cbi-mcp-server

CB Insights' MCP Server

GitHub Stars

8

User Rating

Not Rated

Favorites

0

Views

120

Forks

3

Issues

1

Installation
Difficulty
Intermediate
Estimated Time
10-20 minutes
Requirements
Python 3.7以上
uv 最新版

Installation

Installation

Prerequisites

Please specify required software and versions:
Python: 3.7 or higher
uv: Latest version

Installation Steps

1. Clone Repository

bash
git clone https://github.com/cbinsights/cbi-mcp-server.git
cd cbi-mcp-server

2. Install Dependencies

bash
pip install -r requirements.txt

3. Set Environment Variables

Create a .env file and set the following environment variables:
bash
CBI_CLIENT_ID=your_client_id
CBI_CLIENT_SECRET=your_client_secret
CBI_MCP_PORT=8000
CBI_MCP_TIMEOUT=30

4. Start Server

bash
uv run server.py

Troubleshooting

Common Issues

Issue: Server won't start Solution: Check Python version and reinstall dependencies. Issue: Environment variables not set correctly Solution: Double-check the contents of the .env file.

Configuration

Configuration

Basic Configuration

Set the following in the .env file:
bash
CBI_CLIENT_ID=your_client_id
CBI_CLIENT_SECRET=your_client_secret
CBI_MCP_PORT=8000
CBI_MCP_TIMEOUT=30

Advanced Configuration

Security Settings

Store API keys in environment variables and avoid hardcoding them in the code.
Set appropriate file access permissions.

Configuration Example

Basic Configuration

bash
CBI_CLIENT_ID=your_client_id
CBI_CLIENT_SECRET=your_client_secret
CBI_MCP_PORT=8000
CBI_MCP_TIMEOUT=30

Examples

Examples

Basic Usage

Using with Claude Desktop

1Verify MCP Server Startup
Open Claude Desktop and confirm that the configuration has been loaded correctly.
2Execute Basic Commands

   Available tools from this MCP server:
   - ChatCBI: Sends a message to the AI and returns the response.
   

Programmatic Usage

python
import requests

def call_chatcbi(message, chat_id=None):
    response = requests.post(
        'http://localhost:8000/chat',
        json={
            'message': message,
            'chatID': chat_id
        }
    )
    return response.json()

Usage example

result = call_chatcbi('Hello, AI!') print(result)

Use Cases

Automating customer support through interactions with the AI chatbot.
Retrieving data analysis results from the AI to generate reports.
Providing real-time responses to user inquiries.
Building a content recommendation system based on related information.