Quickchat Ai MCP

🚀 Quickchat AI MCP Server

Quickchat AI MCP Server provides a seamless way to integrate and manage AI interactions with customized knowledge bases.

🚀 Quick Start

1. Create a Quickchat Account: Visit the Quickchat official website to register and log in.
2. Set Up the Knowledge Base: Navigate to the "Knowledge Base" section in the dashboard and add and configure your question - answer pairs.
3. Activate MCP: Go to the "MCP" page, fill in the name and description, and click "Enable".

🔗 Useful Links

• Video Tutorial
• Blog Post

📦 Installation of uv Tool

Install and configure uv:

pip install uv

💻 Usage Examples in Claude Desktop and Other AI Applications

Configuration Example

Use the following JSON configuration in Claude Desktop or Cursor:

{
  "mcpServers": {
    "< QUICKCHAT AI MCP NAME >": {
      "command": "uv",
      "args": ["run", "--with", "mcp[cli]", "--with", "requests", "mcp", "run", "< 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

🔄 Sharing Configuration

1. On the Quickchat MCP page, turn off the "Require API Key" option.
2. Share the configuration without the API key:

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

✨ Features

1. Debugging Tool: Use the MCP Inspector for debugging:

   uv run mcp dev src/__main__.py
   

2. Log Viewing: View all conversation records in the Quickchat dashboard.
3. Flexible Interaction: Supports open - ended communication with the Quickchat AI agent.

💻 Running from Source Code

Using the Debugging Tool

uv run mcp dev src/__main__.py

Usage in AI Applications

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

⭐ GitHub Star History