Quickchat

🚀 Quickchat AI MCP Server

The MCP (Model Context Protocol) server of Quickchat AI allows anyone to integrate their Quickchat AI agents into their favorite AI applications, such as Claude Desktop, Cursor, VS Code, Windsurf, and more.

🚀 Quick Start

1. Create a Quickchat AI account and start a 7-day free trial of any plan.
2. Set up your AI's knowledge base, functions, and settings.
3. Go to the MCP page to activate your MCP. Give it a name, add a description, and (optionally) add commands. This information is crucial - AI applications need to know when to communicate with your AI, and what its capabilities and knowledge are.
4. Done! Now you can use the Quickchat AI agent to interact with other AI applications.

💻 Usage Examples

Configuration in Claude Desktop

Add the following content to the claudia.json file:

{
  "mcpServers": {
    "< QUICKCHAT AI MCP Name >": {
      "command": "uv",
      "args": ["run", "--with", "mcp[cli]", "--with", "requests", "mcp", "run", "< Your Path >/quickchat-ai-mcp/src/__main__.py"],
      "env": {
        "SCENARIO_ID": "< QUICKCHAT AI Scenario ID >",
        "API_KEY": "< QUICKCHAT AI API Key>"
      }
    }
  }
}

Configuration in Cursor

Add the following content to the config.json file:

{
  "mcpServers": {
    "< QUICKCHAT AI MCP Name >": {
      "command": "uv",
      "args": ["run", "--with", "mcp[cli]", "--with", "requests", "mcp", "run", "< Your Path >/quickchat-ai-mcp/src/__main__.py"],
      "env": {
        "SCENARIO_ID": "< QUICKCHAT AI Scenario ID >",
        "API_KEY": "< QUICKCHAT AI API Key>"
      }
    }
  }
}

📦 Sharing MCP

Share Configuration

Add the following content to the shared.json file to share your MCP:

{
  "mcpServers": {
    "< QUICKCHAT AI MCP Name >": {
      "command": "uv",
      "args": ["run", "--with", "mcp[cli]", "--with", "requests", "mcp", "run", "< Your Path >/quickchat-ai-mcp/src/__main__.py"],
      "env": {
        "SCENARIO_ID": "< QUICKCHAT AI Scenario ID >"
      }
    }
  }
}

Update MCP

Update your MCP configuration, including the name, description, and other parameters, in the Quickchat AI management interface. All changes will take effect in real-time.

🔧 Running from Source Code

Debugging with the MCP Check Tool

uv run mcp dev src/__main__.py

Debugging in Claude Desktop or Cursor

Use the following JSON configuration:

{
  "mcpServers": {
    "< QUICKCHAT AI MCP Name >": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "mcp[cli]",
        "--with",
        "requests",
        "mcp",
        "run",
        "< Your Path >/quickchat-ai-mcp/src/__main__.py"
      ],
      "env": {
        "SCENARIO_ID": "< QUICKCHAT AI Scenario ID >",
        "API_KEY": "< QUICKCHAT AI API Key>"
      }
    }
  }
}

Testing

Ensure the code is correctly formatted and all tests pass:

ruff check --fix
ruff format
uv run pytest

✨ Features

• You can control all aspects of the MCP from the Quickchat AI management interface. Changes take effect with just one click.
• View all conversation records in the Quickchat inbox.
• Unlike most static tools, this is not a static tool. It's an open way to interact with Quickchat AI agents.

⭐ GitHub Star History