chatmcp logo

chatmcp

CommunityPopular
daodao97

ChatMCP is an AI chat client implementing the Model Context Protocol (MCP).

Publisherdaodao97
Repositorychatmcp
LanguageDart
Forks
208
Stars
2.2K
Available tools
0
Transport typestdio
Categories
LicenseApache-2.0
Links
  • Connect tools to AI workflows

    chatmcp exposes MCP capabilities that can be used by compatible AI clients and agents.

  • 0 available tools

    Browse the callable actions below, including names and descriptions when provided by the server.

  • Ready-to-copy setup

    Use the installation snippets to configure this server in your preferred MCP client.

  • Open source signals

    2.2K stars and 208 forks from the linked repository.

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

English | 简体中文 | Türkçe

Install

macOSWindowsLinuxiOSAndroidWeb
ReleaseReleaseRelease ¹TestFlightReleaseGitHub Pages ²

¹ Linux Notes:

  • See Linux requirements below for AppImage/DEB runtime dependencies on Ubuntu 22.04 and 24.04
  • Improved Experience: Latest versions include better dark theme support, unified data storage following XDG Base Directory Specification, and optimized UI layout for Linux desktop environments is planned
  • Tested on major distributions: Ubuntu, Fedora, Arch Linux, openSUSE

² Note: Web version runs entirely in your browser with local storage for chat history and settings.

Documentation

Also, you can use DeepWiki to get more information about chatmcp.
Ask DeepWiki DeepWiki is an AI-powered platform that transforms any public GitHub repository into a fully interactive, easy-to-understand wiki. By analysing code, documentation, and configuration files, it creates clear explanations, interactive diagrams, and even allows for real-time Q&A with the AI.

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

Data Sync

ChatMCP applications can sync data within the same local area network

Data sync

Usage

Make sure you have installed uvx or npx in your system

MacOS

bash
# uvx
brew install uv

# npx
brew install node 

Linux

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

# npx (using apt)
sudo apt update
sudo apt install nodejs npm

Linux Requirements (Ubuntu 22.04 and 24.04)

For running ChatMCP AppImage/DEB on Ubuntu and derivatives, install the following runtime packages:

  • AppImage (FUSE): libfuse2
  • GTK 3: libgtk-3-0
  • Graphics/EGL:
    • Ubuntu 22.04: libegl1-mesa, libgles2, libgl1-mesa-dri, libglx-mesa0
    • Ubuntu 24.04: libegl1, libgles2, libgl1-mesa-dri, libglx-mesa0
  • X11 utilities and SQLite: libx11-6, xdg-utils, libsqlite3-0

Install commands:

  • Ubuntu 22.04:
bash
sudo apt install -y libfuse2 libgtk-3-0 libegl1-mesa libgles2 libgl1-mesa-dri libglx-mesa0 libx11-6 xdg-utils libsqlite3-0 libsqlite3-dev
  • Ubuntu 24.04:
bash
sudo apt install -y libfuse2 libgtk-3-0 libegl1 libgles2 libgl1-mesa-dri libglx-mesa0 libx11-6 xdg-utils libsqlite3-0 libsqlite3-dev

Optional (recommended): mesa-vulkan-drivers, mesa-utils (for diagnostics like glxinfo)

  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

Data Storage

ChatMCP follows platform-specific best practices for data storage:

Storage Locations

macOS:

bash
~/Library/Application Support/ChatMcp/

Windows:

bash
%APPDATA%\ChatMcp\

Linux:

bash
~/.local/share/ChatMcp/           # Honors $XDG_DATA_HOME if set
~/.local/share/run.daodao.chatmcp # Flutter dependency

Mobile:

  • Application Documents Directory

File Structure

All platforms store data in a unified directory structure:

  • logs folder - Application logs
  • chatmcp.db - Main database file containing chat history and messages
  • shared_preferences.json - Application settings and preferences
  • mcp_server.json - MCP server configurations

Reset Application Data

To completely reset the application (delete all chat history, settings, and configurations):

macOS:

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

Windows:

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

Linux:

bash
rm -rf ~/.local/share/ChatMcp
rm -rf ~/.local/share/run.daodao.chatmcp

Development

Install Flutter

To develop or run ChatMCP, you need to have Flutter installed.
Follow the official Flutter installation guide for your platform.

After installing, verify with:

bash
flutter --version

Mandatory Code Formatting and Pre-commit Hook

To keep a consistent code style across contributors, this repository enforces Dart formatting on every commit.

  • The repository ships a versioned Git hook at .githooks/pre-commit.
  • On commit, it runs dart format ., re-adds changed files, and then performs a no-output check to ensure nothing remains unformatted.
  • Commits that are not properly formatted will be rejected locally; in addition, CI will fail unformatted PRs.

Quick setup (once per clone):

bash
make setup-git-hooks

Manual setup (alternative):

bash
git config core.hooksPath .githooks
chmod +x .githooks/pre-commit

Requirements (at least one must be available on PATH):

  • Dart SDK, or
  • Flutter (bundles Dart)

Examples:

  • macOS/Linux (Flutter):
    bash
    export PATH="$PATH:$HOME/flutter/bin"
    which flutter && flutter --version
    which dart && dart --version
  • macOS/Linux (Dart SDK):
    bash
    export PATH="$PATH:$HOME/dart-sdk/bin"
    which dart && dart --version
  • Windows (PowerShell): Add C:\\src\\flutter\\bin (or your Flutter path) to the User/System PATH. Validate via:
    powershell
    where flutter
    where dart

IDE note: After changing PATH, restart your IDE so VCS operations (commit) inherit the updated environment.

CI enforcement:

  • A GitHub Actions workflow check-format runs dart format --output=none --set-exit-if-changed . on push/PR and will fail if any file is not formatted.

Policy:

  • Do not bypass hooks (e.g., --no-verify). Such changes will fail in CI and must be reformatted anyway.

Clone and Run Locally

bash
# Clone the repository
git clone https://github.com/daodao97/chatmcp.git
cd chatmcp

# Install dependencies
flutter pub get

# Run on macOS
flutter run -d macos

# Run on Linux (requires Flutter desktop support enabled)
flutter run -d linux

# Build release for Linux
flutter build linux

Web Version

Local Development

bash
# Install dependencies
flutter pub get

# Run Web version locally
flutter run -d chrome
# Or specify port
flutter run -d chrome --web-port 8080
# Or run as web-serer for other browsers.
flutter run -d web-server

Build Web Version

bash
# Build production version
flutter build web

# Build with base path (for deploying to subdirectory)
flutter build web --base-href /chatmcp/

Deploy to GitHub Pages

bash
# 1. Build Web version
flutter build web --base-href /chatmcp/

# 2. Push build/web directory contents to gh-pages branch
# Or use GitHub Actions for automatic deployment

After building, files will be in the build/web directory and can be deployed to any static website hosting service.

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.

Create a fork of mcp_server_market and add your MCP Server to the mcp_server_market.json end of the file.

json
{
    "mcpServers": {
        "existing-mcp-servers": {},
        "your-mcp-server": {
              "command": "uvx",
              "args": [
                  "--from",
                  "git+https://github.com/username/your-mcp-server",
                  "your-mcp-server"
            ]
        }
    }
}

You can send a Pull Request to the mcp_server_market repository to add your MCP Server to the Market. After your PR is merged, your MCP Server will be available in the Market and other users can use it immediately.

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

Installation

TypingMind
Prerequisites:

Node.js 18+

{
  "mcpServers": {
    "daodao97-chatmcp": {
      "command": "",
      "args": []
    }
  }
}

Use chatmcp MCP with multiple AI models

TypingMind connects MCP tools at the workspace level, so once chatmcp is connected, you can use it with different AI models in TypingMind instead of setting it up separately for each model. This MCP runs locally through the TypingMind MCP connector on your device.

Setup guide to use the local connector

Use this when the MCP server needs access to local files, apps, or private resources on your computer.

1

Open the MCP settings

In TypingMind, go to Settings, Advanced Settings, then Model Context Protocol and choose Setup Connector.

  1. Open TypingMind in your browser.
  2. Click the Settings icon.
  3. Go to Advanced Settings.
  4. Open the Model Context Protocol section.
  5. Click Setup Connector and choose This Device.
TypingMind MCP connector setup screen with This Device selected
2

Run the connector command

Choose This Device, copy the command from TypingMind, and run it in Terminal. Keep the process running while you use MCP.

  1. Copy the setup command shown by TypingMind.
  2. Open Terminal on macOS or Windows Terminal on Windows.
  3. Paste and run the command.
  4. Approve the package install if Terminal asks you to proceed.
  5. Keep the Terminal window running while using MCP tools.
3

Add chatmcp as a server

When the connector status is Ready, click Edit Servers and paste the MCP server configuration.

  1. Wait until the connector status shows Ready.
  2. Click Edit Servers.
  3. Paste the chatmcp MCP server configuration.
  4. Save the server list.
  5. Refresh if you want to confirm the connector is still ready.
TypingMind MCP settings showing active server and Edit Servers button
{
  "mcpServers": {
    "daodao97-chatmcp": {
      "command": "npx",
      "args": [
        "-y",
        "chatmcp"
      ]
    }
  }
}
4

Use it across models

Save the server list, open Plugins, enable the chatmcp MCP tools, then select any supported AI model in TypingMind and use the tools in chat or assign them to an AI agent.

  1. Open the Plugins page in TypingMind.
  2. Enable the chatmcp MCP tools.
  3. Start a chat and choose the AI model you want to use.
  4. Use the MCP tools in chat or assign them to an AI agent.
  5. Switch to another AI model whenever needed without reconnecting MCP.
TypingMind chat using enabled MCP tools with a selected AI model
Can you use chatmcp to help me with this task?
chatmcp
Sure. I read it.
Here is what I found using chatmcp.

Frequently asked questions

What is the chatmcp MCP server used for?

chatmcp is an MCP server that lets compatible AI clients connect to external tools and context. In TypingMind, you can add this MCP server once and make its tools available in your AI workspace.

Can I use chatmcp MCP with multiple AI models in TypingMind?

Yes. TypingMind connects MCP tools at the workspace level, so you can use chatmcp with different AI models such as Claude, ChatGPT, Gemini, or other models you have configured in TypingMind without setting up the MCP server separately for each model.

Why use chatmcp MCP with TypingMind?

TypingMind is one of the best frontends for LLM chat because it brings multiple AI models, prompts, plugins, AI agents, API keys, and MCP tools into one workspace. With chatmcp connected, you can use its MCP tools across your preferred models while keeping your chat workflow organized in TypingMind.

How do I connect chatmcp MCP to TypingMind?

chatmcp runs through the TypingMind local MCP connector. This is best when the MCP server needs access to local files, desktop apps, command-line tools, or private resources on your computer.

What tools does chatmcp MCP provide in TypingMind?

chatmcp exposes MCP capabilities that can be enabled from the TypingMind Plugins page and used in chat or assigned to AI agents.

Do I need to share my API keys with TypingMind to use chatmcp MCP?

No. TypingMind is local-first and lets you keep your model providers, API keys, prompts, and MCP configuration under your control. If chatmcp requires authentication, add the required headers, OAuth settings, or local configuration for that MCP server when you create the connection.

Related MCP Servers

View all

Set up your own AI workspace now

Get notified about new features and future giveaways by subscribing to our newsletter 👇