Real-time global intelligence dashboard. AI-powered news aggregation, geopolitical monitoring, and infrastructure tracking in a unified situational awareness interface
MCP server for Twelve Data market data
This server connects an agent to Twelve Data through MCP so it can read prices, indicators, fundamentals, news, and market events. You can use the hosted endpoint at `https://mcp.twelvedata.com/mcp`, or run it locally with your own API key for a desktop MCP setup.
People who want their agent to pull live and historical financial data into a conversation.
You can ask an agent for market data, indicators, and company facts without copying them from another site.
What it does
Cloud MCP endpoint
Use the hosted server at `https://mcp.twelvedata.com/mcp` with a browser login flow.
Local API key mode
Run the server on your own machine with `TWELVE_DATA_API_KEY` in `.env`.
Market data access
Fetch real-time and historical prices for stocks, ETFs, forex, crypto, and commodities.
Technical indicators
Query indicators such as RSI, MACD, SMA, BBANDS, ATR, and more than 60 others.
Company and fund data
Access fundamentals, earnings, dividends, splits, profiles, ETF and mutual fund details, and key stats.
Regulatory and news data
Pull company news, SEC/EDGAR filings, insider transactions, institutional holdings, and market movers.
How to get it
- 1Requires Python 3.10+ (3.12 recommended; on macOS brew install python@3.12 or make…
make install
- 2Create a .env file in the project root with your key
TWELVE_DATA_API_KEY=your_api_key_here
README
Twelve Data MCP Server
Connect Claude, ChatGPT, and other AI assistants to the Twelve Data financial API — real-time and historical prices, 60+ technical indicators, fundamentals, earnings, dividends, ETFs, company news, market movers, and more.
You need a Twelve Data account. Sign up at twelvedata.com.
There are two ways to use it. Most people should use the cloud server (Option 1) — there is nothing to install.
Option 1 — Use our cloud server (recommended)
Connect your AI assistant to our hosted server:
https://mcp.twelvedata.com/mcp
That's it. No installation, no API key to copy and paste. When you connect, a browser window opens and you log in with your Twelve Data account — your personal API key is linked automatically and stays tied to your account.
How to add it
Claude (Desktop / Web) and ChatGPT support custom connectors / MCP servers:
- Open your assistant's Connectors (or Integrations / MCP servers) settings.
- Add a new connector with the URL
https://mcp.twelvedata.com/mcp. - When prompted, click Connect / Log in — a Twelve Data login page opens in your browser.
- Authorize, and you're done. Ask things like "What's the RSI for AAPL?" or "Show me TSLA's latest earnings."
The exact menu names differ between apps and versions, but the flow is always the same: add the URL, then log in via the browser popup.
Option 2 — Run it locally with your API key
Prefer to run the server on your own machine (e.g. for Claude Desktop over stdio)? You only need your Twelve Data API key — no OAuth setup.
1. Get your API key
Log in at twelvedata.com → your dashboard → API Keys. Copy your key.
2. Install
Requires Python 3.10+ (3.12 recommended; on macOS brew install python@3.12 or make python-install).
make install
3. Add your API key
Create a .env file in the project root with your key:
TWELVE_DATA_API_KEY=your_api_key_here
4. Connect to Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json:
{
"mcpServers": {
"twelvedata": {
"command": "/path/to/twelve-data-mcp/.venv/bin/python",
"args": ["/path/to/twelve-data-mcp/src/server.py"]
}
}
}
Use the .venv/bin/python path (not the system Python — macOS ships 3.9, and this server needs 3.10+). Restart Claude Desktop after editing the config.
That's all — the server reads your API key from .env and every request uses it. No login step needed.
What you can ask
- Prices — stocks, ETFs, forex, crypto, commodities (real-time & historical)
- Technical indicators — RSI, MACD, SMA, BBANDS, ATR, and 60+ more
- Fundamentals — financial statements, earnings, dividends, splits, company profiles, market cap, key stats, IPO calendar
- Funds — ETF & mutual fund profiles, performance, holdings, risk
- News — company news & press releases
- Market intelligence — movers, exchange rates, analyst ratings, price targets
- Regulatory — SEC/EDGAR filings, insider transactions, institutional holdings
Symbol formats: stocks AAPL, crypto BTC/USD, forex EUR/USD.
Partners
Running your own public instance or setting up a dedicated OAuth login? That's a partner arrangement — reach out to us at twelvedata.com and we'll provide the setup guide and OAuth credentials.
Files in the repo
- src
- .env.example
- .gitignore
- CLAUDE.md
- Dockerfile
- Makefile
- PARTNERS.md
- pyproject.toml
- README.md
Discussion (0)
Ask about usage, or say what you built with itSign in to join the discussion.
No comments yet. Be the first to say what this is good for.
More connectors
High-performance code intelligence MCP server. Indexes codebases into a persistent knowledge graph — average repo in milliseconds. 158 languages, sub-ms queries, 99% fewer tokens. Single static binary, zero dependencies.

Universal provider proxy for OpenAI Codex & Claude Code — use any LLM (Claude, Gemini, Grok, DeepSeek, Ollama…) with Codex CLI, App, SDK, and Claude Code
Git-native persistent memory for AI coding agents. Implements Google OKF v0.2 with sub-300µs in-memory BM25 search, embedded MCP server, and progressive disclosure. Slashes token bloat by 80% with zero external databases or dependencies. Built in pure Go.
Stop your AI from making things up — it proposes, deterministic tools decide, every claim checked against ground truth with evidence. Grounded facts and context survive resets. Reverse engineering is the proving ground. MCP server + CLI.
20 MB lightweight cross-platform database client for 90+ databases, including MySQL, PostgreSQL, SQLite, Redis, MongoDB, DuckDB, SQL Server, and Dameng. Built-in AI, MCP Server, CLI, desktop and Docker. | 轻量级跨平台数据库管理工具,支持 MySQL、PostgreSQL、SQLite、Redis、MongoDB、达梦等 90+ 数据库,提供桌面端、Docker、CLI、内置 AI 助手和 MCP Server。