Onchain Safety Mcp

Overview

Onchain Safety Mcp is a Model Context Protocol server that provides token safety analysis for AI agents, delivering rug pull and honeypot verdicts with safety scores across PulseChain, Monad, Base, and BSC. By implementing MCP, it lets AI assistants call token safety checks as native tools rather than requiring manual data transfer between applications.

The server runs locally via the npm package @wickpics/onchain-safety-mcp, communicating over stdio. It requires an API Key for authentication. Version v0.2.0 is available under the MIT license, with full source code hosted at aitools420/onchain-safety-mcp on GitHub.

Onchain Safety Mcp is listed in the AI & Agents category and works with all MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and Zed. If you maintain this server, claim your listing to verify ownership and keep information current.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "onchain_safety_mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@wickpics/onchain-safety-mcp"
      ]
    }
  }
}