Skip to content

Octagon MCP Server for Market Data

The Octagon MCP server provides specialized AI-powered financial research and analysis by integrating with the Octagon Market Intelligence API, enabling users to easily analyze and extract detailed insights from public filings, earnings call transcripts, financial metrics, stock market data, extensive private market transactions, and prediction market research within Claude Desktop and other popular MCP clients.

Demo

Connecting to the Octagon Remote MCP Server

The Octagon Remote MCP server is available at:

  • https://mcp.octagonagents.com/mcp for Remote MCP clients that support OAuth (recommended)
  • https://mcp.octagonagents.com/{OCTAGON_API_KEY}/mcp for Remote MCP clients that don't support OAuth yet

Authentication

Octagon MCP supports both API keys and Public Keys:

  • API keys provide full access to Octagon capabilities.
  • Public Keys work with limited model/endpoint access.

For instructions on creating either credential type, see Authentication for Octagon Agents API.

When using the MCP server with non-OAuth clients, set {OCTAGON_API_KEY} to either your API key or Public Key.

Using with Claude.ai

Note: Requires Claude Pro, Team, or Enterprise

For Claude.ai Admins

Only Workspace Owners and Primary Owners can set up MCP server connections in Claude.ai:

  1. Go to Settings in Claude.ai
  2. Navigate to the "Integrations" section
  3. Click "Add integration"
  4. For Integration name, enter "Octagon"
  5. For Integration URL, enter https://mcp.octagonagents.com/mcp
  6. Click "Add"
  7. Select which Octagon tools to enable for your workspace
  8. Click "Save"

For Claude.ai Users

After your admin has set up the integration:

Navigate to claude.ai Click on the tools menu (next to the search icon) Select "Octagon" from the list of available integrations If this is your first time using the integration, you'll be prompted to authenticate Once authenticated, you can start using Claude with Octagon

Running on Claude Desktop

To configure Octagon MCP for Claude Desktop:

  1. Open Claude Desktop
  2. Go to Settings > Developer > Edit Config
  3. Add the following to your claude_desktop_config.json:
json
{
  "mcpServers": {
    "octagon-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote@latest",
        "https://mcp.octagonagents.com/mcp"
      ]
    }
  }
}
  1. Restart Claude for the changes to take effect

Using with Cursor

Install MCP Server

Option 2: Manual Configuration

  1. Go to your Cursor editor's settings
  2. Navigate to "Tools & Integrations" > "New MCP Server"
  3. Add the following to your mcp.json
json
{
  "mcpServers": {
    "octagon": {
      "url": "https://mcp.octagonagents.com/mcp"
    }
  }
}
  1. Save your mcp.json file and authenticate with OAuth when prompted

Features

Octagon MCP gives your AI assistant a set of finance-focused research capabilities, so you can ask natural-language questions and get structured, source-backed answers without stitching data together manually.

Market intelligence

Analyze public and private markets in one workflow:

  • SEC filings analysis and data extraction (8,000+ public companies — 10-K, 10-Q, 8-K, 20-F, S-1)
  • Earnings call transcript analysis (10 years of historical and current)
  • Financial metrics and ratios analysis (10 years of historical and current data)
  • Stock market data access (10,000+ active tickers, daily historical and current data)

Learn more: Octagon Agent

Deep research for complex questions

Run broader investigations that combine multiple sources and up-to-date web context for thematic analysis, competitive research, and event-driven workflows.

Learn more: Deep Research Agent

Prediction markets

Generate structured reports for prediction market events, compare implied probabilities, surface potential mispricings across active markets, and review historical snapshots to understand how expectations changed over time.

Learn more: Prediction Markets Agent and Prediction Markets Events History

What is the Model Context Protocol (MCP)?

The Model Context Protocol (MCP) is an open standard that allows AI applications to extend models with additional capabilities and context. Think of MCP as a "USB-C port for AI applications" - it provides a standardized way for AI models to connect with external tools, data sources, and specialized capabilities.

MCP enables AI models to:

  • Access external knowledge and data sources
  • Use specialized tools for specific domains
  • Leverage capabilities beyond what's built into the base model

The Octagon MCP server implements this protocol to provide specialized investment research capabilities directly to your preferred AI tools and interfaces like Cursor, Claude Desktop, and Windsurf.

For a deeper understanding of the MCP protocol, see Anthropic's MCP documentation.

Alternative usage with local MCP server

To run against a local Octagon MCP server, see: Octagon MCP Server GitHub Repository.

Resources