How to integrate Polygon io MCP with LlamaIndex

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

30 min · no commitment · see it on your stack

Polygon io logo
LlamaIndex logo
divider

Introduction

This guide walks you through connecting Polygon io to LlamaIndex using the Composio tool router. By the end, you'll have a working Polygon io agent that can get daily summary for aapl stock, retrieve latest news on tsla ticker, check if nyse market is open now through natural language commands.

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

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

Also integrate Polygon io 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 Polygon io
  • Connect LlamaIndex to the Polygon io MCP server
  • Build a Polygon io-powered agent using LlamaIndex
  • Interact with Polygon io 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 Polygon io MCP server, and what's possible with it?

The Polygon io MCP server is an implementation of the Model Context Protocol that connects your AI agent and assistants like Claude, Cursor, etc directly to your Polygon io account. It provides structured and secure access to real-time and historical financial market data, so your agent can pull ticker lists, fetch stock summaries, analyze technical indicators, and surface news updates on your behalf.

  • Comprehensive ticker discovery and lookup: Instantly retrieve detailed lists of supported stock, forex, crypto, and option tickers to power your trading dashboards or research tools.
  • Daily summary and technical analysis: Ask your agent to fetch daily price summaries, calculate exponential moving averages, MACD, or RSI for any supported ticker and timeframe.
  • Financial events and dividend insights: Pull up historical dividend distributions, keep tabs on scheduled market holidays, and plan trading activities around real exchange calendars.
  • Up-to-date market status monitoring: Have your agent check real-time market open/close statuses and trading conditions across multiple exchanges and asset classes.
  • Automated news aggregation for securities: Let your agent gather the latest news articles, sentiment analysis, and headlines for specific tickers, helping you stay informed with minimal effort.

Supported Tools & Triggers

Tools
Get All TickersTool to retrieve a comprehensive list of supported ticker symbols across all asset classes.
Get Condition CodesTool to retrieve a unified list of trade and quote condition codes and their definitions.
Get Crypto EMATool to calculate Exponential Moving Average (EMA) technical indicator for a crypto ticker.
Get Crypto MACDTool to calculate Moving Average Convergence/Divergence (MACD) technical indicator for a crypto ticker.
Get Crypto Open/CloseTool to get the open, close, high, low, and volume for a cryptocurrency pair on a specific date.
Get Crypto RSITool to calculate the Relative Strength Index (RSI) for a cryptocurrency ticker.
Get Crypto SMATool to calculate Simple Moving Average (SMA) technical indicator for a cryptocurrency ticker.
Get Daily Open/CloseTool to get the daily open, close, after-hours, and pre-market prices for a stock on a specific date.
Get DividendsTool to retrieve a historical record of cash dividend distributions for a given ticker.
Get Economy Inflation Indicators (Enhanced)Tool to retrieve key indicators of realized inflation including CPI and PCE price indexes with comprehensive date filtering.
Get Exponential Moving AverageTool to retrieve the Exponential Moving Average for a stock ticker.
Get SEC FilingTool to retrieve detailed information about a specific SEC filing by filing ID.
Get SEC Filing FileTool to download a specific file from an SEC filing.
Get Forex EMATool to calculate Exponential Moving Average (EMA) technical indicator for a forex pair.
Get Forex MACDTool to calculate Moving Average Convergence/Divergence (MACD) technical indicator for a forex pair.
Get Forex Real-Time Currency ConversionTool to convert amounts between currency pairs using real-time forex rates.
Get Forex RSITool to calculate the Relative Strength Index (RSI) technical indicator for a forex pair.
Get Forex SMATool to calculate Simple Moving Average (SMA) technical indicator for a forex pair.
Get Futures QuotesTool to get real-time quote information for futures contracts with bid/ask prices, sizes, and timestamps.
Get Grouped Daily Market SummaryTool to retrieve daily OHLCV data for the entire market for a given date.
Get Historic Forex TicksTool to get historic ticks for a currency pair on a specific date.
Get Inflation ExpectationsTool to retrieve inflation expectations data from the Federal Reserve, including market-based rates and Cleveland Fed model estimates.
Get IPO DataTool to retrieve comprehensive information on Initial Public Offerings (IPOs), including upcoming and historical events.
Get Labor Market DataTool to retrieve labor market data including unemployment rate, labor force participation rate, average hourly earnings, and job openings.
Get MACDTool to retrieve the Moving Average Convergence/Divergence (MACD) for a stock ticker.
Get Market HolidaysTool to retrieve upcoming market holidays and their corresponding open/close times.
Get Market StatusTool to retrieve the current trading status across major exchanges and currency markets.
Get NewsTool to retrieve the most recent news articles for a specified ticker.
Get Options Contract OverviewTool to retrieve comprehensive details about a specific options contract including contract type, exercise style, expiration date, strike price, and underlying ticker.
Get Options EMATool to calculate Exponential Moving Average (EMA) technical indicator for an options ticker.
Get Options MACDTool to calculate Moving Average Convergence/Divergence (MACD) technical indicator for an options ticker.
Get Options RSITool to calculate Relative Strength Index (RSI) technical indicator for an options ticker.
Get Options SMATool to calculate Simple Moving Average (SMA) technical indicator for an options ticker.
Get Related CompaniesTool to retrieve tickers related to a given ticker based on similar business or market characteristics.
Get RSITool to retrieve the Relative Strength Index (RSI) for a stock ticker.
Get Simple Moving AverageTool to retrieve the Simple Moving Average (SMA) for any ticker (stocks, forex, crypto).
Get SplitsTool to retrieve historical stock split events for a given ticker.
Get Stocks Custom BarsTool to retrieve aggregated historical OHLC and volume data for a stock over custom date ranges with configurable time windows.
Get Stocks Daily Market SummaryTool to retrieve daily OHLC, volume, and VWAP data for all U.
Get Stocks Filings Risk FactorsTool to retrieve risk factors identified in companies' 10K filings.
Get Stocks Filings SectionsTool to retrieve raw text content from specific sections of SEC filings (10-K, 10-Q, etc.
Get Stocks Free FloatTool to retrieve free float data for US-listed securities showing the most recent available number of shares available for public trading and the percentage of total shares outstanding.
Get Stocks Full Market SnapshotTool to retrieve a comprehensive snapshot of the entire U.
Get Stocks Income StatementsTool to retrieve comprehensive income statement data including revenue, expenses, and net income from company SEC filings.
Get Stocks Previous Day BarTool to retrieve the previous trading day's open, high, low, close (OHLC), and volume data for a stock ticker.
Get Stocks Risk Factor TaxonomiesTool to retrieve the complete list of risk factor classifications used in the risk factors endpoint.
Get Stocks V1 DividendsTool to retrieve historical dividend payment records for US stocks with split-adjusted amounts and historical adjustment factors.
Get Short Interest DataTool to retrieve comprehensive FINRA short interest data that tracks the short selling metrics for securities on a specific settlement date.
Get Short Volume DataTool to retrieve short selling volume data for stock tickers.
Get Stocks V1 SplitsTool to retrieve historical stock split and reverse split events for US equities with historical adjustment factors for price normalization.
Get Ticker EventsTool to retrieve timeline of ticker change events such as symbol renaming or rebranding.
Get Ticker OverviewTool to retrieve comprehensive details for a single ticker, including identifiers, industry, and branding assets.
Get Ticker TypesTool to retrieve a list of all ticker types supported by Polygon.
Get Treasury YieldsTool to retrieve daily market yields for US Treasury securities across standard maturities (1-month to 30-year).
List ExchangesTool to retrieve all exchanges supported by Polygon.
List Filing FilesTool to retrieve files associated with an SEC filing by filing ID.
List SEC FilingsTool to retrieve SEC filings from the Polygon.
List Options ContractsTool to list and filter options contracts by underlying ticker, type, expiration, strike, and more.
Last Quote for a SymbolTool to retrieve the last quote tick for a given stock symbol.
Last Trade for a Currency PairTool to retrieve the last trade tick for a currency pair in the forex market.

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 Polygon io account and project
  • Basic familiarity with async Python/Typescript

Getting API Keys for OpenAI, Composio, and Polygon io

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 Polygon io 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 polygon io_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=["polygon_io"],
    )

    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 Polygon io actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Polygon io 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, polygon io)
  • 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 Polygon io 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 Polygon io 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 Polygon io

Run the agent

npx ts-node llamaindex-agent.ts

When prompted, authenticate and authorise your agent with Polygon io, then start asking questions.

Complete Code

Here's the complete code to get you started with Polygon io 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=["polygon_io"],
    )

    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 Polygon io actions."
    system_prompt = """
    You are a helpful assistant connected to Composio Tool Router.
    Use the available tools to answer user queries and perform Polygon io 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 Polygon io to LlamaIndex through Composio's Tool Router MCP layer. Key takeaways:
  • Tool Router dynamically exposes Polygon io 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 Polygon io MCP Agent with another framework

OpenAI Agents SDK logo

OpenAI Agents SDK

Use Polygon io MCP with OpenAI Agents SDK

Claude Agent SDK logo

Claude Agent SDK

Use Polygon io MCP with Claude Agent SDK

Claude Code logo

Claude Code

Use Polygon io MCP with Claude Code

Claude Cowork logo

Claude Cowork

Use Polygon io MCP with Claude Cowork

Codex logo

Codex

Use Polygon io MCP with Codex

OpenClaw logo

OpenClaw

Use Polygon io MCP with OpenClaw

Hermes logo

Hermes

Use Polygon io MCP with Hermes

CLI logo

CLI

Use Polygon io MCP with CLI

Google ADK logo

Google ADK

Use Polygon io MCP with Google ADK

LangChain logo

LangChain

Use Polygon io MCP with LangChain

Vercel AI SDK logo

Vercel AI SDK

Use Polygon io MCP with Vercel AI SDK

Mastra AI logo

Mastra AI

Use Polygon io MCP with Mastra AI

CrewAI logo

CrewAI

Use Polygon io MCP with CrewAI

FAQ

What are the differences in Tool Router MCP and Polygon io MCP?

With a standalone Polygon io MCP server, the agents and LLMs can only access a fixed set of Polygon io tools tied to that server. However, with the Composio Tool Router, agents can dynamically load tools from Polygon io 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 Polygon io tools.

Can I manage the permissions and scopes for Polygon io while using Tool Router?

Yes, absolutely. You can configure which Polygon io 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 Polygon io 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↗