Real-time web data integration with search, browsing, and dynamic scraping for AI workflows, delivering fresh context and export options.

Community hub cataloging Cursor components, plugins, events, and jobs with auto-detection and Open Plugins alignment.

⌥ AI Coding agent for the terminal — hash-anchored edits, optimized tool harness, LSP, Python, browser, subagents, and more

《御舆：解码 Agent Harness》42万字拆解 AI Agent 的Harness骨架与神经 —— Claude Code 架构深度剖析，15 章从对话循环到构建你自己的 Agent Harness。在线阅读网站：

An MCP server, which connects to Discord through a bot, and provides comprehensive integration with Discord.

Enables code-aware tools to search Pinecone docs, configure indexes, generate code, and test vector operations with live data in development.

Unified access to 74M+ company records, 823M+ employees, and 399M+ job postings for AI-powered workflows.

A next-gen FOSS self-hosted unified zero trust secure access platform that can operate as a remote access VPN, a ZTNA platform, API/AI/MCP gateway, a PaaS, an ngrok-alternative and a homelab infrastructure.

Context management for Claude Code. Hooks maintain state via ledgers and handoffs. MCP execution without context pollution. Agent orchestration with isolated context windows.

Flexible Python framework for building and orchestrating multimodal AI agents with CLI-first tooling and secure authentication.

Seamless Terraform API integration delivering workspace management, registry access, and OTEL metrics for advanced IaC automation.

Platform for Longbridge OpenAPI enabling real-time quotes, trading actions, portfolio data, and live push updates across multiple languages.

A single hub to find Claude Skills, Agents, Commands, Hooks, Plugins, and Marketplace collections to extend Claude Code, Claude Desktop, Agent SDK and OpenClaw

Zotero MCP: Connects your Zotero research library with Claude and other AI assistants via the Model Context Protocol to discuss papers, get summaries, analyze citations, and more.

CyberStrikeAI is an AI-native security testing platform built in Go. It integrates 100+ security tools, an intelligent orchestration engine, role-based testing with predefined security roles, a skills system with specialized testing skills, and comprehensive lifecycle management capabilities.

Ephemeral, specialized agents coordinate via a persistent knowledge graph using MCP, enabling real-time visualization, safe parallel development, and robust task orchestration.

Enterprise AI Platform with guardrails, MCP registry, gateway & orchestrator

mcp)** (by yuna0x0) - An MCP server for HackMD, a collaborative markdown editor. It allows users to create, read, and update documents in HackMD using the Model Context Protocol.

Chrome extension to let agents control your browser. Runs Playwright snippets in a stateful sandbox. Available as CLI or MCP

Hybrid rule-based and LLM-driven data quality evaluation with modular prompts and MCP integration.

MCP server that integrates Microsoft Teams messaging (read, post, mention, list members and threads)

An MCP proxy server that aggregates and serves multiple MCP resource servers through a single HTTP server.

Open-source multi-agent framework leveraging Solace event mesh, A2A communication, and dynamic embeds.

The world's first open-source AI-native vector design tool and the first to feature concurrent Agent Teams. Design-as-Code. Turn prompts into UI directly on the live canvas. A modern alternative to Pencil.