trading-signals
Model Context Protocol for technical analysis ability
claude mcp add --transport stdio tripolskypetr-trading-signals-mcp npx -y trading-signals-mcp
How to use
Trading Signals MCP Server provides real-time cryptocurrency trading signals and market insights via MCP. It analyzes multiple timeframes (from 1 minute to 1 hour) and exposes a suite of technical indicators, order book insights, and historical candle data to help you identify entry and exit points, validate strategies, and monitor liquidity. The server is designed to be integrated into Claude Desktop or other MCP hosts, delivering structured data through the MCP framework so you can compose alerts, dashboards, or automated trading signals around tools like Long-Term, Short-Term, Swing-Term, and Micro-Term analyses, as well as volume, slope, and order book analytics. Available methods include fetchLongTermSignals, fetchShortTermSignals, fetchSwingTermSignals, fetchMicroTermSignals, fetchVolumeData, fetchSlopeData, fetchBookData, and historical candle fetchers to support comprehensive backtesting and live decision making. You can request symbol-specific data (for example BTCUSDT) and rely on Binance data feeds for live market information.
To use it, configure the MCP host (e.g., Claude Desktop) to point to the trading-signals-mcp server entry, typically by adding:
{ "mcpServers": { "trading-signals-mcp": { "command": "npx", "args": ["-y", "trading-signals-mcp"] } } }
Once configured, start the MCP host and invoke the available tools via MCP calls. You can request multi-timeframe analyses, subscribe to live updates, and pull historical candle data to feed dashboards or automated strategies.
How to install
Prerequisites:\n- Node.js v18 or later (as required by the MCP server)\n- npm (comes with Node.js)\n\nInstallation steps (NPX usage, no local install required):\n1) Ensure Node.js is installed. Verify with:\n node -v && npm -v\n\n2) Add the MCP server to your Claude Desktop (or MCP host) configuration:\n - macOS: ~/Library/Application Support/Claude/claude_desktop_config.json\n - Windows: %APPDATA%\Claude\claude_desktop_config.json\n - Linux: ~/.config/Claude/claude_desktop_config.json\n\n Use the following configuration snippet:\n\njson\n{\n "mcpServers": {\n "trading-signals-mcp": {\n "command": "npx",\n "args": ["-y", "trading-signals-mcp"]\n }\n }\n}\n\n\n3) Alternatively, run locally with NPX (no install):\n\nbash\nnpx -y trading-signals-mcp\n\n\n4) If you prefer a local clone for customization, clone the repo, install dependencies, and build:\n\nbash\ngit clone https://github.com/tripolskypetr/trading-signals-mcp.git\ncd trading-signals-mcp\nnpm install\nnpm run build\n\n\n5) Configure Claude Desktop to point to the built index (example path):\njson\n{\n "mcpServers": {\n "trading-signals-mcp": {\n "command": "node",\n "args": ["/path/to/trading-signals-mcp/build/index.mjs"]\n }\n }\n}\n\n
Additional notes
Tips and notes:\n- This MCP server relies on Binance public APIs for market data; ensure network access to Binance endpoints.\n- The recommended and simplest usage is via NPX without installing dependencies locally.\n- If you customize locally, remember to build before pointing your MCP host to the built index.\n- The npm package name to reference in NPX is trading-signals-mcp.\n- Monitor for API rate limits or changes in Binance endpoints; implement error handling in your MCP host to gracefully handle data unavailability.\n- You can extend or modify available tools (e.g., fetchLongTermSignals, fetchShortTermSignals) to match your trading framework or risk controls.\n- When integrating with Claude Desktop or other MCP hosts, keep the configuration JSON synchronized with your environment to avoid mismatches in command/args.
Related MCP Servers
gemini-cli
An open-source AI agent that brings the power of Gemini directly into your terminal.
gaianet-node
Install, run and deploy your own decentralized AI agent service
aci
ACI.dev is the open source tool-calling platform that hooks up 600+ tools into any agentic IDE or custom AI agent through direct function calling or a unified MCP server. The birthplace of VibeOps.
sre
The SmythOS Runtime Environment (SRE) is an open-source, cloud-native runtime for agentic AI. Secure, modular, and production-ready, it lets developers build, run, and manage intelligent agents across local, cloud, and edge environments.
armor-crypto
The MCP server for interacting with Blockchain, Swaps, Strategic Planning and more.
sugar
🍰 Sugar - The autonomous layer for AI coding agents