AI Topic: MCP

Open-source platform for stateful AI agents with persistent memory. Build, observe, and deploy agents via ADE, REST API, SDKs, and a desktop app. Connect tools via MCP; use any model; run self-hosted or on Letta Cloud.

Memory layer for AI apps and agents. Open-source SDK + managed API that adds long-term, semantic and graph memory with fast retrieval, policy controls, and analytics.

High-accuracy web research and search APIs built for AI agents, providing structured answers, citations, and MCP-ready integrations.

Local MCP server in Figma Dev Mode that pipes design context (variables, components, layout) to AI coding tools like VS Code, Cursor, Windsurf, and Claude Code.

Zapier’s Model Context Protocol server exposes Zaps and app actions as MCP tools for AI agents like Claude, Cursor, and Windsurf.

TypeScript framework for building and shipping MCP applications with file system routing, hot reloading, and flexible deployment options.

MCP server that gives AI coding agents access to Figma design data for one-shot design implementation.

Free, open-source coding agent toolkit that connects LLMs to your codebase using symbolic tools, editing, and execution.

Keep your AI agents grounded in real, up-to-date library docs and examples using version-aware context injection.

Open-source, multimodal agentic framework from Moonshot AI designed for structured tool use, function calling, and advanced orchestration.