Happy slice of mcp pizzaMCP.pizza

chatmcp

MCP.Pizza Chef: daodao97

ChatMCP is a versatile, cross-platform AI chat client that implements the Model Context Protocol (MCP), enabling seamless integration with large language models across multiple operating systems including MacOS, Windows, Linux, iOS, and Android. It provides a unified interface for interacting with AI models, supporting real-time context feeding and tool invocation as defined by MCP standards. ChatMCP simplifies deploying AI chat capabilities on desktop and mobile platforms, making it ideal for developers and users seeking a consistent, powerful AI chat experience with broad device compatibility.

Use This MCP client To

Engage in AI-powered chat across multiple platforms Integrate MCP-compliant AI chat in desktop and mobile apps Test and develop AI chat workflows with real-time context Use as a client for multi-LLM environments supporting MCP Deploy AI chatbots with consistent UI on MacOS, Windows, Linux, iOS, Android

README

logo

chatmcp

Cross-platform Macos | Windows | Linux | iOS | Android AI Chat Client

English | 简体中文

Install

macOS Windows Linux iOS Android
Release Release Release ¹ TestFlight Release

¹ Note: On Linux you need to install libsqlite3-0 libsqlite3-dev, as this dependency needs it https://pub.dev/packages/sqflite_common_ffi

sudo apt-get install libsqlite3-0 libsqlite3-dev

Preview

Artifact Display Thinking Mode Generate Image LaTeX Support HTML Preview Mermaid Diagram mcp workflow mcp inmemory MCP Tools LLM Provider MCP Stdio MCP SSE

Usage

Make sure you have installed uvx or npx in your system

MacOS

# uvx
brew install uv

# npx
brew install node

Linux

# uvx
curl -LsSf https://astral.sh/uv/install.sh | sh

# npx (using apt)
sudo apt update
sudo apt install nodejs npm
  1. Configure Your LLM API Key and Endpoint in Setting Page
  2. Install MCP Server from MCP Server Page
  3. Chat with MCP Server

  • stdio mcp server

  • sse mcp server

Debug

  • logs & data

macOS:

~/Library/Application Support/ChatMcp

Windows:

%APPDATA%\ChatMcp

Linux:

~/.local/share/ChatMcp

Mobile:

  • Application Documents Directory

reset app can use this command

macOS:

rm -rf ~/Library/Application\ Support/ChatMcp

Windows:

rd /s /q "%APPDATA%\ChatMcp"

Linux:

rm -rf ~/.local/share/ChatMcp

Development

flutter pub get
flutter run -d macos

Features

  • Chat with MCP Server
  • MCP Server Market
  • Auto install MCP Server
  • SSE MCP Transport Support
  • Auto Choose MCP Server
  • Chat History
  • OpenAI LLM Model
  • Claude LLM Model
  • OLLama LLM Model
  • DeepSeek LLM Model
  • RAG
  • Better UI Design
  • Dark/Light Theme

All features are welcome to submit, you can submit your ideas or bugs in Issues

MCP Server Market

You can install MCP Server from MCP Server Market, MCP Server Market is a collection of MCP Server, you can use it to chat with different data.

Your feedback helps us improve chatmcp and helps other users make informed decisions.

Thanks

License

This project is licensed under the Apache License 2.0.

Star History

chatmcp FAQ

How do I install ChatMCP on Linux?
Install dependencies libsqlite3-0 and libsqlite3-dev using sudo apt-get install libsqlite3-0 libsqlite3-dev, then download the release from GitHub.
Is ChatMCP available on mobile platforms?
Yes, ChatMCP supports iOS via TestFlight and Android via GitHub releases.
Does ChatMCP support real-time context updates?
Yes, as an MCP client, ChatMCP supports feeding structured, real-time context to LLMs.
Can ChatMCP interact with multiple LLM providers?
Yes, it is designed to be provider-agnostic, compatible with OpenAI, Anthropic Claude, Google Gemini, and others.
What platforms does ChatMCP support?
ChatMCP is cross-platform, supporting MacOS, Windows, Linux, iOS, and Android.
How do I update ChatMCP?
Updates are available via GitHub releases for desktop platforms and TestFlight for iOS.
Does ChatMCP require special hardware?
No special hardware is required; it runs on standard devices supporting the listed OSes.
Is ChatMCP open source?
Yes, ChatMCP is open source and available on GitHub for community contributions and transparency.