thetadata-mcp
MCP server that wraps the Theta Data API to provide AI assistants with real-time and historic stock, options, and index data, including OHLC, trades, quotes, Greeks, and more.
README
Theta Data MCP Server
A local MCP (Model Context Protocol) wrapper for the Theta Data API, providing AI models with access to real-time and historic stock, options, and index data.
Overview
This MCP server is generated from the Theta Data OpenAPI specification using FastMCP. It exposes API endpoints as MCP tools, allowing AI assistants to query market data directly.
Supported Data Types
- Stocks: Symbols, EOD data, OHLC, trades, quotes, snapshots
- Options: Symbols, expirations, strikes, contracts, Greeks, implied volatility
- Indices: Symbols, prices, OHLC, market values
- Calendar: Market open dates
Prerequisites
- Python 3.10+
- uv for package management
- Theta Data terminal running locally (default:
http://127.0.0.1:25503) - A Theta Data subscription (subscribe here)
Installation
# Create virtual environment and install all dependencies (including dev)
uv sync
Usage
Running the Server
# Run with stdio transport (default)
uv run server.py
# Run with SSE transport
uv run server.py --transport sse
# Custom base URL
uv run server.py --base-url http://localhost:25503/v3
# Custom timeout
uv run server.py --timeout 60.0
Environment Variables
| Variable | Description | Default |
|---|---|---|
THETADATA_BASE_URL |
Theta Data API base URL | http://127.0.0.1:25503/v3 |
THETADATA_TIMEOUT |
Request timeout in seconds | 30.0 |
MCP Client Configuration
Add the following to your MCP client config, replacing /path/to/thetadata-mcp with the actual path to this repository:
{
"mcpServers": {
"thetadata": {
"command": "uv",
"args": [
"--directory",
"/path/to/thetadata-mcp",
"run",
"server.py"
],
"env": {
"THETADATA_BASE_URL": "http://127.0.0.1:25503/v3",
"THETADATA_TIMEOUT": "30.0"
}
}
}
}
Available Tools
The server exposes all Theta Data v3 API endpoints as MCP tools, including:
Stock Data
stock_list_symbols- List all stock symbolsstock_list_dates- List available dates for a request typestock_snapshot_ohlc- Real-time OHLC datastock_snapshot_trade- Real-time trade datastock_snapshot_quote- Real-time quote datastock_history_eod- Historic EOD datastock_history_ohlc- Historic OHLC barsstock_history_trade- Historic trade datastock_history_quote- Historic quote data
Options Data
option_list_symbols- List optionable symbolsoption_list_expirations- List expirations for a symboloption_list_strikes- List strikes for an expirationoption_list_contracts- List option contractsoption_snapshot_ohlc- Real-time option OHLCoption_snapshot_greeks_all- All Greeks (delta, gamma, theta, vega, rho)option_snapshot_greeks_implied_volatility- Implied volatilityoption_history_eod- Historic option EOD dataoption_history_greeks_all- Historic Greeks data
Index Data
index_list_symbols- List index symbolsindex_snapshot_price- Real-time index pricesindex_history_eod- Historic index EOD data
Calendar
calendar_open_today- Check if market is open todaycalendar_on_date- Check if market is open on a specific date
See the Theta Data API documentation for full details on parameters and responses.
Example Queries
Once connected to an MCP client, you can ask:
- "List all available stock symbols"
- "Get the current OHLC data for AAPL"
- "What are the available option expirations for SPY?"
- "Show me the Greeks for the SPY 500 call expiring next Friday"
- "Is the market open today?"
Development
Pre-commit Hooks
This project uses pre-commit to run ruff linting and formatting automatically on every commit.
Setup (one-time per clone):
uv run pre-commit install
The hook will now automatically check and fix code formatting when you commit changes.
Manual Development Commands
# Run linting with uv
uv run ruff check .
# Format code with uv
uv run ruff format .
# Regenerate endpoints_by_subscription documentation
uv run python generate_endpoint_docs.py
Regenerating Endpoint Documentation
The generate_endpoint_docs.py script reads the x-min-subscription field from openapiv3_updated.yaml and regenerates the markdown files in endpoints_by_subscription/. Each tier file shows all endpoints available at that subscription level and below (cumulative):
endpoints_free.md- Free tier endpointsendpoints_value.md- Free + Value tier endpointsendpoints_standard.md- Free + Value + Standard tier endpointsendpoints_professional.md- All endpoints
License
MIT License - See LICENSE file for details.
Resources
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.