TensorFeed is a Model Context Protocol (MCP) server: AI news, model pricing, service status, and machine-payable premium tools. AFTA-certified. In practice that means any MCP-compatible AI assistant can call TensorFeed's tools directly — the model decides when to use them in a conversation or agent run.
You can run TensorFeed two ways: connect to the hosted endpoint at https://mcp.tensorfeed.ai/mcp with no local install, or run it on your own machine via the npm package @tensorfeed/mcp-server. The current release is v2.0.1, published under the MIT license, with source at RipperMercs/tensorfeed-mcp on GitHub.
TensorFeed 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 TensorFeed for tensorfeed.ai, claim this listing to verify ownership, earn the Verified badge, and keep the details current.
