DealForge autonomously sources, scores, and writes investment memos on venture deals. Stop manually hunting.
1,180+ deals tracked · 22 AI investment memos · Updated daily
Show HN: MCPfinder – An MCP server that finds and installs other MCP servers
I’ve been building and using agents heavily lately. The Model Context Protocol ecosystem is growing insanely fast, but discovering and configuring new tools is still highly manual. Every time I needed to connect an agent to a new service, I had to browse registries, figure out the transport type, identify required env vars, and manually update "mcp.json" files.<p>So I built MCPfinder. It aggregates servers from the official MCP registry, Glama, and Smithery (around 25,000 combined entries) into a deduplicated, ranked catalog.<p>But the real twist is the DX: MCPfinder is itself an MCP server :D<p>You only install it once as your "base capability" via standard stdio: npx -y @mcpfinder/server<p>From then on, when you tell your AI, "I need to query my PostgreSQL database," the magic happens autonomously.<p>It's completely free, AGPL-3.0 licensed, and built purely to optimize AI-tool surface discovery.<p>I'd love to hear your thoughts, feedback, or edge cases where JSON generation for specific platforms is acting up.
MCPfinder addresses a timely friction point in the rapidly expanding Model Context Protocol ecosystem by enabling autonomous tool discovery for AI agents. While the recursive 'MCP server for MCP servers' approach is clever, the project currently lacks significant traction and faces high platform risk from established registries or protocol owners.