https://github.com/data-goblin/fabric-model-reader-mcp
https://github.com/data-goblin/fabric-model-reader-mcp
Last synced: 11 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/data-goblin/fabric-model-reader-mcp
- Owner: data-goblin
- License: other
- Created: 2025-07-16T20:09:32.000Z (12 months ago)
- Default Branch: main
- Last Pushed: 2025-07-18T14:59:41.000Z (11 months ago)
- Last Synced: 2025-07-24T06:29:55.220Z (11 months ago)
- Size: 757 KB
- Stars: 2
- Watchers: 0
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Fabric Model Reader MCP
[](https://www.python.org/downloads/)
[](https://github.com/anthropics/mcp)
[](https://github.com/anthropics/dxt)
[](LICENSE)
Basic single-file MCP server for reading and analyzing Fabric semantic models. Available as both a standalone MCP server and a Desktop Extension (DXT).
**⚠️ IMPORTANT: This extension requires authentication with Microsoft/Azure to access Power BI workspaces. You must authenticate using Azure CLI or provide a Personal Access Token before use.**
## Quick Start
### For Claude Desktop Users (Easiest)
**Prerequisites**:
1. Python 3.8+ must be installed and in your PATH
- **Mac/Linux**: Usually pre-installed as `python3`. Use the `_python3` version.
- **Windows**: Download from [python.org](https://python.org) - during installation, check "Add Python to PATH". Use the `_python` version.
2. Install required Python packages:
```bash
# For Mac/Linux:
pip3 install fastmcp requests keyring
# For Windows:
pip install fastmcp requests keyring
```
**Installation**:
1. Download `fabric-model-reader_python3.dxt` or `fabric-model-reader_python.dxt` (check the repository for the latest .dxt file)
2. Double-click the `.dxt` file
3. Click "Install" in Claude Desktop
4. **Configure authentication** (see Authentication section below)
### For Other MCP Clients
1. Install dependencies:
```bash
pip install -r requirements.txt
```
2. Configure your MCP client to use this server. Example for VS Code:
```json
{
"mcpServers": {
"fabric-model-reader": {
"command": "python3",
"args": ["path/to/fabric-model-reader-mcp.py"]
}
}
}
```
3. Authenticate using one of the supported methods:
- Personal Access Token
- Azure CLI
4. Start using the server through your MCP client.
5. For convenient use, you should use the [Fabric Workspace Reader MCP server](https://github.com/data-goblin/fabric-workspace-reader-mcp) and other supported Microsoft Fabric MCP servers.
### Authentication
The extension supports three authentication methods:
- **Azure CLI**: `az login` (recommended)
- **Environment Variable**: Set `POWERBI_TOKEN`
- **System Keyring**: Store token securely in system keyring
## AI References
Code and docs were created with the help of the following AI models:
- Claude Opus 4.0
- Claude Sonnet 4.0
- Gemini 2.5
## Security & Privacy Disclaimer
**IMPORTANT**: Users of this software are **solely responsible** for:
- 🔐 **Securing authentication credentials** and access tokens
- 🏢 **Compliance** with organizational data security policies
- 🛡️ **Protecting sensitive data** accessed through this software
- 📋 **Regulatory compliance** with GDPR, CCPA, and other data privacy laws
- 🚨 **Implementing access controls** and proper data handling procedures
The authors assume **NO responsibility** for:
- Data breaches or unauthorized access
- Privacy violations or data exposure
- Misuse of organizational data
- Security incidents resulting from use of this software
## General Disclaimer
THIS SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. THE USER ASSUMES ALL RESPONSIBILITY AND RISK FOR THE USE OF THIS SOFTWARE.