Enola.dev is an agentic AI toolkit for various LLMs (incl. e.g. Google Gemini & Anthropic APIs; as well as thousands of local models via Ollama). It comes with a number of built-in tools, and MCP client support for external tools. It has several UIs:

• Chat Web UI, served by a built-in local HTTP web-server
• Chat CLI Textual User Interface (TUI) for the terminal (also available via a built-in SSH server)
• One-shot ai agent prompt CLI

It can also simply invoke (call) any MCP server's tools directly (without LLM).

Think n8n + ChatGPT. FLUJO is a desktop application that integrates with MCP to provide a workflow-builder interface for AI interactions. Built with Next.js and React, it supports both online and offline (ollama) models, it manages API Keys and environment variables centrally and can install MCP Servers from GitHub. FLUJO has a ChatCompletions endpoint and flows can be executed from other AI applications like Cline, Roo or Claude.

• Environment & API Key Management
• Model Management
• MCP Server Integration
• Workflow Orchestration
• Chat Interface

Goose is a general-purpose AI agent that can dynamically plug into new extensions and learn how to use them. It solves higher-level problems using tools from multiple extensions and can interact with multiple extensions at once.

Glue is a full-featured, thread-first team chat platform with a built-in AI agent and support for MCP, enabling teams to leverage intelligent tools and insights. Learn more.

HyperChat is an open Chat client that can use various LLM APIs to provide the best Chat experience and implement productivity tools through the MCP protocol.

JDBCX extends JDBC by providing enhanced support for data formats and compression, object mapping, advanced type conversion, multi-language query capabilities, and MCP support.

kibitiz is the free and open-source Replit. Minimally, it is a lightweight chat interface to the popular LLM APIs (Anthropic and OpenAI API formats supported). Experience automated tool loops: try asking your agent to use wcgw to make a change to a local repository, then fix linter and compiler errors, make a commit, and push to remote, all without user intervention! Even better, code on-the-go by setting up MCP servers on your laptop, then connecting from your mobile through Kinode.

LangBot is an open-source platform for creating LLM based instant messaging bots. It supports multi platforms like Discord, Telegram, WeChat, QQ. Currently supports LLMs from OpenAI, Anthropic, DeepSeek, Ollama, and more. And easy for users to create agents with MCP or plugins. Users can also customize their experience through WebUI, or create plugins to extend the functionality of the bot.

Klavis AI is building open-source infrastructure to make Model Context Protocols (MCPs) easy for everyone. We provide:

• 💬 Slack & Discord Clients: Run MCPs directly from your favorite messaging platforms
• ☁️ Hosted MCP Servers: Access powerful tools without infrastructure management
• 🎛️ Simple Web UI: Configure and manage everything with no coding required

Whether you're a non-technical user wanting to leverage AI workflows or a developer looking to build and scale MCPs, Klavis makes it simple.

Kiro is an AI assistant and IDE built to assist developers. Kiro helps you do your best work by bringing structure to AI coding with spec-driven development.

Enhanced ChatGPT Clone: Features Agents, Anthropic, AWS, OpenAI, Assistants API, Azure, Groq, o1, GPT-4o, Mistral, OpenRouter, Vertex AI, Gemini, Artifacts, AI model switching, message search, Code Interpreter, langchain, DALL-E-3, OpenAPI Actions, Functions, Secure Multi-User Auth, Presets, open-source for self-hosting.

Lutra is the first AI task agent that connects all your work apps. It is designed to turn your conversations into automated workflows. Lutra understands your goals and actions it can take, and it automatically determines how to work with your apps to get tasks done. After completing a task, you can create playbooks which save the steps as reusable automations. Lutra connects with MCP servers easily: you only need to provide the server URL and it does all the setup behind the scenes.

mcp-agent is a simple, composable framework to build agents using Model Context Protocol.

Inspiration: Anthropic announced 2 foundational updates for AI application developers:

1. Model Context Protocol - a standardized interface to let any software be accessible to AI assistants via MCP servers.
2. Building Effective Agents - a seminal writeup on simple, composable patterns for building production-ready AI agents.

mcp-agent puts these two foundational pieces into an AI application framework:

1. It handles the pesky business of managing the lifecycle of MCP server connections so you don't have to.
2. It implements every pattern described in Building Effective Agents, and does so in a composable way, allowing you to chain these patterns together.
3. Bonus: It implements OpenAI's Swarm pattern for multi-agent orchestration, but in a model-agnostic way.

Modern AI chat framework with multi-model support: Features OpenAI, Anthropic Claude, Google Gemini, Azure OpenAI, Ollama, and 100+ AI models. Includes plugin system, knowledge base, text-to-speech, vision recognition, DALL-E image generation, function calling, multi-agent conversations, PWA support, mobile-responsive design, i18n localization, theme customization, and self-hosting capabilities. Built with Next.js for optimal performance and user experience.

This chatbot example demonstrates how to integrate the Model Context Protocol (MCP) into a simple CLI chatbot. The implementation showcases MCP's flexibility by supporting multiple tools through MCP servers and is compatible with any LLM provider that follows OpenAI API standards.

A simple CLI to run LLM prompt and implement MCP client.

MCP Playground is a comprehensive web-based MCP client for testing Claude and Gemini models with MCP server integration. Features dual AI provider support, advanced tool management with granular access control, custom system prompts, OAuth authentication, and real-time server monitoring. Perfect for testing MCP servers, comparing AI providers, and debugging tool implementations without writing code.

Key Features:

• Dual AI Support - Claude & Gemini models with seamless switching
• Smart Tool Control - Restrict which tools AI can access (all/selected/none)
• Custom System Prompts - Shape AI personality and behavior
• OAuth & Bearer Auth - Production-ready authentication support
• Real-time Testing - Live server monitoring and direct tool execution

A simple CLI to run LLM prompt, attach files, discuss with MCP servers. For multiple LLMs, including local models.

A simple Slack bot that uses LLMs and the Model Context Protocol (MCP) tools.

Memex is the first MCP client and MCP server builder in one desktop app. Unlike traditional MCP clients that only consume existing servers, Memex can create custom MCP servers from natural language prompts, immediately integrate them into its toolkit, and use them to solve problems—all within a single conversation.

Key MCP Features:

• Prompt-to-MCP Server: Generate fully functional MCP servers from natural language descriptions
• Self-Testing & Debugging: Autonomously test, debug, and improve created MCP servers
• Universal MCP Client: Works with any MCP server through intuitive, natural language integration
• Curated MCP Directory: Access to tested, one-click installable MCP servers (Neon, Netlify, GitHub, Context7, and more)
• Multi-Server Orchestration: Leverage multiple MCP servers simultaneously for complex workflows

This unique dual capability of creating AND consuming MCP tools makes Memex the most versatile all-in-one solution in the MCP ecosystem.

A powerful universal CLI client for MCP Servers that provides seamless integration with multiple protocols, AI models, and tools through an intelligent interface.

uv add mcpomni-connect or pip install mcpomni-connect

Add MCP Capabilities to Chatgpt, Gemini, Grok, Google AI Studio, DeepSeek, AI Studio, OpenRouter, T3 Chat, Mistral and Github Copilot. This extension allows you to connect to any MCP server and use its tools, models, and capabilities directly from your browser without any API key required in these Chat Platforms.

Nerve is an ADK ( Agent Development Kit ) and CLI designed to be a simple yet powerful platform for creating and executing LLM-based agents fully integrated with MCP.

Light and Fast AI Assistant, with Claude, DeepSeek, GPT4, Gemini Pro & MCP support.

A terminal client for Ollama, with support for MCP servers.

This project provides a Slack bot client that serves as a bridge between Slack and Model Context Protocol (MCP) servers. By leveraging Slack as the user interface, it allows LLM models to interact with multiple MCP servers using standardized MCP tools.

Key features:

• ✅ Multi-Mode MCP Client:
  • SSE for real-time communication
  • HTTP transport for JSON-RPC
  • stdio for local development and testing
• ✅ Slack Integration:
  • Socket Mode for secure, firewall-friendly communication
  • Works with both channels and direct messages
• ✅ Tool Registration: Dynamically register and call MCP tools
• ✅ Docker container support

No-code MCP clients for Slack, Microsoft Teams, and Discord with full support for MCP servers, connected knowledge sources, and custom instructions.

Superinterface is AI infrastructure and a developer platform to build in-app AI assistants with support for MCP, interactive components, client-side function calling and more.

Key features:

• Use tools from MCP servers in assistants embedded via React components or script tags
• SSE transport support
• Use any AI model from any AI provider (OpenAI, Anthropic, Ollama, others)

✨ A Sleek and Powerful AI Chat Desktop Application ✨

SeekChat supports MCP tool execution, enabling AI to directly control your computer and perform various tasks. Easily automate file management, data analysis, code development, and more, turning AI into a truly intelligent assistant.

Simple AI (simple-ai-io) is a command-based web/cli application, supports MCP.

Tambo is a platform for building custom chat experiences, with integrated custom user interface components.

A client that connects to any MCP server using Server-Sent Events (SSE) and displays conversations in a chat-like UI.
It is a standalone Apify Actor for testing MCP servers over SSE, with support for Authorization headers.
Built with plain JavaScript (old-school style) and hosted on Apify, it requires no setup to run.

Key features:

• Connects to any MCP server via Server-Sent Events (SSE).
• Works with the Apify MCP Server to interact with one or more Apify Actors.
• Dynamically utilizes tools based on context and user queries (if supported by the server).
• Open-source—review, suggest improvements, or modify as needed.

Tiles is a notebook interface that makes working with AI agents easier.

Tome is an open source cross-platform desktop app designed for working with local LLMs and MCP servers. Tome manages your MCP servers so there's no fiddling with uv/npm or json files - connect it to Ollama, copy/paste some MCP servers, and chat with an MCP-powered model in seconds.

Key features:

• MCP servers are managed by Tome so there is no need to install uv or npm or configure JSON
• Users can quickly add or remove MCP servers via UI
• Any tool-supported local model on Ollama is compatible

LLM discord bot with MCP support, customizable personality and scheduling

Key Features:

• Invokes an LLM agent every time someone sends a message
• Integrates with MCP servers
• Supports all well-known LLM providers
• Supports custom agent instructions

VS Code integrates MCP with GitHub Copilot through agent mode, allowing direct interaction with MCP-provided tools within your agentic coding workflow. Configure servers in Claude Desktop, workspace or user settings, with guided MCP installation and secure handling of keys in input variables to avoid leaking hard-coded keys.

Key Features:

• Support for stdio and server-sent events (SSE) transport
• Per-session selection of tools per agent session for optimal performance
• Easy server debugging with restart commands and output logging
• Tool calls with editable inputs and always-allow toggle
• Integration with existing VS Code extension system to register MCP servers from extensions

The first agentic IDE, and then some. The Windsurf Editor is where the work of developers and AI truly flow together, allowing for a coding experience that feels like literal magic.

Witsy is an AI desktop assistant supporting models from all major providers and one keyboard shortcut away!

Enconvo is your AI Agent Launcher that revolutionizes productivity. With instant access, automate your daily tasks effortlessly. Our intelligent AI Agent system, powered by 150+ built-in tools and MCP support, learns and adapts to your workflow. Experience seamless automation and enhanced productivity with the most versatile AI assistant for macOS.

A tiny command-line interface chat application that brings AI conversations to your terminal. Features include chat data storage in JSONL files, interactive chat interface, support for multiple bot configurations compatible with OpenAI chat completion streaming format, Deepseek-r1 reasoning content support, and MCP client support with multiple server configurations.

Zed is a high-performance, multiplayer code editor from the creators of Atom and Tree-sitter.

MindPal is a no-code platform for building and deploying AI agents and multi-agent workflows. It enables anyone without technical skills to create powerful AI automation solutions by connecting any AI model with any tool. Build complex workflows where multiple AI agents work together to accomplish tasks, with built-in support for MCP servers and tools.

Key features:

• No-code AI agent builder
• Multi-agent workflow orchestration
• Support for any AI model provider
• MCP server integration
• Visual workflow designer
• Built-in tool marketplace

WhatsMCP is a WhatsApp agent that allows you to interact with MCP servers. It is a simple and easy to use tool that allows you to interact with your AI stack from WhatsApp.

Runbear enables teams to create AI assistants in communication tools like Slack, MS Teams, and HubSpot. It supports MCP through SSE transport and provides managed MCP servers for easy integration.

Key Features:

• Support for MCP tools in team communication platforms
• Integration with remote MCP servers via SSE
• Managed MCP server options for teams

mcp-client-go is a Golang client library for the Model Context Protocol (MCP). It allows developers to register and interact with various MCP-based services such as Amap (Gaode Maps) using a unified API.

BoltAI is an all-in-one AI chat client. It supports MCP tools calling, dynamic MCP server management and in-context server control.

Key features:

• Multiple AI providers & models
• MCP server integration
• Native app: fast & powerful
• Import configuration from Claude or Cursor
• Built-in configuration editor

Argo is a localized large model agent builder. Build agents with local & Cloud LLMs, RAG, MCP tools. Users can share these creations in our community, download AI agents from others.

Key features:

• Download opensource LLMs from ollama, huggingface or modelscope with one click.
• Use local docs for RAG, sync with directories.
• Support MCP tools.
• Manage Agents with individual prompt, model, knowledge and MCP tools.

A CLI host application that enables Large Language Models (LLMs) to interact with external tools through the Model Context Protocol (MCP).

Lightweight, Fast, Simple, CLI-Based MCP Client for STDIO MCP Servers, to fill the gap and provide bridge between your local LLMs running Ollama and MCP Servers. Specially crafted for Zin MCP Servers for reverse engineering.

Lightweight, Fast, Simple, CLI MCP Client for MCP Servers. Supporting TUI, stdio and NapCat. Any LLM API compatible with the OpenAI API, such as Ollama and DeepSeek, can be configured for use.

Qordinate is a personal assistant that talks on your behalf, it knows what to share, when to share and with whom to share. It's available across WhatsApp and Arattai today, with other platforms coming soon. Learn more.

PraisonAI is a production-ready Multi-AI Agents framework with native MCP integration. Features fastest agent instantiation (3.77μs), 100+ LLM support via LiteLLM, agentic workflows (route/parallel/loop/repeat), built-in memory, and self-reflection. Available as Python & JavaScript SDKs.

Looking for MCP servers? Check out the awesome-mcp-servers repository.