Model Context Protocol (MCP) Server Directory

Build a Weaviate Vector Database MCP server for Claude Desktop and Cursor: BM25+dense hybrid search, vectorization, typed cross-references for graph RAG, and an OAuth 2.0 secured streamable-HTTP transport.

Bridge Anthropic's MCP tool surface to Google/A2A's agent-to-agent task lifecycle: discovery via Agent Cards, task-state negotiation, and a single gateway that turns any MCP tool into a delegable A2A task for the enterprise.

Run Langfuse as an AgentOps observability plane reachable from Claude Desktop: OpenTelemetry GenAI semantic conventions, gen_ai.* trace ingestion, dual-device session replay, and per-trace cost tracking over a native MCP server at /api/public/mcp.

Architect a high-performance, stateless FastMCP server using Cloudflare Workers, fortified with OAuth 2.0 to securely extend Cursor's AI capabilities at the edge.

Build a robust hybrid FastMCP server combining Supabase Vector search and PostgreSQL relational queries to supercharge Claude Desktop's intelligence.

Discover how to build an Enterprise Hybrid MCP Server connecting GitHub and Jira for autonomous CI/CD triage. This guide includes complete Python SDK code, OAuth 2.0 token security, and configuration for Claude Desktop.

Learn how to build a highly scalable, stateless FastMCP TypeScript Server integrated with Supabase Vector and secured by OAuth 2.0. This deep dive covers schema definitions, Claude Desktop configuration, and advanced token security.

Enterprise Supabase Vector MCP Tool: Real-Time Vector Search & Schema Inspection for Cursor By Deepak Bagada, CEO at SaaSNext & Principal AI Architect....

FastMCP 2026 Stateless Architecture Guide: Building Scalable Cloudflare Worker MCP Servers By Deepak Bagada, CEO at SaaSNext & Principal AI Architect. W...

Connect Claude Desktop directly to your Supabase PostgreSQL database using the official Supabase Vector Model Context Protocol server.

Comprehensive guide to building high-performance MCP servers for Cursor IDE using FastMCP 3.0 TypeScript SDK with OAuth 2.0.

BaseRT delivers 1.56x faster decode than llama.cpp and 1.35x faster than MLX on Apple Silicon. Complete benchmark comparison and setup guide.