Polygon.io MCP Server

Polygon.io · Market & Financial Data

Official

Tick-level US equities data, WebSocket streaming and low-latency quotes.

tick datastreamingUS equities

Status

Official

Auth

API key

Hosting

Both

Community rating

Not rated yet

Open documentation →

Rate this server

How to connect Polygon.io MCP Server

Step 1

Local server — run it on your machine

Polygon.io MCP Server runs locally over stdio. You need Node.js (for npx) or Python (for uvx) installed, then add the command below to your client's MCP config file.

Command

uvx --from git+https://github.com/polygon-io/mcp_polygon@v0.4.0 mcp_polygon

Client config snippet

{
  "mcpServers": {
    "polygon-io": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/polygon-io/mcp_polygon@v0.4.0",
        "mcp_polygon"
      ]
    }
  }
}

Step 2

Authenticate with API key

Create a key in the vendor's dashboard and store it as an environment variable in your client config — never paste it into a chat window.

Step 3

Verify, then widen access

Restart your client, confirm the server's tools appear, and run one read-only question first. Keep client-side approval prompts on for any tool that can write, trade or send. Confirm with your firm's compliance policy before connecting systems holding client data.

Prompts that use this server

Starter prompts from the Practice Stacks that rely on Market & Financial Data.

Market context talking points

Three to five neutral talking points on recent market moves.

Client Review Meeting PrepWealth PlatformsMarket & Financial Data

Read-only: pull <client name>'s current holdings and sector or asset-class weights from the wealth platform, then use market-data tools to explain what moved those specific exposures over the last quarter. Return three to five neutral talking points, each tied to a holding or weight and to the market data behind it. No forecasts, no recommendations to buy or sell, no performance promises. Cite the source and date for both the holdings figure and the market figure so I can verify before I use it with a client.

Guardrail · Educational framing only. Avoid forward-looking or promissory language.

Tax-lot and wash-sale check

A flag list before trades are placed.

Trade & RebalanceCustody & ClearingMarket & Financial Data

Read-only: for the proposed sells in <account>, review tax lots at the custodian and flag short-term gains, large realised gains, and any purchase in the last 30 days that could create a wash sale. Then use market-data tools to value each lot at the latest available price and to check for splits, mergers or other corporate actions that would change basis or share count. Output Symbol / Lot / Acquired / Basis / Market value / Gain-loss / Flag / Source. Do not place or modify trades. Tell me where the data may be delayed or incomplete.

Guardrail · Read-only. Confirm lot data with the custodian before acting on it.

Draft quarterly performance commentary

Commentary you edit, grounded in your own reporting data.

Portfolio Reporting & PerformanceWealth PlatformsMarket & Financial Data

Read-only: using my portfolio reporting data for <client or composite>, draft quarterly commentary covering returns vs. benchmark, main contributors and detractors, and allocation changes — then pull the benchmark and index returns for the same period from market-data tools rather than relying on the reporting system's stored figures. Show a small reconciliation of reported benchmark return vs. market-data benchmark return and flag any variance. Neutral tone, no forecasts, no performance promises. Cite the figure source for every number. Do not send or publish anything — output the draft for review.

Guardrail · Draft only. Performance commentary usually needs compliance review before delivery.

Read the full connection guide →