Repolode
Submit
daodao97

daodao97/chatmcp

Cross-platform AI chat client that connects LLMs such as OpenAI, Claude, Ollama and DeepSeek to MCP servers.

Open-source alternative to:ChatGPTClaude Desktop

View on GitHubWebsite
Stars
2,227
Forks
210
Open issues
49
Last commit
last month

What is it?

ChatMCP is a desktop, mobile and web AI chat client built on the Model Context Protocol (MCP). It lets you chat with large language models while giving the model access to external tools and data through MCP servers, which can be run over stdio or SSE transports.

The app is written in Dart with Flutter and ships for macOS, Windows, Linux, iOS, Android and the browser. Users configure their LLM API key and endpoint in the settings page, then install MCP servers from a built-in server market and start chatting with them. Chat history and settings are stored locally in a SQLite database.

The project supports OpenAI, Claude, Ollama and DeepSeek models, with dark and light themes. Features such as RAG and automatic MCP server installation are listed as not yet implemented.

Key features

  • 01Chat with LLMs while connecting MCP servers as tools
  • 02Supports stdio and SSE MCP transports
  • 03Works with OpenAI, Claude, Ollama and DeepSeek models
  • 04Built-in MCP server market for installing servers
  • 05Local storage of chat history and settings
  • 06Dark and light themes

Use cases

  • Using a local Ollama model with filesystem or database MCP servers
  • Testing and debugging MCP servers through a chat interface
  • Running one AI chat client across desktop, mobile and web

Quick start

  1. 1

    Download the app for your platform from the Releases page

  2. 2

    Clone the repository

    git clone https://github.com/daodao97/chatmcp.git
  3. 3

    Install Flutter dependencies inside the cloned folder

    flutter pub get
  4. 4

    Run the app on macOS

    flutter run -d macos

Things to know

  • Running from source requires the Flutter SDK, and the Linux build needs Flutter desktop support enabled.
  • You must configure your own LLM API key and endpoint in the Settings page before chatting.
  • Installing MCP servers via the default stdio setup requires uvx or npx on your system.

Topics

#mcp#llm#chat-client#flutter#ollama#openai#claude#cross-platform#ai#chat

FAQ

What is chatmcp?
Cross-platform AI chat client that connects LLMs such as OpenAI, Claude, Ollama and DeepSeek to MCP servers. ChatMCP is a desktop, mobile and web AI chat client built on the Model Context Protocol (MCP). It lets you chat with large language models while giving the model access to external tools and data through MCP servers, which can be run over stdio or SSE transports.
Is chatmcp free to use? What license does it have?
chatmcp is open source under the Apache-2.0 license. Check the license terms before using it in commercial products.
Is chatmcp still maintained?
Updated within 6 months. The last commit to chatmcp was on Sep 7, 2026.
What can I use chatmcp for?
Using a local Ollama model with filesystem or database MCP servers Testing and debugging MCP servers through a chat interface Running one AI chat client across desktop, mobile and web
How do I install chatmcp?
Download the app for your platform from the Releases page Clone the repository: git clone https://github.com/daodao97/chatmcp.git Install Flutter dependencies inside the cloned folder: flutter pub get Run the app on macOS: flutter run -d macos
Where can I get chatmcp?
The source code and installation instructions are on GitHub: https://github.com/daodao97/chatmcp

Summary generated by AI from the project's README. GitHub stats refresh daily.

Related projects