AI ProtocolEvolution

A Model Context Protocol (MCP) server that provides privacy-focused web search, content fetching, and parsing through DuckDuckGo, with LLM-ready formatting and rate limiting.

GitHub's official Model Context Protocol (MCP) server that connects AI agents, assistants, and tools directly to GitHub's APIs for reading repositories, managing issues/PRs, code analysis, and workflow automation.

Serena is a powerful open-source coding agent toolkit that turns any LLM into a fully-featured coding agent with semantic code retrieval and editing powered by the Language Server Protocol (LSP) via the Model Context Protocol (MCP).

Official Model Context Protocol (MCP) server from Pollinations.ai that enables AI assistants like Claude, Cursor, and VS Code to generate high-quality images, text, audio, and video directly through natural language using the unified Pollinations generative AI API — with no authentication required and free compute.

Powerful open-source coding agent toolkit that turns any LLM into a full-featured AI coding agent with semantic code retrieval, editing, and IDE-like capabilities via the Model Context Protocol (MCP). Leverages the Language Server Protocol (LSP) for deep understanding across 20+ programming languages.

Official Model Context Protocol (MCP) server from data.gouv.fr that enables AI chatbots and agents (Claude, ChatGPT, Gemini, Cursor, etc.) to search, explore, discover, and analyze over 74,000 French public open datasets through natural language conversation.

Official cloud-hosted Atlassian Rovo MCP Server that securely connects AI assistants and agents (like Claude, Cursor, VS Code) to your Jira, Confluence, and Compass data for real-time search, summarization, creation, and updates using natural language — all while respecting user permissions and without caching content.

Official Microsoft MCP server that securely connects AI assistants like GitHub Copilot to your Azure DevOps organization, providing real-time context for work items, pull requests, pipelines, and more—running locally to keep your data secure.

MCP server that connects AI agents to the Godot game engine. Enables launching the editor, running projects, capturing debug output, and controlling execution.

Idea Reality MCP is an open-source MCP server that provides pre-build reality checks for AI coding agents. It automatically scans GitHub, Hacker News, npm, PyPI, Product Hunt, and Stack Overflow for existing projects, returning a 0-100 reality signal, duplicate likelihood, top competitors, evidence, and pivot suggestions before any code is written.

A production-ready plugin for OpenClaw that implements the A2A (Agent-to-Agent) v0.3.0 protocol, enabling bidirectional communication, task delegation, and automatic peer discovery between OpenClaw agents and other A2A-compatible agents across different servers.

Hermes Agent is an open-source, self-improving autonomous AI agent by Nous Research that learns from experience, builds reusable skills, maintains persistent cross-session memory, and evolves to become more capable over time.

Open SWE is an open-source asynchronous coding agent built by LangChain. It autonomously handles GitHub issues by researching codebases, planning tasks, writing and testing code, self-reviewing, and opening pull requests — acting like a full-time software engineer on your team.

Andrej Karpathy's open-source AI agent that autonomously runs LLM training experiments overnight on a single GPU, editing code, evaluating improvements, and iterating while you sleep.

OpenClaw's powerful Chrome DevTools MCP integration. Attach your local AI agent to your real signed-in Chrome browser (with cookies, tabs, and logins intact) for full web control — click, type, read pages, take snapshots, and automate any task directly in your live browser.

Skywork AI is a unified AI‑powered workspace featuring agentic capabilities to research, generate, and produce professional content across documents, presentations, spreadsheets, webpages, audio, and more.

Lovart AI Agent is a next‑generation autonomous creative AI that turns natural language prompts into professional visual designs, videos, and brand assets with an intuitive conversational workflow.

Simular AI provides advanced, research-driven autonomous AI agents that control your computer like a human, automating complex workflows on Mac, with Windows support coming soon, and open-source frameworks like Agent S for building computer-use agents.

Fully open-source generalist AI agent by Kortix. Autonomously completes complex real-world tasks using natural language, with web browsing, research, data extraction, document generation, and workflow automation capabilities.

Cloudflare's Dynamic Worker Loader API enables Workers to spawn new, isolated Workers at runtime with arbitrary code, providing lightweight sandboxing ideal for executing AI-generated code securely and efficiently.

The fast, Pythonic framework for building MCP (Model Context Protocol) servers and clients. Turn any Python function into production-ready LLM tools with zero boilerplate.

Microsoft A2A (Agent‑to‑Agent) is Microsoft’s implementation and support of the open Agent2Agent (A2A) protocol for interoperable AI agent communication across platforms and services.

Production-ready, easy-to-use multi-agent framework for building transparent, scalable LLM-powered applications with ReAct agents, tools, memory, evaluation, realtime voice, and secure runtime support.

LobeHub is a modern AI agent platform and marketplace for discovering, building, and collaborating with intelligent agent teammates. It features native Model Context Protocol (MCP) integration and the world's largest curated MCP Servers Marketplace with tens of thousands of ready-to-use integrations.