MCP Clients

MCP provides a standardized way for AI models to discover and interact with external tools, applications, and data sources. When you enter a chat prompt to a language model with agent mode in VS Code, the model can invoke various tools to perform tasks like file operations, accessing databases, or calling APIs in response to your request.

n8n is a visual AI agent/workflow builder platform. The MCP Client Tool node allows you to use the tools exposed by an external MCP server. You can connect the MCP Client Tool node to your models to call external tools with n8n agents. There is also functionality to expose n8n tools as a remote MCP server.

This integration enables using MCP Servers in Home Assistant for providing additional tools to use with a conversation agent. For example, you can add an MCP server that supports memory functionality, or that can search the web using functionality not already available in Home Assistant. Controlling Home Assistant is done by providing MCP clients access to the Assist API of Home Assistant. You can control what devices and entities it can access.

Code at the speed of thought – Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter. MCP features supported: Prompts.

Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way. MCP features supported: Resources, Tools.

Cursor lets you breeze through changes by predicting your next edit. It knows your codebase, so you can get answers from your codebase or refer to files or docs. Edit in natural language. Use MCP by going to Settings > Features > MCP Servers. Features supported: Tools.

Cherry Studio is a powerful AI assistant desktop application built with Electron, React, and TypeScript that enables users to interact with various AI models and services. It features a tray-based interface, multi-language support, and integrates with external services like Nutstore for cloud storage. The application includes knowledge base functionality, file management capabilities, and supports various document formats through specialized loaders, making it valuable for content creation, document processing, and AI-assisted productivity tasks.

Coding assistant plugin for VSCode and JetBrains. Chat to understand and iterate on code in the sidebar. Autocomplete to receive inline code suggestions as you type. Edit to modify code without leaving your current file. Actions to establish shortcuts for common use cases. Differentiated through its extensibility, Continue.dev allows developers to configure and combine different language models, knowledge bases, and tools to create tailored coding assistance. MCP features supported: Resources, Prompts, Tools.

LibreChat is the ultimate open-source app for all your AI conversations, fully customizable and compatible with any AI provider — all in one sleek interface. Compatible with macOS and Windows. Open source under the MIT license. MCP features supported: Tools.

Smolagents is a streamlined library for running powerful agents with minimal code. It features a compact 1,000-line core focused on simplicity, specializes in secure code agents that execute in sandboxed environments, and integrates with Hugging Face Hub. The library is model-agnostic (supporting local models, Hub providers, OpenAI, Anthropic, and others via LiteLLM), works with multiple input modalities (text, vision, video, audio), and accommodates various tool ecosystems including LangChain, Anthropic's MCP, and Hub Spaces.

Autonomous coding agent right in your IDE, capable of creating/editing files, executing commands, using the browser, and more with your permission every step of the way. In many ways similar to Cline (from which it is forked), but has built out additional agentic capabilities and AI features. MCP features supported: Resources, Tools.

UI-TARS-desktop is an Electron-based GUI agent application that allows users to control their computer using natural language through Vision-Language Models. The project consists of two main components: a UI-TARS desktop application for visual interaction with the system and an Agent-TARS application that handles natural language processing and computer control. It includes operators for browser automation and desktop control, with support for multiple VLM providers including HuggingFace.