Token Metrics is a Blockchain MCP server that lets Claude Code, Cursor, Windsurf and any MCP-compatible AI agent real-time crypto market data, AI-driven ratings, and trading signals. Install in 1 minute with mcpizy install token-metrics.
Blockchain
Real-time crypto market data, AI-driven ratings, and trading signals.
mcpizy install token-metricsnpx -y @tokenmetrics/mcpQuery onchain data — ERC20 tokens, transaction history, wallet balances across chains.
Interface with blockchains — staking, DeFi, swap, bridging across multiple networks.
Real-time DEX analytics across 20+ blockchains. Trading pairs, volumes, liquidity.
Enable AI agents to purchase anything securely. Micropayments for AI workflows.
If Token Metrics doesn't fit your stack, these Blockchain MCP servers solve similar problems.
Read and write to 2,000+ blockchains. Smart contracts, NFTs, tokens, and dApp development.
Authentication and smart wallet infrastructure for Web3. Embedded wallets and account abstraction.
Connect Bitcoin Lightning wallet to AI agents. Instant micropayments and wallet management.
The Token Metrics MCP server is an Blockchain Model Context Protocol server that lets Claude Code, Cursor, Windsurf, VS Code with Copilot, and other MCP-compatible AI agents real-time crypto market data, AI-driven ratings, and trading signals. It exposes Token Metrics's capabilities as tools the AI can call directly from your editor or CLI.
The fastest way is the MCPizy CLI: run `mcpizy install token-metrics` and MCPizy will add the server to your `.claude.json` automatically. You can also install it manually by adding an entry under `mcpServers` in `.claude.json` with the command `npx -y @tokenmetrics/mcp` and restarting Claude Code.
Yes. The Token Metrics MCP server is free and open source (see the GitHub repository linked on this page). You may still need a Token Metrics account or API key to connect the server to the underlying service, but the MCP layer itself has no MCPizy subscription cost.
Yes. Any MCP-compatible client works — including Claude Code, Claude Desktop, Cursor (via `.cursor/mcp.json`), Windsurf, VS Code with Copilot Chat, and custom agents built on the MCP SDK. The same install command targets all of them; only the config file path differs.
Once installed, your AI agent can real-time crypto market data, AI-driven ratings, and trading signals directly inside your conversation. Typical use cases include asking Claude Code or Cursor to run Token Metrics operations, inspect results, chain Token Metrics with other MCP servers (see our Workflow Recipes), and automate repetitive blockchain tasks without leaving your editor.