Octagon

Appearance

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

Tools ​

octagon-agent ​

Orchestrates Public and Private Market agents for comprehensive market intelligence analysis. Combines insights from SEC filings, earnings calls, financial metrics, stock data, institutional holdings, private company research, funding analysis, M&A transactions, investor intelligence, and debt analysis to provide holistic market intelligence. Best for complex research requiring multiple data sources and comprehensive analysis across public and private markets.

Public market data

  • 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)
  • Stock market data access (10,000+ active tickers, daily historical and current)

Private market data

  • Private company research (3M+ companies)
  • Funding rounds and venture capital research (500K+ deals)
  • M&A and IPO transaction research (2M+ deals)
  • Debt transactions research (1M+ deals)

octagon-deep-research-agent ​

A comprehensive agent for deep investment research that synthesizes up-to-date insights from multiple web and data sources. Best for investment research questions requiring up-to-date aggregated information from the web — competitive landscapes, thematic deep dives, event studies, and cross-market impact analysis.

octagon-prediction-markets-agent ​

A specialized agent for generating research reports on Kalshi prediction market events (Polymarket coming soon). Surfaces price drivers, compares market vs. model probabilities, and identifies potential mispricings across 120+ active markets in categories including Politics, Economics, Crypto, Sports, Entertainment, Science & Technology, and Climate.

Optionally specify caching behavior to control report generation that mirrors the model variants. See Prediction Markets Agent for more details.

prediction_markets_history ​

Fetches historical data for a prediction market event by ticker symbol. Supports time-window filtering via captured_from and captured_to, pagination via limit and cursor.

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

Get Your Octagon API Key ​

To use Octagon MCP, you need to:

  1. Sign up for a free account at Octagon
  2. After logging in, from left menu, navigate to API Keys
  3. Generate a new API key
  4. Use this API key in your configuration as the OCTAGON_API_KEY value

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

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 such as Claude Desktop, go to: Octagon MCP Server GitHub Repository.

Resources ​