Charts Visualization

this is the mcp for charts visualization in python

python

0

GitHub Stars

python

Language

7 months ago

First Indexed

3 months ago

Catalog Refreshed

Documentation & install

Readme and setup notes from the catalogue, plus a client-ready config you can copy for your MCP host.

Installation

Add the following to your MCP client configuration file.

Configuration

View docs

{
  "mcpServers": {
    "sakshi1x-mcp_visualization": {
      "command": "python",
      "args": [
        "src/server.py"
      ]
    }
  }
}

You can deploy and run a web service that generates bar and pie charts from structured data, saving them as PNG images and serving them via a REST API. This MCP server lets you visualize data quickly by producing chart images that you can embed or reference in your applications.

How to use

You interact with the server through an MCP client or by sending requests to the MCP endpoint. Generate a chart by providing your structured data and selecting a chart type (bar or pie). The server renders the chart as a PNG image, saves it to a static directory, and exposes it at a unique URL for easy access, for example under /static/charts/.

How to install

Prerequisites you need before you start:

Python 3.9+
venv (built-in)
git

Follow these steps to set up and run the server locally:

git clone <repo-url>
cd charts_visualization

python3 -m venv .venv
source .venv/bin/activate
pip install -r requirements.txt

# Start the server using Python
python src/server.py

# Alternatively, start with Uvicorn
uvicorn src.server:app --host 0.0.0.0 --port 8000

# The server will serve generated chart PNGs at http://localhost:8000/static/charts/ and respond to /mcp endpoint requests.

Notes and tips

Generated charts are saved in a static directory and can be accessed via URLs that point to the static charts path.
You can use either the plain Python runner or Uvicorn to host the server, depending on your needs (development vs. production).

Troubleshooting

If the PNGs are not appearing, verify the static/charts directory exists and that the server has write permissions to that path.
If requests to /mcp do not yield a chart, confirm that the input data is correctly structured and that a supported chart type (bar or pie) is selected.