DeepChat

v1.0.0Communicationstable

🐬DeepChat - A smart assistant that connects powerful AI to your personal world

agentagent-skillsaiai-assistantai-sdk
Share:
5,826
Stars
0
Downloads
0
Weekly
0/5

What is DeepChat?

DeepChat is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to 🐬deepchat - a smart assistant that connects powerful ai to your personal world

🐬DeepChat - A smart assistant that connects powerful AI to your personal world

This server falls under the Communication category on MCPgee, the world's largest MCP server directory with 33,000+ servers.

Features

  • 🐬DeepChat - A smart assistant that connects powerful AI to y

Use Cases

Personal AI assistant
Cross-platform support
Agent skill integration
ThinkInAIXYZ

Maintainer

LicenseApache-2.0
Languagetypescript
Versionv1.0.0
UpdatedMay 22, 2026
Statushealthy
Maintenanceactive

Works with

ClaudeOpenAIwindowsmacoslinux

Installation

Manual Installation

npx deepchat

Configuration

Configuration Details

Config File

claude_desktop_config.json

Performance

Response Metrics

Response Time< 200ms
ThroughputMedium

Resource Usage

Memory UsageLow
CPU UsageLow

How to Set Up and Use DeepChat

DeepChat is a cross-platform AI chat application built on Electron that connects popular AI providers — including Claude, ChatGPT, Gemini, and DeepSeek — to a unified interface with full MCP protocol support for Resources, Prompts, and Tools. It integrates web search (Google, Bing, Brave, Baidu), a built-in Node.js runtime for running npx-based MCP servers without extra setup, remote control via Telegram, Discord, Feishu, and WeChat, plus a skills/agent system that lets users install capabilities from URLs or ZIP files. Teams and individual users install DeepChat when they want a feature-rich AI desktop client that can connect to any MCP server and run multi-modal workflows without writing code.

Prerequisites

  • Windows, macOS, or Linux (AppImage/deb for Linux)
  • An API key for at least one supported provider: Anthropic (Claude), OpenAI, Google Gemini, DeepSeek, or a local Ollama instance
  • No Node.js install required — DeepChat ships a built-in Node.js runtime for MCP servers
1

Download and install DeepChat

Download the installer for your platform from the GitHub releases page or the official website.

# macOS (Homebrew)
brew install --cask deepchat

# Or download directly:
# https://github.com/ThinkInAIXYZ/deepchat/releases
# Windows: DeepChat-Setup-x.x.x.exe
# macOS:   DeepChat-x.x.x.dmg
# Linux:   DeepChat-x.x.x.AppImage or .deb
2

Configure your AI provider

Launch DeepChat, open Settings, and go to Model Providers. Add your API key for Claude, OpenAI, Gemini, DeepSeek, or point it at a local Ollama instance.

# API keys to have ready:
# Anthropic Claude  → sk-ant-...
# OpenAI            → sk-...
# Google Gemini     → AIza...
# DeepSeek          → sk-...
# Ollama (local)    → no key, set base URL: http://localhost:11434
3

Add an MCP server

In Settings, navigate to MCP Servers and add a server using its stdio command. DeepChat's built-in Node.js runtime means npx-based servers work without a separate Node.js installation.

# Example: add Desktop Commander MCP
# In DeepChat MCP settings:
# Command: npx
# Args:    -y @wonderwhy-er/desktop-commander@latest
4

Enable web search integration

Configure one of the supported search providers (Brave, Google, Bing, Baidu) in Settings to give the AI live web access during conversations.

5

Set up remote control (optional)

DeepChat can be controlled remotely via messaging platforms. Configure a Telegram bot token, Discord webhook, or Feishu/Lark integration in Settings to send prompts from your phone or team chat.

DeepChat Examples

Client configuration

DeepChat is a standalone desktop application. MCP servers are configured through its UI, not via a JSON file you edit manually. The underlying config for an MCP server in DeepChat follows this shape:

{
  "mcpServers": {
    "desktop-commander": {
      "command": "npx",
      "args": ["-y", "@wonderwhy-er/desktop-commander@latest"]
    },
    "microsandbox": {
      "command": "npx",
      "args": ["-y", "microsandbox-mcp"]
    }
  }
}

Prompts to try

DeepChat works best for conversational AI tasks with optional tool and search augmentation.

- "Search the web for the latest version of Next.js and summarise the new features"
- "Read the file at ~/project/README.md and write a Chinese translation"
- "Use the code execution tool to run this Python snippet and show me the output"
- "Send a Telegram message to my team channel summarising today's work"

Troubleshooting DeepChat

MCP server fails to start within DeepChat

DeepChat ships a built-in Node.js runtime, but the version may differ from your system Node.js. Test the MCP server command in a terminal first. If it works externally but not in DeepChat, check that the command path is absolute or that npx resolves correctly in DeepChat's bundled environment.

AI model returns 'API key invalid' error

Re-enter your API key in Settings > Model Providers. Ensure the key matches the selected provider — for example, an OpenAI key (sk-...) cannot be used for Anthropic Claude. For Ollama, confirm the daemon is running with `ollama serve`.

Web search returns no results

Verify you have configured a search provider in Settings and that any required API key (e.g., Brave Search API key) is entered correctly. Brave Search requires a free API account at https://brave.com/search/api/.

Frequently Asked Questions about DeepChat

What is DeepChat?

DeepChat is a Model Context Protocol (MCP) server that 🐬deepchat - a smart assistant that connects powerful ai to your personal world It connects AI assistants to external tools and data sources through a standardized interface.

How do I install DeepChat?

Follow the installation instructions on the DeepChat GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.

Which AI clients work with DeepChat?

DeepChat works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.

Is DeepChat free to use?

Yes, DeepChat is open source and available under the Apache-2.0 license. You can use it freely in both personal and commercial projects.

Browse More Communication MCP Servers

Explore all communication servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.

Quick Config Preview

{ "mcpServers": { "deepchat": { "command": "npx", "args": ["-y", "deepchat"] } } }

Add this to your claude_desktop_config.json or .cursor/mcp.json

Read the full setup guide →

Ready to use DeepChat?

Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.

33,000+ ServersFree & Open SourceStep-by-Step Guides