FastMCP

GolfMCP is an open source framework designed to streamline the creation and deployment of production-ready Model Context Protocol (MCP) servers, enabling organizations to build secure, scalable AI-agent infrastructure without worrying about boilerplate. It allows developers to define tools, prompts, and resources as simple Python files, after which Golf handles routing, authentication, telemetry, and observability, so you focus on logic, not plumbing. The platform supports enterprise authentication (JWT, OAuth Server, API key), automatic telemetry, and a file-based structure that eliminates decorators or manual schema wiring. With built-in utilities for LLM interactions, error logging, OpenTelemetry integration, and deployment tools (such as a CLI with golf init, golf build dev, golf run), Golf provides a full stack for agent-native services. Included also is the Golf Firewall, an enterprise-grade security layer for MCP servers that enforces token validation.

Cloudflare MCP Server Portals is a cloud-hosted access layer for organizations using Model Context Protocol (MCP) servers with AI clients. It brings approved remote MCP servers behind a single HTTP endpoint protected by Cloudflare Access, allowing administrators to apply identity-based policies and manage server availability. Administrators can choose which tools and prompts each portal exposes and route requests through Cloudflare Gateway for HTTP logging and data loss prevention inspection. The portal supports OAuth and service-token authentication; Access records tool, prompt, and resource activity. Users connect through MCP clients such as Claude Desktop, Workers AI Playground, OpenCode, or Windsurf. It serves IT and security teams managing internal or SaaS MCP services and authorized employees or agents. Only remote HTTP servers are supported; local stdio-only servers require a separate HTTP endpoint.