mcp
Twelve Data MCP (Model Context Protocol) Server provides seamless, real-time access to financial market data via WebSocket, enabling reliable streaming of price quotes, market metrics, and events directly into your applications.
claude mcp add --transport stdio twelvedata-mcp uvx mcp-server-twelve-data -k YOUR_TWELVE_DATA_API_KEY -u YOUR_OPENAI_API_KEY
How to use
The Twelve Data MCP Server exposes Twelve Data data through the MCP (Model Context Protocol) interface, allowing Claude Desktop or other MCP clients to route natural language requests to Twelve Data endpoints via the u-tool. The server leverages u-tool to interpret English requests, select the appropriate Twelve Data API call, and return structured results such as historical time series, real-time quotes, and instrument metadata. To start using it, configure your MCP client to connect to the local uvx-based server (or the remote server) and supply your Twelve Data API key and an OpenAI API key for the routing and endpoint selection steps. Once running, you can query data like stock performance, RSI calculations, currency rates, and more through natural language commands that u-tool translates into specific Twelve Data API calls.
Key capabilities include natural language routing, endpoint selection across the Twelve Data catalog, and automatic execution of the chosen API call with properly formed parameters. The included installation options demonstrate how to run the server locally without a full codebase via uvx, or install via pip for a Python-based setup. You can also connect Claude Desktop (or other MCP clients) with preconfigured JSON snippets to point to the local server or to the Twelve Data remote endpoint. This setup aims to minimize the need to navigate Twelve Data’s 100+ endpoints by providing high-level natural language requests like “Show me Apple stock performance this week” or “Get Bitcoin RSI with a 14-day period.”
How to install
Prerequisites:
- A Twelve Data API key (required for data access).
- An OpenAI API key (required for the u-tool routing and GPT-4o orchestration).
- Optionally, Python 3.x and/or Node.js depending on the installation method you choose.
- Using UV (recommended)
- Ensure you have uvx installed. Follow the uvx installation guide at https://docs.astral.sh/uv/guides/tools/ and install uvx.
- Run the MCP server locally:
This will expose the Twelve Data MCP via the MCP server interface. You can customize credentials via the environment or via your MCP client configuration.uvx mcp-server-twelve-data --help
- Using pip (Python installation)
- Install the server package:
pip install mcp-server-twelve-data python -m mcp_server_twelve_data --help - Start the server with your keys configured in your MCP client or environment:
python -m mcp_server_twelve_data \ -k YOUR_TWELVE_DATA_API_KEY \ -u YOUR_OPENAI_API_KEY
- Docker usage
- Build the container:
docker build -t mcp-server-twelve-data . - Run the container with required keys:
docker run --rm mcp-server-twelve-data \ -k YOUR_TWELVE_DATA_API_KEY \ -u YOUR_OPENAI_API_KEY \ -t streamable-http
- Optional: Node.js/npm-based usage (via MCP tooling or remote access)
- If you prefer an npm-based workflow for inspection or MCP tooling, you can use npx to run the remote or inspector tooling as shown in the README, but the core server runs via uvx or pip.
Additional notes
Tips and common issues:
- Ensure your API keys are kept secure and not exposed in public configs. Use environment variables or secure secrets management where possible.
- When using the remote Twelve Data MCP (via npx), supply correct headers for Authorization and OpenAI API key as shown in the setup examples.
- If you encounter authentication or rate-limit errors, verify your Twelve Data subscription level and that the API key is active.
- The u-tool relies on OpenAI GPT-4o; ensure your OpenAI API key has access to GPT-4o capabilities and your usage complies with OpenAI's terms.
- For Claude Desktop integration, you can either run the local stdio server with a utool-based command or point Claude to a remote MCP endpoint by configuring the JSON in claude_desktop_config.json as shown in the README.
- If you need to switch between local uvx and remote mcp-server-twelve-data, adjust the mcpServers configuration in your MCP client accordingly.
- When debugging, you can use the MCP Inspector via npx @modelcontextprotocol/inspector uvx mcp-server-twelve-data@latest -k YOUR_TWELVE_DATA_API_KEY to verify routing and parameters.
Related MCP Servers
mcp -qdrant
An official Qdrant Model Context Protocol (MCP) server implementation
mcp-pinecone
Model Context Protocol server to allow for reading and writing from Pinecone. Rudimentary RAG
mcp-rquest
A MCP server providing realistic browser-like HTTP request capabilities with accurate TLS/JA3/JA4 fingerprints for bypassing anti-bot measures. It also supports converting PDF and HTML documents to Markdown for easier processing by LLMs.
pfsense
pfSense MCP Server enables security administrators to manage their pfSense firewalls using natural language through AI assistants like Claude Desktop. Simply ask "Show me blocked IPs" or "Run a PCI compliance check" instead of navigating complex interfaces. Supports REST/XML-RPC/SSH connections, and includes built-in complian
mcp-kubernetes
A Model Context Protocol (MCP) server that enables AI assistants to interact with Kubernetes clusters. It serves as a bridge between AI tools (like Claude, Cursor, and GitHub Copilot) and Kubernetes, translating natural language requests into Kubernetes operations and returning the results in a format the AI tools can understand.
davinci -professional
An enterprise-grade MCP server that exposes the full functionality of DaVinci Resolve and DaVinci Resolve Studio (through version 20) to either Claude Desktop or Cursor MCP clients. Fully configured and tested as a Claude Desktop Extension making installation as easy as clicking a button. Supports both Windows and Macintosh.