Options

You deploy the MCP Options Order Flow Server to get real-time options flow analysis, pattern detection, and institutional bias insights through a high-performance, extensible MCP interface. This server connects to a data broker to deliver fast, actionable options data that you can query and monitor via MCP clients.

How to use

You use an MCP client to connect to the Options Order Flow Server and request analyses for specific tickers. Start by configuring your client to point at the local MCP runtime or remote endpoint, then invoke tools to analyze current flow, configure monitoring for chosen contracts, and check monitoring status. You will receive XML-formatted results that include activity levels, direction bias, detected patterns with confidence scores, and historical trends.

How to install

Prerequisites you need to fulfill before starting depend on the server’s runtime. You must have Python 3.8 or newer and a running mcp-trading-data-broker service that exposes a gRPC server on port 9090.

# 1) Install Python 3.8+ if needed
# 2) Ensure the data broker is running and accessible at port 9090
# 3) Prepare a virtual environment for the MCP server
python -m venv venv
source venv/bin/activate  # macOS/Linux
venv\Scripts\activate     # Windows

# 4) Install Python dependencies
pip install -r requirements.txt

Additional sections

Connection details and runtime options are defined below so you can start the server reliably and maintain a stable MCP integration.

Environment variables used by the MCP server to connect to the data broker and control logging are listed here for your reference.

Environment and startup details

The server communicates with the data broker over gRPC. Set the following environment variables to establish the connection and configure logging according to your needs.

export GRPC_HOST=localhost
export GRPC_PORT=9090
export GRPC_TIMEOUT=30
export LOG_LEVEL=INFO

Claude Desktop integration

If you use Claude Desktop MCP integration, add a server configuration that points to your local runtime and the gRPC endpoint.

{
  "mcpServers": {
    "options-flow": {
      "command": "python",
      "args": ["run_server.py"],
      "cwd": "/path/to/mcp-options-order-flow-server",
      "env": {
        "GRPC_HOST": "localhost",
        "GRPC_PORT": "9090"
      }
    }
  }
}

Available tools

analyze_options_flow

Get comprehensive options order flow analysis for a ticker. Returns XML containing monitored contracts, activity levels, directional bias, detected patterns, historical trends, and institutional bias.

configure_options_monitoring_tool

Configure monitoring for specific contracts by ticker, expiration, strike range, and whether to include calls and puts.

get_monitoring_status_tool

Retrieve the current monitoring configuration for a ticker in XML form.

data_broker_health_check

Check connectivity and health status of the data broker, including connection details and response time.