MCP Servers
The open registry for Model Context Protocol servers. Find the right tools, resources, and prompts for your AI agents — filtered by category, transport, or use case.
Servers
195
Tools
516
Categories
11
Contributors
171
A Model Context Protocol server for HashiCorp Nomad that lets AI agents inspect and operate a Nomad cluster. Supports listing jobs, allocations, and nodes, reading allocation logs, and submitting or stopping jobs, which helps with debugging scheduling issues and running day-to-day workload operations.
A powerful, native Go implementation of a Kubernetes MCP server with support for Kubernetes and OpenShift. Unlike kubectl wrappers, it interacts directly with the Kubernetes API server — no external CLI tools required. Distributed as a single lightweight binary for Linux, macOS, and Windows. Supports multi-cluster configurations, Helm chart management, Tekton pipelines, pod exec, log streaming, and optional OpenTelemetry distributed tracing.
A Model Context Protocol server for Apache Kafka implemented in Go. Lets AI assistants inspect clusters, list and describe topics and consumer groups, produce test messages, and consume recent records, making it easier to debug and operate event-streaming pipelines from natural language.
Skills vs MCP servers
what’s the difference?Skillsthe “what to do”
A skill packages know-how — instructions, an example prompt, and recommended models — so an agent performs a task consistently. Skills add knowledge, not new connections.
MCP serversthe “how to connect”
An MCP server gives an agent new capabilities by connecting it to real systems (databases, APIs, files) over a transport. MCP adds connections and actions, not task instructions.
Rule of thumb: reach for a skill when you need the model to do a task well, and an MCP server when you need it to reach a tool or system. They compose — a skill can rely on tools an MCP server provides.
Built an MCP server?
Submit it to the registry — it’s open source and community-maintained.