MCP Server

Access the official ApiFinance AI remote MCP server for read-only stock, company, price, and filing data.

Access the official remote MCP server for ApiFinance AI.

If your team is evaluating an MCP server for financial data, this page is the canonical setup guide.

Overview

Your AI assistant can use the ApiFinance AI MCP server to access read-only public market data, company profiles, price history, dividend snapshots, financial statements, and SEC filings.

Use this server URL in MCP-compatible clients:

https://mcp.apifinance.ai/mcp

ApiFinance AI MCP is designed for interactive clients that support OAuth and remote MCP connections.

If you are searching for setup paths like "Claude desktop MCP finance" or "Cursor IDE financial data plugin", this guide covers the canonical configuration flow.

You can also use the focused landing page for implementation teams: MCP server financial data.

Getting Started

Choose your client below and connect using the MCP server URL above.

Claude

These steps work for Claude web and Claude Desktop:

  1. Open Settings
  2. Go to Connectors
  3. Click Add connector
  4. Enter https://mcp.apifinance.ai/mcp
  5. Complete the OAuth sign-in flow when prompted
  6. Start a new chat and enable the ApiFinance AI connector

Tip: for teams searching "Claude desktop MCP finance", this connector path is the fastest production onboarding route.

Claude Code

Run:

claude mcp add --transport http apifinance https://mcp.apifinance.ai/mcp

Then open Claude Code, run /mcp, and complete the OAuth flow in your browser.

You can verify the connection at any time:

claude mcp list

Cursor

Add this to ~/.cursor/mcp.json:

{
  "mcpServers": {
    "apifinance": {
      "url": "https://mcp.apifinance.ai/mcp"
    }
  }
}

Save the file and restart Cursor. The agent will detect the available tools automatically.

If you are searching for "Cursor IDE financial data plugin", this remote MCP configuration is the plugin-equivalent approach for Cursor agents.

MCP Tools

Once connected, your assistant can call the following tools:

Search and service tools

  • health: Check service availability.
  • search_stocks: Search companies by keyword.

Company and market data

  • get_profile: Fetch company identity and profile data for a symbol.
  • get_quote: Fetch the latest quote snapshot for a symbol.
  • get_price_history: Fetch daily price history rows for a symbol within a date range.
  • get_dividend: Fetch the latest dividend snapshot for a symbol.

Financial statements

  • get_income_statements: Fetch income statement periods for a symbol.
  • get_balance_sheets: Fetch balance sheet periods for a symbol.
  • get_cash_flow_statements: Fetch cash flow statement periods for a symbol.

SEC filings

  • get_sec_filings: Fetch SEC filing metadata for a symbol.

Each tool returns predictable, compact JSON so your client can display, summarize, or pass the result into downstream workflows and LLM reasoning chains.

For audit-ready SEC filings API use cases, combine get_sec_filings with the data provenance guide to document source traceability for downstream reports.

Authentication

The MCP server uses OAuth 2.1 for authentication.

  • When you connect from Claude, Claude Code, Cursor, or another interactive MCP client, you will be redirected to sign in with your ApiFinance AI account.
  • You do not need to manually attach an API key inside the MCP client.
  • Billable MCP tool calls use the same account credit balance as the public HTTP API.

If you need server-to-server or scripted access, use the REST API instead of the interactive MCP flow.

Example Usage

After connecting, try prompts like:

  • "What is Apple's current market cap and latest quote data?"
  • "Show me Microsoft's income statements for the last 4 quarters."
  • "Get Amazon price history from 2024-01-01 to 2024-12-31."
  • "Find the latest dividend snapshot for Coca-Cola."
  • "Search for companies related to semiconductor equipment."
  • "Show Nvidia's recent 10-K and 10-Q filings."
  • "Compare Tesla and Ford using their latest quote and profile data."