A Python MCP application framework for building servers, clients, and interactive apps through one API, with stdio and Streamable HTTP transports.
MCP Servers
Connect agents to tools and data through the Model Context Protocol
An official Grafana MCP server that lets compatible AI clients discover dashboards and data sources, query Prometheus metrics and Loki logs, and work with alerts, incidents, and OnCall flows within existing Grafana permissions, with read-only, query-free, and network-hardening controls.
MCPHub is a self-hosted gateway between AI clients and multiple MCP servers, combining endpoint aggregation, group routing, access control, credential isolation, runtime logs, and optional vector-based smart routing.
A native Go MCP server that exposes Kubernetes and OpenShift resources, pod diagnostics, events, Helm operations, and optional ecosystem toolsets, with controls for read-only access, denied resources, and RBAC-scoped identities.
OpenAI's self-hosted client for connecting private or localhost MCP servers to ChatGPT, Codex, the Responses API, and AgentKit through Secure MCP Tunnel without exposing the MCP listener to the public internet.




