Compatible with every major AI agent and IDE
What is the Polygon.io MCP Server?
Connect your Polygon.io account to any AI agent to retrieve institutional-grade financial data through natural language. Monitor market trends, analyze historical performance, and inspect company fundamentals without leaving your chat interface.
What you can do
- Market Aggregates — Fetch OHLCV (Open, High, Low, Close, Volume) bars for any ticker over custom timeframes (minute, hour, day)
- Real-Time & Historical Trades — Access tick-by-tick trade data to analyze precise market movements and execution prices
- Company Fundamentals — Retrieve detailed metadata for stock tickers, including industry classifications and company descriptions
- Dividend Tracking — List historical cash dividend distributions, frequencies, and ex-dividend dates for specific assets
- Ticker Discovery — Query the full list of supported tickers and financial instruments available on the platform
How it works
- Subscribe to this server
- Enter your Polygon.io API Key
- Start querying financial markets from Claude, Cursor, or any MCP-compatible client
Who is this for?
- Financial Analysts — quickly pull historical aggregates and dividend data for modeling and reporting
- Traders & Quants — inspect tick-by-tick trades and quotes (NBBO) to validate strategies directly from the terminal
- Fintech Developers — verify ticker metadata and market connectivity while building financial applications
Built-in capabilities (6)
Get aggregate bars for a stock
Get company details for a ticker
List historical dividends
Get tick-by-tick quotes (NBBO)
io. Query all supported tickers
Get tick-by-tick trades
Why LlamaIndex?
LlamaIndex agents combine Polygon.io tool responses with indexed documents for comprehensive, grounded answers. Connect 6 tools through Vinkius and query live data alongside vector stores and SQL databases in a single turn. ideal for hybrid search, data enrichment, and analytical workflows.
- —
Data-first architecture: LlamaIndex agents combine Polygon.io tool responses with indexed documents for comprehensive, grounded answers
- —
Query pipeline framework lets you chain Polygon.io tool calls with transformations, filters, and re-rankers in a typed pipeline
- —
Multi-source reasoning: agents can query Polygon.io, a vector store, and a SQL database in a single turn and synthesize results
- —
Observability integrations show exactly what Polygon.io tools were called, what data was returned, and how it influenced the final answer
Polygon.io in LlamaIndex
Polygon.io and 4,000+ other MCP servers. One platform. One governance layer.
Teams that connect Polygon.io to LlamaIndex through Vinkius don't need to source, host, or maintain individual MCP servers. Every tool call runs inside a hardened runtime with credential isolation, DLP, and a signed audit chain.
Raw MCP | Vinkius | |
|---|---|---|
| Server catalog | Find and host yourself | 4,000+ managed |
| Infrastructure | Self-hosted | Sandboxed V8 isolates |
| Credential handling | Plaintext in config | Vault + runtime injection |
| Data loss prevention | None | Configurable DLP policies |
| Kill switch | None | Global instant shutdown |
| Financial circuit breakers | None | Per-server limits + alerts |
| Audit trail | None | Ed25519 signed logs |
| SIEM log streaming | None | Splunk, Datadog, Webhook |
| Honeytokens | None | Canary alerts on leak |
| Custom domains | Not applicable | DNS challenge verified |
| GDPR compliance | Manual effort | Automated purge + export |
Why teams choose Vinkius for Polygon.io in LlamaIndex
The Polygon.io MCP Server runs on Vinkius-managed infrastructure inside AWS — a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts. All 6 tools execute in hardened sandboxes optimized for native MCP execution.
Your AI agents in LlamaIndex only access the data you authorize, with DLP that blocks sensitive information from ever reaching the model, kill switch for instant shutdown, and up to 60% token savings. Enterprise-grade infrastructure, zero maintenance.

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
How Vinkius secures
Polygon.io for LlamaIndex
Every tool call from LlamaIndex to the Polygon.io MCP Server is protected by DLP redaction, cryptographic audit chains, V8 sandbox isolation, kill switch, and financial circuit breakers.
Frequently asked questions
Can I get historical price data for a specific stock over a date range?
Yes. Use the get_aggregates tool by providing the ticker, multiplier, timespan (e.g., 'day'), and the 'from' and 'to' dates. The agent will return the OHLCV bars for that period.
How do I find the description and industry of a specific company?
Simply use the get_company tool with the stock ticker (e.g., 'AAPL'). It will retrieve the official company metadata, including its business description and industry classification.
Is it possible to see the most recent trades for a ticker?
Yes! The list_trades tool allows you to fetch tick-by-tick trade data for a specific ticker, showing execution prices and sizes as they happen in the market.
How does LlamaIndex connect to MCP servers?
Use the MCP client adapter to create a connection. LlamaIndex discovers all tools and wraps them as query engine tools compatible with any LlamaIndex agent.
Can I combine MCP tools with vector stores?
Yes. LlamaIndex agents can query Polygon.io tools and vector store indexes in the same turn, combining real-time and embedded data for grounded responses.
Does LlamaIndex support async MCP calls?
Yes. LlamaIndex's async agent framework supports concurrent MCP tool calls for high-throughput data processing pipelines.
BasicMCPClient not found
Install: pip install llama-index-tools-mcp
Explore More MCP Servers
View all →
Home River Group
10 toolsConnect and manage Home River Group properties, units, and residents via Entrata API.

Activepieces
32 toolsAutomate workflows with Activepieces — manage flows, monitor executions, and handle app connections directly from your AI agent.

ContextQA
10 toolsAutomate testing via ContextQA — manage test suites, track AI-healing executions, trigger automated runs, and audit API tests directly from any AI agent.

WordPress Media Uploader
1 toolsThis MCP does exactly one thing: it downloads images from a URL and uploads them directly to your WordPress Media Library. Incredible for giving Claude the ability to generate and deploy blog cover images instantly.
