Agentradar is a Model Context Protocol (MCP) server: Trust scoring, scam detection, and EAS attestations for ERC-8004 + x402 agents on Base. In practice that means any MCP-compatible AI assistant can call Agentradar's tools directly — the model decides when to use them in a conversation or agent run.
It runs locally: the npm package @agentradar/mcp speaks MCP over stdio on your machine. The current release is v0.1.3, published under the MIT license, with source at Bichev/agentradar-mcp on GitHub.
Agentradar is listed under AI & Agents on mcp.site and works with any MCP client — Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, Zed and the rest of the ecosystem — using the install snippets below. If you maintain Agentradar for Bichev, claim this listing to verify ownership, earn the Verified badge, and keep the details current.
▸npm package — @agentradar/mcp · MCP over stdio
▸Open source — MIT license · Bichev/agentradar-mcp