Skip to main content

A Model Context Protocol server providing tools access Twelve Data.

Project description

Twelve Data MCP Server

Overview

The Twelve Data MCP Server provides a seamless integration with the Twelve Data API to access financial market data. It enables retrieval of historical time series, real-time quotes, and instrument metadata for stocks, forex pairs, and cryptocurrencies.

Note: This server is currently in early-stage development; features and tools may evolve alongside updates to the Twelve Data API.

Obtaining Your API Key

To use Twelve Data MCP Server, you must first obtain an API key from Twelve Data:

  1. Visit Twelve Data Sign Up.
  2. Create an account or log in if you already have one.
  3. Navigate to your Dashboard and copy your API key.

Important: Access to specific endpoints or markets may vary depending on your Twelve Data subscription plan.

Tools

  1. time_series Fetch historical price data for a symbol.

    • Inputs:

      • symbol (string): Ticker, e.g. AAPL
      • interval (string): Data interval, e.g. 1min, 1day
      • start_date (string, optional): ISO-8601 start timestamp
      • end_date (string, optional): ISO-8601 end timestamp
    • Returns: Array of OHLCV bars.

  2. price Get the latest price for a symbol.

    • Inputs:

      • symbol (string)
    • Returns: Latest price quote.

  3. stocks List available stock instruments.

    • Inputs:

      • exchange (string, optional): Exchange code to filter by
    • Returns: Array of stock metadata.

  4. forex_pairs List available forex pairs.

    • Inputs: none
    • Returns: Array of forex pair metadata.
  5. cryptocurrencies List available cryptocurrencies.

    • Inputs: none
    • Returns: Array of cryptocurrency metadata.

Installation

Using UV (recommended)

Directly run without local installation using uvx:

uvx mcp-server-twelve-data --help

Using pip

Install the server via pip:

pip install mcp-server-twelve-data
python -m mcp_server_twelve_data --help

Configuration

Claude Desktop integration

Add the following snippet to your claude_desktop_config.json:

{
  "mcpServers": {
    "twelvedata": {
      "command": "uvx",
      "args": ["mcp-server-twelve-data", "--apikey", "YOUR_API_KEY"]
    }
  }
}

VS Code integration

Automatic setup (with UV)

Install with UV in VS Code

Manual setup

For manual configuration, add to your User Settings (JSON):

{
  "mcp": {
    "servers": {
      "twelvedata": {
        "command": "uvx",
        "args": ["mcp-server-twelve-data", "-t", "streamable-http"]
      }
    }
  }
}

Debugging

Use the MCP Inspector for troubleshooting:

npx @modelcontextprotocol/inspector uvx mcp-server-twelve-data

Development guide

  1. Local testing: Utilize the MCP Inspector as described in Debugging.
  2. Claude Desktop:: Update claude_desktop_config.json to reference local source paths.

Docker usage

Build and run the server using Docker:

docker build -t mcp-server-twelve-data .
docker run --rm mcp-server-twelve-data --apikey YOUR_API_KEY

License

This MCP server is licensed under the MIT License. See the LICENSE file for details.

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mcp_server_twelve_data-0.1.5.tar.gz (522.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mcp_server_twelve_data-0.1.5-py3-none-any.whl (96.6 kB view details)

Uploaded Python 3

File details

Details for the file mcp_server_twelve_data-0.1.5.tar.gz.

File metadata

File hashes

Hashes for mcp_server_twelve_data-0.1.5.tar.gz
Algorithm Hash digest
SHA256 e9e70fdfd2487f282b3a1c3617ba6c47aa9c4259252eb7fb0b1f633afa432c93
MD5 192336b519edcd616a9283de4ccd32fb
BLAKE2b-256 86e6ad891876e93d3dd31960d118d9f44184d8fb0559a68254e895c92d177c00

See more details on using hashes here.

File details

Details for the file mcp_server_twelve_data-0.1.5-py3-none-any.whl.

File metadata

File hashes

Hashes for mcp_server_twelve_data-0.1.5-py3-none-any.whl
Algorithm Hash digest
SHA256 6d626bdcb67d9d931bbe670c4d0e2acf5af47e0bcd35b84970e3ea51518287be
MD5 244ea0f3697b2f2f533ced05113f0b4c
BLAKE2b-256 c12c0de7fa2e8096056315088f661843a191c1efe03d115dab3e87c4b97a3866

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page