# Taboola_MCP

Read information from your Taboola Account

Installation Instructions

README: https://github.com/matlafu/taboola_mcp

Taboola MCP Connector

An MCP (Model Context Protocol) tool that connects Taboola Advertising API with AI assistants like Claude (in Cursor, Claude Desktop, etc.), allowing you to analyze your campaign data through natural language conversations.

Features

• Natural Language Querying: Ask questions about your Taboola campaigns in plain English
• Campaign Performance Analysis: Get summaries, trends, and insights about your advertising performance
• Account Management: View all your accounts and campaigns in one place
• Data Visualization: See performance trends with simple ASCII charts right in your chat interface
• Comprehensive Insights: Get actionable recommendations based on your campaign data

Setup

Prerequisites

• Python 3.8+ installed
• A Taboola account with API access
• Valid Taboola API credentials (client ID and client secret)

Installation

1. Clone or download this repository and install dependencies

2. Install dependencies

   pip install -r requirements.txt
   

3. Set up your environment variables

   Create a .env file in the root directory with your Taboola API credentials:

   TABOOLA_CLIENT_ID=your_client_id
   TABOOLA_CLIENT_SECRET=your_client_secret
   

4. Test the connector

   Run the script to verify it connects to Taboola correctly:

   python taboola_connector.py
   

   You should see logs indicating successful authentication and account loading.

Using with Cursor

1. Add the connector to Cursor's MCP configuration

   Open or create .cursor/mcp.json in your user directory and add the following entry:

   {
     "mcpServers": {
       "Taboola_Connector": {
         "command": "FULL/PATH/TO/YOUR/DIRECTORY/taboola_mcp/.venv/Scripts/python",
         "args": [
           "FULL/PATH/TO/YOUR/DIRECTORY/taboola_mcp/taboola_connector.py"
         ]
       }
     }
   }
   

2. Restart Cursor

   Close and reopen Cursor to load the updated MCP configuration.

3. Verify the connection

   In Cursor's chat, ask a simple question like "List my Taboola accounts" to verify the connection works.

Available Tools

The connector provides the following tools for interacting with Taboola:

Example Queries

You can ask questions in natural language like:

• "Show me my Taboola campaign performance for the last 30 days."
• "What were my top performing campaigns last month?"
• "List all my active Taboola campaigns."
• "Give me a summary of my account performance with charts."
• "Analyze my campaign data from June 1 to June 30."
• "Which campaigns had the highest CTR last week?"

Troubleshooting

Connection Issues

• "TaboolaConnector is not available": Check that your .env file exists with correct credentials.
• Python Command Not Found: Make sure the Python path in .cursor/mcp.json is correctly specified.
• No tools available: Ensure the MCP server is running correctly by checking logs in taboola_mcp.log.

Authentication Errors

• Bad client credentials: Verify your TABOOLA_CLIENT_ID and TABOOLA_CLIENT_SECRET are correct.
• No accounts found: Check that your API credentials have access to the accounts you're trying to query.

Path Issues

• If you see errors about files not found, make sure all paths in your configuration are absolute paths (not relative).

Technical Details

The connector communicates with the Taboola API to retrieve campaign data, and exposes this data through MCP tools. This allows AI assistants to query and analyze your advertising data.

The connector follows these steps:

1. Authenticate with Taboola API
2. Fetch available accounts
3. Provide tools to query campaign data
4. Process and format the data for easy consumption by AI assistants

Contributing

If you'd like to contribute to this project, found a bug or an issue, please open an issue or submit a pull request :)

License

MIT License