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.
Discover awesome MCP servers.
Kamalesh-Seervi
AlexlaGuardia
A nervous system for AI agents — awareness daemon, frame-based tool filtering, signal protocol, session handoff, and event triggers. 14 modules, 268 tests, zero dependencies. MCP server with stdio and SSE transports.
tengfone
devinellis
frippe75
Intelligent VMware MCP Server with Natural Language Processing for Infrastructure Management
GodZlayer
roysam
CDataSoftware
This project builds a read-only MCP server. For full read, write, update, delete, and action capabilities and a simplified setup, check out our free [CData MCP Server for Amazon Athena (beta)](https://www.cdata.com/download/download.aspx?sku=FKZK-V&type=beta).
k4han
willschipp
Spring AI implementation of a Kubernetes MCP Server
dj-pearson
The Supabase Coolify MCP Server enables AI agents to fully manage self-hosted Supabase instances on Coolify. It provides 52 production-ready tools for database migrations (with rollback), edge functions, storage, authentication, and health monitoring. Features include Zod-based i
peanut996
joshwhitfield
sheep52031
admin-amaravati-io
adanb13
Cirdan maps and watches the live infrastructure your agent session can reach — Docker, Kubernetes, cloud, IaC, and telemetry — then exposes it over MCP. It fingerprints the environment, builds a dependency graph, detects incidents, and can run evidence-backed actions. It inherits
manucr619
This is a Cloudflare Worker that serves as an MCP (Model Context Protocol) server for interacting with the Zerodha Kite Connect API.
MCP-Mirror
Mirror of
tomtev
guptaprakhariitr
MCP server for drug-interaction-mcp — see README
mohdhaji87
This MCP server exposes all AWS Bedrock Guardrails management features as tools, allowing you to create, edit, delete, and export guardrails (including all policy types) programmatically or via LLMs like Claude Desktop. It also supports exporting guardrail configurations as Terra
OpenWorkspace-o1
AWS Aurora Postgres with Pgvector Extension MCP Server.
landpageapp
listingbureau
Amazon organic ranking MCP server. Run campaigns, track keyword positions, monitor rank movement.
fenoh3ry
flav0000
jeffpoulton
Humboldtian
anandkumarpatel
CDataSoftware
This read-only MCP Server allows you to connect to Azure Synapse data from Claude Desktop through CData JDBC Drivers. For full CRUD support, check out the first managed MCP platform: CData Connect AI (https://www.cdata.com/ai/).
CDataSoftware
This project builds a read-only MCP server. For full read, write, update, delete, and action capabilities and a simplified setup, check out our free CData MCP Server for Azure DevOps (beta): https://www.cdata.com/download/download.aspx?sku=HNZK-V&type=beta
zefarie
MCP server for Pterodactyl and Pelican game server panels. 73 tools for server management, power control, file operations, backups, schedules, databases, users, nodes, eggs, and allocations. Supports both stdio (npm) and remote (Cloudflare Worker) modes.
miludeerforest
rawatadit
CDataSoftware
This read-only MCP Server allows you to connect to Amazon Redshift data from Claude Desktop through CData JDBC Drivers. Free (beta) read/write servers available at
dgallitelli
A simple implementation of MCP Client/Server architecture with HTTP SSE transport layer, dockerized.
miracledevlol
ZubeidHendricks
MCP Server for the Azure DevOps API, enabling project management, repository operations, and more.
mikec-naitive
MCP client repository for Cloudflare services integration with Cursor/GitHub - enables natural language interaction with Cloudflare's 13 MCP servers including documentation, Workers bindings, observability, container services, and AutoRAG.
apexradius
guptaprakhariitr
MCP server for hn-trending-mcp — see README
rawatadit
MCP-Mirror
Mirror of
devopsjester
Spel
spacemagic-dev
githubpradeep
sugarshop
deploy mcp server using Python fastmcp and Cloudfloare.
alexcraviotto
sivakumarl
MCP Server with Cloudflare Workers
ArchitectRavi
SAP On Azure MCP Server for TypeScript
kopp0510
k8s-mcp-server is a Kubernetes and Helm management tool based on Model Context Protocol (MCP), designed specifically for n8n workflow automation platform.
ductnn
A lightweight MCP server that provides natural language processing and API access to Kubernetes clusters, combining both kubectl commands and Kubernetes Python client.
endo-sys
ackriv
aal80
patrickdappollonio
mcp-kubernetes-ro is a Model Context Protocol (MCP) server providing read-only access to Kubernetes clusters for AI assistants. It enables AI models to list resources, get resource details, retrieve pod logs, discover API resources, and perform base64 encoding/decoding operations
MCP-Mirror
Mirror of
matthewfreshit
devanshjainms
MCP server to access Azure using az commands.
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.