Skip to content
#

MCP

Star

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 1,801 public repositories matching this topic...

Language: Rust
Filter by language
All 46,105 Python 15,531 TypeScript 13,362 JavaScript 4,450 Go 2,291 Rust 1,801 Shell 874 HTML 855 C# 638 Java 497 Swift 254
Sort: Most stars
Sort options
Most stars Fewest stars Most forks Fewest forks Recently updated Least recently updated

yvgude / lean-ctx

Sponsor
Star 3k

Control what your AI can see. LeanCTX (Lean Context) is the context intelligence layer for AI agents — one local Rust binary that decides what they read, remembers what they learn, guards what they touch, and proves what they save. 60–90% fewer tokens as the receipt. 76 MCP tools, 30+ agents, local-first.

rust ai mcp developer-tools cursor copilot ai-agents llm gemini-cli ai-coding mcp-server claude-code token-optimization agentic-coding context-engineering context-layer reduce-token-costs lean-context context-intelligence
  • Updated Jul 2, 2026
  • Rust

Created by Anthropic

Released November 2024

Followers
797 followers
Website
github.com/topics/mcp

Related topics

agent-harness ai-agent llm mcp-server