Skip to content
#

MCP

Model Context Protocol (MCP) is an open standard that defines how AI applications connect to external tools, data sources, and services. MCP uses a client-server architecture where AI-powered applications (clients) communicate with lightweight programs (servers) that expose specific capabilities through a standardized interface.

MCP servers can provide tools (executable functions), resources (read-only data), and prompts (reusable templates). The protocol supports multiple transport mechanisms including stdio for local processes and HTTP with Server-Sent Events for remote connections.

The protocol was created by Anthropic and released as an open specification. It is supported by AI tools including Claude Code, Cursor, Codex, Windsurf, and Claude Desktop.

Here are 834 public repositories matching this topic...

An intelligent WhatsApp chatbot powered by Spring AI, OpenAI's GPT-4, and Model Context Protocol (MCP). Features conversation memory, dynamic tool calling for employee data queries, and real-time messaging via Meta's WhatsApp Business API. Includes MCP Inspector for debugging and ngrok support for local webhook development

  • Updated Nov 27, 2025
  • Java

MCP server that lets AI agents manage your email over IMAP — search, read, organize folders, move/delete messages — as a secure hosted service. Users link their IMAP account once; agents connect via OAuth 2.1 with scoped permissions and never see the raw password. Java 21 / Spring Boot.

  • Updated Aug 4, 2026
  • Java

Created by Anthropic

Released November 2024

Followers
1k followers
Website
github.com/topics/mcp

Related topics

agent-harness ai-agent llm mcp-server