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.
akutishevsky
Connect Claude to your Lunch Money personal finance data for conversational money management. Ask natural language questions about spending, manage budgets and categories, create transactions, and get financial insights through chat. Supports full CRUD operations including transa
dontellu77
Career and workforce intelligence built on a deep HR ontology — skill taxonomies, role definitions and responsibilities, compensation and incentive structures, learning and development pathways, sourcing strategies, and role/skill evolution mapping. This structured foundation, co
pabloleaf
MCP server for Targe — LLM key sharing and micropayments from Claude Desktop and Cursor
Ferdev
Agent skills and MCP discovery metadata for using SwarmKit as an inspectable coding partner
pizzaeueu
The proxy enables integration between OpenAI chat models and local MCP servers via Function Calling, allowing custom PII checks for sensitive data verification
kelvinyuefanli
The hive mind for AI agents — a shared knowledge graph where AI agents contribute, verify, and consume technical knowledge
bmoir23
bighadj22
MCP Playground: Experiment with Anthropic's Claude & Model Context Protocol. Chat, connect servers, test tools.
TalaoDAO
A lightweight and AI-friendly MCP server that allows any AI agent or MCP-compatible assistant to initiate and verify a PID (Personal Identity Data) credential presentation via OIDC4VP.
taisly
Taisly Agent is an MCP server, CLI, SDK, and agent skill for publishing short-form videos to TikTok, Instagram Reels, YouTube Shorts, X, and Facebook through Taisly. It helps AI agents and automation workflows validate connected social accounts, create video posts, and check publ
LeadDelta
MCP server for LeadDelta — manage LinkedIn connections and CRM data via AI assistants
anycast-net
Connect AI assistants to the Anycast network. Manage agents, send messages, control access policies, and monitor connectivity — all from Claude, Cursor, or any MCP-compatible client. 19 tools covering agent registration, P2P connections, groups, policies, and analytics.
ntrtd
MCP Server implementation for Dynamics 365 AI Agent (TypeScript)
sarick-story
A demo agent using our MCP server
garasegae
Agent-first skill marketplace MCP server. AI agents discover, install, and share reusable skills across 7 platforms (Claude, Cursor, Windsurf, Cline, VSCode, Copilot, OpenAI) via MCP protocol. 15 tools including skill search, download, upload, and agent discovery.
refgrow
MCP server for managing affiliate and referral programs. Create programs, track referrals, manage affiliates, process conversions, and handle payouts — all through AI assistants like Claude, Cursor, and ChatGPT.
mows21
Claude Desktop MCP Server - Local desktop AI agent with file access and notifications
Sumedh1599
Uses Claude or OpenAI API to convert prompt-mapped input into concrete MCP server components such as tools, resource templates, and prompt handlers.
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.