What is an MCP server?
An MCP server is a program built on the Model Context Protocol that wraps a tool, data source, or API — like file access, a database, or web search — into a capability an AI assistant can discover and call.
Browse MCP servers by category and sort by GitHub stars or newest additions. Open a listing for configuration and setup details.
bestK
MCP
rondweb
beastpu
mcp tools for k8s resources management using cursor agent
shuaking
philipp-eisen
Simple MCP server to add images to Cloudflare Images
MalcolmFeatonby
geelen
Talk to a Cloudflare Worker from Claude Desktop!
devinellis
majie1993
wakeupworld
dulltz
MCP server for working with HCP Terraform
tje8x
Track and optimize AI API spending across 16 providers. Real-time pricing, model routing analysis, caching opportunities, unit economics, and spend forecasting. Connects to OpenAI, Anthropic, AWS, GCP, Stripe, and more.
bhatiarajesh
GavinLucas
More than just a fully featured MCP server that lets AI agents manage Docker — containers, images, networks, volumes, swarm services, secrets, configs, nodes, plugins, etc., it helps you create workflows to easily manage your Docker environments.
cloudforgetech6-ctrl
CloudForge MCP lets Claude visualise your cloud architecture diagrams, generate production-ready Terraform HCL from natural language, import existing IaC, and manage Azure, AWS, and GCP resources — all from chat.
irvinebroque
roy3drucker
lfpicoloto1
agent-ready
younggeeks
sverze
AWS API/lambda hosting MCP client server that queries bedrock LLM using MCP hosted tools
MCP-Mirror
Mirror of
MichaelYangjson
Laity624
MCP test
zhb0808
zzerding
ysys143
Dockerized MCP server environments for seamless agent-tool integration.
growtha
MCP-Mirror
Mirror of
devanshjainms
MCP server to access Azure using az commands.
pathikpa
cyhw
guptaprakhariitr
MCP server for uspto-patents-mcp — see README
CarlLee1983
Git-driven MCP Server for managing Prompt templates with Handlebars support. Store prompts in Git, sync automatically, and use dynamic templates in Cursor, Claude Desktop, and other MCP clients. Features hot-reload, group filtering, version management, and Docker/Kubernetes deplo
imsardine
jademind
A lightweight Python MCP server that exposes Amazon Product Advertising API 5.0 keyword search and ASIN lookup—returning products with your Associate partner-tagged URLs.
scoritz
Superjolt is a Platform-as-a-Service (PaaS) that enables developers to deploy JavaScript applications instantly with a single command: npx superjolt deploy. Through its native Model Context Protocol (MCP) integration, developers can manage their entire deployment infrastructure u
bjacobso
tatsuiman
dxsim
MCP server to directly access AWS location services using the GeoPlaces API, provides direct geocoding or reverse-geocoding capabilities like Google Maps API
miracledevlol
sheep52031
alvinmrrry
ajot
berkayyildirim
A Zero-Trust MCP server for AWS Cost Explorer
HenkDz
komination
ductnn
A lightweight MCP server that provides natural language processing and API access to Kubernetes clusters, combining both kubectl commands and Kubernetes Python client.
subomi
paulobrien
Common questions about MCP servers, tools, and integrations
An MCP server is a program built on the Model Context Protocol that wraps a tool, data source, or API — like file access, a database, or web search — into a capability an AI assistant can discover and call.
Every server's detail page includes ready-to-paste config snippets for Claude Desktop, Cursor, VS Code, and other common clients — most installs take just a couple of minutes.
Most servers listed here are free and open source. Some wrap third-party APIs (cloud services, paid data providers, etc.) that require your own API key or subscription.
A local MCP server runs on your device and usually connects over stdio, giving you more direct control over data but requiring a runtime and installation. A remote MCP server is hosted by a provider and connects over HTTP, making setup easier while adding network and provider availability dependencies.
Claude Desktop, Claude Code, Cursor, VS Code, Codex, and other AI clients that support the Model Context Protocol can connect to MCP servers. Configuration formats and supported transports vary by client.
Review the source repository, maintenance activity, dependencies, requested permissions, and data-handling documentation before installation, and prefer official or trusted maintainers. Use least-privilege credentials for sensitive access such as files, databases, shells, and production systems.