalf.

  • Get global commodities and market prices: Instantly retrieve real-time and historical price indices for all major commodities and markets—including aluminum, copper, coffee, corn, and crude oil.
  • Analyze company financial statements: Ask your agent to fetch detailed annual or quarterly balance sheets for any supported company, making fiscal analysis a breeze.
  • Access upcoming earnings calendars: Pull comprehensive earnings schedules for the next three months, so you never miss an important financial event.
  • Retrieve earnings call transcripts with sentiment: Automatically obtain full-text earnings call transcripts for a given company and quarter, including sentiment signals to help you gauge market tone.
  • Perform historical data research: Let your agent gather time series data for commodities and financial indicators, supporting deeper market research and trend analysis.

Supported Tools & Triggers

Tools
Get All Commodities Price IndexTool to retrieve the global price index of all commodities.
ALUMINUMTool to fetch global aluminum prices.
Balance SheetTool to return annual and quarterly balance sheets for a company.
Brent Crude Oil PricesTool to fetch Brent crude oil prices.
Cash FlowTool to return annual and quarterly cash flow statements for a company.
Global Coffee PriceTool to retrieve the global coffee price series.
Company Overview (Stocks Only)Tool to retrieve company overview and fundamental data for individual company stocks.
COPPERTool to fetch global price of copper in monthly, quarterly, and annual intervals.
CornTool to retrieve global price of corn in monthly, quarterly, and annual intervals.
COTTONTool to retrieve global cotton prices in monthly, quarterly, and annual intervals.
Consumer Price Index (CPI)Tool to fetch monthly and semiannual Consumer Price Index (CPI) data of the United States.
Crypto Intraday Time SeriesTool to retrieve intraday time series data for cryptocurrencies with realtime updates.
Currency Exchange RateTool to retrieve real-time exchange rate for a currency pair.
Digital Currency Daily Time SeriesTool to retrieve daily historical time series for a digital currency traded on a specific market.
Digital Currency Monthly Time SeriesTool to retrieve monthly digital currency prices in a fiat currency.
Digital Currency Weekly Time SeriesTool to retrieve weekly digital currency prices in a fiat currency.
Durable Goods OrdersTool to fetch monthly manufacturers' new orders of durable goods data for the United States.
EarningsTool to retrieve annual and quarterly earnings (EPS history) for a specific company symbol.
Earnings CalendarTool to return the earnings calendar for the next three months.
Earnings Call TranscriptTool to retrieve the earnings call transcript for a given company and quarter.
Federal Funds RateTool to fetch daily, weekly, and monthly federal funds rate data of the United States.
FX Daily Time SeriesTool to fetch daily time series (open, high, low, close) for a currency pair.
FX Intraday Time SeriesTool to retrieve intraday OHLC time series for a forex pair at 1-60 minute intervals (premium endpoint).
FX Monthly Time SeriesTool to get monthly time series (open, high, low, close) for a currency pair.
FX Weekly Time SeriesTool to get weekly time series (open, high, low, close) for a currency pair.
Get Dividend HistoryTool to retrieve historical dividend payment records for a stock symbol.
Get Historical OptionsTool to retrieve full historical options chain for a symbol on a specific date with 15+ years of history, including Greeks and IV.
Analytics Sliding WindowTool to retrieve advanced analytics metrics with sliding window calculations for trend analysis.
Global QuoteTool to retrieve latest price and volume information for a specified security ticker in realtime.
Income StatementTool to fetch annual and quarterly income statements.
InflationTool to fetch annual U.
IPO CalendarTool to retrieve the IPO calendar for the next three months.
Listing StatusTool to fetch listing status of US stocks and ETFs.
Market StatusTool to retrieve current market status (open/closed) for global stock exchanges.
News SentimentTool to fetch live and historical market news & sentiment.
Nonfarm PayrollTool to fetch monthly U.
Real GDPTool to fetch U.
Real GDP Per CapitaTool to fetch quarterly Real GDP per capita data of the United States.
Realtime Bulk QuotesTool to retrieve realtime quotes for US-traded symbols in bulk (up to 100 symbols per request).
Retail SalesTool to fetch monthly retail trade sales data of the United States.
Sector PerformanceTool to retrieve real-time and historical sector performance data.
Stock SplitsTool to retrieve historical stock split events for a symbol.
Global Sugar PriceTool to retrieve the global sugar price series.
Symbol SearchTool to search for best-matching symbols based on keywords.
Technical IndicatorTool to fetch technical indicators for the specified equity or currency pair.
Time Series DailyTool to retrieve daily time series data (date, daily open, high, low, close, volume) for a global equity symbol, covering 20+ years of historical data.
Time Series IntradayTool to retrieve intraday OHLCV for a given equity.
Time Series Intraday ExtendedTool to retrieve historical intraday OHLCV data for the trailing 2 years, covering over 2 million data points per ticker.
Time Series MonthlyTool to retrieve monthly open, high, low, close, and volume for a global equity.
Monthly Adjusted Time SeriesTool to retrieve monthly adjusted OHLC and volume for a global equity.
Weekly Time SeriesTool to fetch weekly open, high, low, close, and volume for a global equity symbol.
Weekly Adjusted Time SeriesTool to fetch weekly adjusted time series data with split/dividend adjustments, covering 20+ years of historical data.
Top Gainers, Losers & Most ActiveTool to fetch the top 20 gainers, losers, and most actively traded US tickers.
US Treasury YieldTool to fetch US Treasury yield data for specified maturity and interval.
Unemployment RateTool to fetch monthly unemployment rate data of the United States.
WHEATTool to fetch global price of wheat.

What is the Composio tool router, and how does it fit here?

What is Composio SDK?

Composio's Composio SDK helps agents find the right tools for a task at runtime. You can plug in multiple toolkits (like Gmail, HubSpot, and GitHub), and the agent will identify the relevant app and action to complete multi-step workflows. This can reduce token usage and improve the reliability of tool calls. Read more here: Getting started with Composio SDK

The tool router generates a secure MCP URL that your agents can access to perform actions.

How the Composio SDK works

The Composio SDK follows a three-phase workflow:

  1. Discovery: Searches for tools matching your task and returns relevant toolkits with their details.
  2. Authentication: Checks for active connections. If missing, creates an auth config and returns a connection URL via Auth Link.
  3. Execution: Executes the action using the authenticated connection.

Step-by-step Guide

Prerequisites

Before you begin, make sure you have:
  • Python 3.8/Node 16 or higher installed
  • A Composio account with the API key
  • An OpenAI API key
  • A Alpha vantage account and project
  • Basic familiarity with async Python/Typescript

Getting API Keys for OpenAI, Composio, and Alpha vantage

OpenAI API key (OPENAI_API_KEY)
  • Go to the OpenAI dashboard
  • Create an API key if you don't have one
  • Assign it to OPENAI_API_KEY in .env
Composio API key and user ID
  • Log into the Composio dashboard
  • Copy your API key from Settings
    • Use this as COMPOSIO_API_KEY
  • Pick a stable user identifier (email or ID)
    • Use this as COMPOSIO_USER_ID

Installing dependencies

pip install composio-llamaindex llama-index llama-index-llms-openai llama-index-tools-mcp python-dotenv

Create a new Python project and install the necessary dependencies:

  • composio-llamaindex: Composio's LlamaIndex integration
  • llama-index: Core LlamaIndex framework
  • llama-index-llms-openai: OpenAI LLM integration
  • llama-index-tools-mcp: MCP client for LlamaIndex
  • python-dotenv: Environment variable management

Set environment variables

bash
OPENAI_API_KEY=your-openai-api-key
COMPOSIO_API_KEY=your-composio-api-key
COMPOSIO_USER_ID=your-user-id

Create a .env file in your project root:

These credentials will be used to:

  • Authenticate with OpenAI's GPT-5 model
  • Connect to Composio's Tool Router
  • Identify your Composio user session for Alpha vantage access

Import modules

import asyncio
import os
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

Create a new file called alpha vantage_llamaindex_agent.py and import the required modules:

Key imports:

  • asyncio: For async/await support
  • Composio: Main client for Composio services
  • LlamaIndexProvider: Adapts Composio tools for LlamaIndex
  • ReActAgent: LlamaIndex's reasoning and action agent
  • BasicMCPClient: Connects to MCP endpoints
  • McpToolSpec: Converts MCP tools to LlamaIndex format

Load environment variables and initialize Composio

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set in the environment")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set in the environment")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set in the environment")

What's happening:

This ensures missing credentials cause early, clear errors before the agent attempts to initialise.

Create a Tool Router session and build the agent function

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["alpha_vantage"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")

    description = "An agent that uses Composio Tool Router MCP tools to perform Alpha vantage actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Alpha vantage actions.
    """
    return ReActAgent(tools=tools, llm=llm, description=description, system_prompt=system_prompt, verbose=True)

What's happening here:

  • We create a Composio client using your API key and configure it with the LlamaIndex provider
  • We then create a tool router MCP session for your user, specifying the toolkits we want to use (in this case, alpha vantage)
  • The session returns an MCP HTTP endpoint URL that acts as a gateway to all your configured tools
  • LlamaIndex will connect to this endpoint to dynamically discover and use the available Alpha vantage tools.
  • The MCP tools are mapped to LlamaIndex-compatible tools and plug them into the Agent.

Create an interactive chat loop

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

What's happening here:

  • We're creating a direct terminal interface to chat with your Alpha vantage database
  • The LLM's responses are streamed to the CLI for faster interaction.
  • The agent uses context to maintain conversation history
  • You can type 'quit' or 'exit' to stop the chat loop gracefully
  • Agent responses and any errors are displayed in a clear, readable format

Define the main entry point

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")

What's happening here:

  • We're orchestrating the entire application flow
  • The agent gets built with proper error handling
  • Then we kick off the interactive chat loop so you can start talking to Alpha vantage

Run the agent

npx ts-node llamaindex-agent.ts

When prompted, authenticate and authorise your agent with Alpha vantage, then start asking questions.

Complete Code

Here's the complete code to get you started with Alpha vantage and LlamaIndex:

import asyncio
import os
import signal
import dotenv

from composio import Composio
from composio_llamaindex import LlamaIndexProvider
from llama_index.core.agent.workflow import ReActAgent
from llama_index.core.workflow import Context
from llama_index.llms.openai import OpenAI
from llama_index.tools.mcp import BasicMCPClient, McpToolSpec

dotenv.load_dotenv()

OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
COMPOSIO_API_KEY = os.getenv("COMPOSIO_API_KEY")
COMPOSIO_USER_ID = os.getenv("COMPOSIO_USER_ID")

if not OPENAI_API_KEY:
    raise ValueError("OPENAI_API_KEY is not set")
if not COMPOSIO_API_KEY:
    raise ValueError("COMPOSIO_API_KEY is not set")
if not COMPOSIO_USER_ID:
    raise ValueError("COMPOSIO_USER_ID is not set")

async def build_agent() -> ReActAgent:
    composio_client = Composio(
        api_key=COMPOSIO_API_KEY,
        provider=LlamaIndexProvider(),
    )

    session = composio_client.create(
        user_id=COMPOSIO_USER_ID,
        toolkits=["alpha_vantage"],
    )

    mcp_url = session.mcp.url
    print(f"Composio MCP URL: {mcp_url}")

    mcp_client = BasicMCPClient(mcp_url, headers={"x-api-key": COMPOSIO_API_KEY})
    mcp_tool_spec = McpToolSpec(client=mcp_client)
    tools = await mcp_tool_spec.to_tool_list_async()

    llm = OpenAI(model="gpt-5")
    description = "An agent that uses Composio Tool Router MCP tools to perform Alpha vantage actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Alpha vantage actions.
    """
    return ReActAgent(
        tools=tools,
        llm=llm,
        description=description,
        system_prompt=system_prompt,
        verbose=True,
    );

async def chat_loop(agent: ReActAgent) -> None:
    ctx = Context(agent)
    print("Type 'quit', 'exit', or Ctrl+C to stop.")

    while True:
        try:
            user_input = input("\nYou: ").strip()
        except (KeyboardInterrupt, EOFError):
            print("\nBye!")
            break

        if not user_input or user_input.lower() in {"quit", "exit"}:
            print("Bye!")
            break

        try:
            print("Agent: ", end="", flush=True)
            handler = agent.run(user_input, ctx=ctx)

            async for event in handler.stream_events():
                # Stream token-by-token from LLM responses
                if hasattr(event, "delta") and event.delta:
                    print(event.delta, end="", flush=True)
                # Show tool calls as they happen
                elif hasattr(event, "tool_name"):
                    print(f"\n[Using tool: {event.tool_name}]", flush=True)

            # Get final response
            response = await handler
            print()  # Newline after streaming
        except KeyboardInterrupt:
            print("\n[Interrupted]")
            continue
        except Exception as e:
            print(f"\nError: {e}")

async def main() -> None:
    agent = await build_agent()
    await chat_loop(agent)

if __name__ == "__main__":
    # Handle Ctrl+C gracefully
    signal.signal(signal.SIGINT, lambda s, f: (print("\nBye!"), exit(0)))
    try:
        asyncio.run(main())
    except KeyboardInterrupt:
        print("\nBye!")

Conclusion

You've successfully connected Alpha vantage to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways:
  • Tool Router dynamically exposes Alpha vantage tools through an MCP endpoint
  • LlamaIndex's ReActAgent handles reasoning and orchestration; Composio handles integrations
  • The agent becomes more capable without increasing prompt size
  • Async Python provides clean, efficient execution of agent workflows
You can easily extend this to other toolkits like Gmail, Notion, Stripe, GitHub, and more by adding them to the toolkits parameter.

How to build Alpha vantage MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Alpha vantage MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Alpha vantage MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Alpha vantage MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Alpha vantage MCP with Claude Cowork

Codex logo

Codex

Use Alpha vantage MCP with Codex

OpenClaw logo

OpenClaw

Use Alpha vantage MCP with OpenClaw

Hermes logo

Hermes

Use Alpha vantage MCP with Hermes

CLI logo

CLI

Use Alpha vantage MCP with CLI

Google ADK logo

Google ADK

Use Alpha vantage MCP with Google ADK

LangChain logo

LangChain

Use Alpha vantage MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Alpha vantage MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Alpha vantage MCP with Mastra AI

CrewAI logo

CrewAI

Use Alpha vantage MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Alpha vantage MCP?

With a standalone Alpha vantage MCP server, the agents and LLMs can only access a fixed set of Alpha vantage tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Alpha vantage and many other apps based on the task at hand, all through a single MCP endpoint.

Can I use Tool Router MCP with LlamaIndex?

Yes, you can. LlamaIndex fully supports MCP integration. You get structured tool calling, message history handling, and model orchestration while Tool Router takes care of discovering and serving the right Alpha vantage tools.

Can I manage the permissions and scopes for Alpha vantage while using Tool Router?

Yes, absolutely. You can configure which Alpha vantage scopes and actions are allowed when connecting your account to Composio. You can also bring your own OAuth credentials or API configuration so you keep full control over what the agent can do.

How safe is my data with Composio Tool Router?

All sensitive data such as tokens, keys, and configuration is fully encrypted at rest and in transit. Composio is SOC 2 Type 2 compliant and follows strict security practices so your Alpha vantage data and credentials are handled as safely as possible.

Used by agents from

Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai
Context
Letta
glean
HubSpot
Agent.ai
Altera
DataStax
Entelligence
Rolai

Never worry about agent reliability

We handle tool reliability, observability, and security so you never have to second-guess an agent action.

Get started for freeGet a demo↗