Crypto MCP server — 21 tools for Claude, Cursor & any MCP client.

MCP (Model Context Protocol) is an open standard that allows AI assistants to connect to external data sources and tools. The Sharpe MCP server exposes 21 tools that give AI agents like Claude and Cursor direct access to real-time crypto market data. When you ask Claude a question like 'What are the highest funding rates right now?', the AI can call the Sharpe MCP server's get_funding_rates tool to fetch live data and answer with current information rather than relying on training data.

No. The MCP server works without an API key by falling back to free public endpoints. This means you can pip install sharpe-mcp, add it to your AI tool's configuration, and start querying immediately with no signup or authentication. For higher rate limits and access to authenticated endpoints with more detailed data, you can optionally set a SHARPE_API_KEY environment variable.

The Sharpe MCP server is compatible with Claude Desktop, Claude Code, Cursor, and any MCP-compatible client. Configuration requires a single line in the tool's MCP settings file pointing to the sharpe-mcp command. The server uses stdio transport, which is the standard MCP communication protocol. As the MCP ecosystem grows, any new MCP-compatible AI tool will work with the Sharpe server without modification.

The three composite tools are analyze_coin (deep dive on a single coin combining funding, futures, options, and market data), market_briefing (comprehensive market overview with top narratives, funding highlights, and arbitrage opportunities), and find_opportunities (scans all data products for high-conviction setups). Use composite tools when you want a comprehensive answer to a broad question. Use individual tools like get_funding_rates or get_futures_data when you need specific data points.

Run pip install sharpe-mcp to install the package. For Claude Desktop, add the server to your claude_desktop_config.json with the command 'sharpe-mcp'. For Claude Code, add it to your MCP settings. For Cursor, add it to the Cursor MCP configuration. The server starts automatically when the AI tool launches and communicates via stdio transport. No separate server process or port configuration is needed.

The MCP server wraps the same REST API but is optimized for AI consumption. Differences include: smart defaults so AI agents get useful results without specifying every parameter, composite tools that synthesize multiple API endpoints into single responses, response formatting optimized for LLM context windows, and automatic truncation of large datasets. The REST API is better for programmatic integration into trading systems, while the MCP server is designed for conversational AI workflows.

Data freshness through the MCP server matches the underlying Sharpe data products: funding rates update every 1-8 hours per exchange, futures and options snapshots every 5-10 minutes, narratives and ecosystems every 30 minutes, and news within 1-5 minutes of publication. The MCP server fetches live data on each tool call — there is no additional caching layer between the MCP server and the underlying data.

Yes. The MCP server is free to install and use with no API key required. All 21 tools including the 3 composite intelligence tools are available on free public endpoints. Rate limits on free endpoints are sufficient for interactive AI conversations. For automated workflows or high-frequency queries, add a SHARPE_API_KEY for higher rate limits.

MCP is an open protocol specification introduced by Anthropic in late 2024 that standardizes how AI assistants connect to external data sources, tools, and services. An MCP server exposes tools (functions the AI can call), resources (data the AI can read), and prompts (templates the AI can use). MCP uses JSON-RPC over stdio or HTTP transport. The protocol is tool-agnostic — any MCP-compatible client (Claude Desktop, Claude Code, Cursor, Zed) can connect to any MCP server. This decouples AI assistants from specific integrations, analogous to how USB decoupled peripherals from operating systems.

The MCP server is optimized for conversational AI workflows — interactive research, market briefings, and agent-driven analysis — rather than high-frequency automated trading. For programmatic trading systems, Sharpe's REST API is the better choice because it offers lower latency, deterministic schemas, and direct HTTP access without the MCP transport overhead. MCP is well-suited for semi-automated workflows where an AI agent periodically checks market conditions and surfaces insights, or for Claude Code users who want to query live market data during development.