BI Chart MCP Server
About
An MCP (Model Context Protocol) server for data transformation and BI charts will allow AI assistants to connect to your data sources, transform data, and generate high-quality visualizations through natural language requests.
Details
- Author
- c-cf
- GitHub stars
- 13
- Downloads
- 263
- Categories
- Search
Jump to
- Built with Python, migrated from TypeScript
- Modular structure: data loading, processing, visualization
- Uses Vega‑Lite for chart rendering
- Includes unit tests for core components
- Configurable via requirements.txt and pyproject.toml
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
BI Chart MCP ServerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
Clone the repository, create a virtual environment, install dependencies from requirements.txt, then start the server using python scripts/run_server.py or python -m mcp_bi_visualizer.server. Run tests with pytest.
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"bi chart mcp server": {
"bi-chart-mcp-server": {
"command": "python",
"args": [
"-m",
"mcp_bi_visualizer.server"
]
}
}
}
}McpServers
{
"bi-chart-mcp-server": {
"command": "python",
"args": [
"-m",
"mcp_bi_visualizer.server"
]
}
}BI Chart MCP Server
This project implements the BI Chart MCP Server using Python. Previously, the functionality was prototyped with TypeScript, but the current and maintained version is built with Python.
Project Structure
- mcp_bi_visualizer/: Contains the main server code and modules.
- server.py: Main entry point for starting the MCP server.
- data/: Data loading and processing modules.
- loader.py
- processor.py
- resources/: Modules to manage project resources.
- manager.py
- memo.py
- visualization/: Visualization components.
- renderer.py
- vega_lite.py
- scripts/
- run_server.py: A script to launch the server.
- tests/: Unit tests for the server and visualization components.
- Other files include configuration files (e.g., pyproject.toml, requirements.txt, setup.py) and documentation.
Installation
1. Clone the repository.
2. Create a virtual environment and activate it:
python -m venv .venv
.venv\Scripts\activate # On Windows
3. Install the required dependencies:
pip install -r requirements.txt
Running the Server
You can run the server using the provided script:
python scripts/run_server.py
Alternatively, you can start the server directly from the module:
python -m mcp_bi_visualizer.server
Testing
Run the tests using your preferred test runner. For example, with pytest:
pytest
Notes
- The project has been migrated from a TypeScript-based implementation to Python.
- For any issues or contributions, please refer to the CONTRIBUTING.md file.
Enjoy using the BI Chart MCP Server!
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
