# Mcp Search Analytics

> MCP server for GA and GSC data analysis

- **Type:** MCP server
- **Install:** `agentstack add mcp-vesivanov-mcp-search-analytics`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [vesivanov](https://agentstack.voostack.com/s/vesivanov)
- **Installs:** 0
- **Category:** [Data & Analytics](https://agentstack.voostack.com/c/data-and-analytics)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [vesivanov](https://github.com/vesivanov)
- **Source:** https://github.com/vesivanov/mcp-search-analytics

## Install

```sh
agentstack add mcp-vesivanov-mcp-search-analytics
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

# MCP Search Analytics Server

A Model Context Protocol (MCP) server for Google Analytics and Search Console data analysis.

## 🚀 Features

- Unified access to Google Analytics 4 and Google Search Console data
- Real-time analytics queries through MCP interface
- Secure credential management via environment variables

## 🔧 Setup

### Prerequisites

- Python 3.8+
- Google Cloud Project with Analytics and Search Console APIs enabled
- Google Service Account with appropriate permissions

### Installation

1. Clone this repository:
```bash
git clone https://github.com/vesivanov/mcp-search-analytics.git
cd mcp-search-analytics
```

2. Create a virtual environment:
```bash
python -m venv venv
source venv/bin/activate  # On Windows: venv\Scripts\activate
```

3. Install dependencies:
```bash
pip install -r requirements.txt
```

### Configuration

1. **Create environment file:**
   ```bash
   cp environment.example .env
   ```

2. **Set up Google Service Account:**
   - Create a service account in Google Cloud Console
   - Download the JSON credentials file
   - Enable Google Analytics Reporting API and Search Console API
   - Grant necessary permissions to your service account

3. **Configure environment variables:**
   Edit `.env` file with your actual values:
   ```
   ANALYTICS_CREDENTIALS_PATH=/path/to/your/credentials.json
   GSC_SITE_URL=https://your-website.com
   GA4_PROPERTY_ID=your-property-id
   ```

### Usage

1. Test your credentials:
```bash
python test_credentials.py
```

2. Run the MCP server:
```bash
python unified_analytics_server.py
```

## 🔐 Security Notes

- **Never commit credential files** (`.json`, `.env`) to version control
- Store credentials securely and use environment variables
- Regularly rotate service account keys
- Follow principle of least privilege for API access

## 📋 Requirements

See `requirements.txt` for Python dependencies.

## 🤝 Contributing

1. Fork the repository
2. Create a feature branch
3. Make your changes
4. Test thoroughly
5. Submit a pull request

## 📄 License

This project is licensed under the MIT License - see the [LICENSE](./LICENSE) file for details.

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [vesivanov](https://github.com/vesivanov)
- **Source:** [vesivanov/mcp-search-analytics](https://github.com/vesivanov/mcp-search-analytics)
- **License:** MIT

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** yes
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-vesivanov-mcp-search-analytics
- Seller: https://agentstack.voostack.com/s/vesivanov
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.