Visualization MCP Server

A powerful Model Context Protocol (MCP) server for creating interactive data visualizations using matplotlib. This server provides comprehensive visualization tools including relationship graphs, scatter plots, 3D visualizations, and more.

Features

• 🔗 Relationship Graphs: Create network diagrams to visualize connections between entities
• 📊 Scatter Plots: Basic and classification scatter plots with customizable styling
• 🌐 3D Visualizations: Support for 3D scatter plots, surface plots, and wireframes
• 📈 Statistical Charts: Histograms, line plots, and heatmaps
• 💾 Auto-save: Automatically saves high-resolution images to temporary directory
• 🖼️ Live Display: Shows plots in interactive matplotlib windows
• 🎨 Customizable: Extensive styling options for colors, labels, and layouts

Installation

Prerequisites

$ python3 -m venv .venv --upgrade-deps 

$ source .venv/bin/activate

$ pip install "mcp[cli]" httpx

$ pip install   matplotlib numpy pandas networkx

Clone and Run

git clone https://github.com/xlisp/visualization-mcp-server.git
cd visualization-mcp-server
python visualization_server.py

Usage

1. Cladue Desktop Client Config

    "visualization": {
      "command": "/Users/clojure/Desktop/visualization-mcp-server/.venv/bin/python",
      "args": [
        "/Users/clojure/Desktop/visualization-mcp-server/visualization_server.py"
      ]
    }

The server provides several visualization tools that can be called via MCP protocol:

1. Relationship Graph

Create network diagrams to show relationships between entities:

# Example: Show relationships between A, B, C, D
nodes = ["Alice", "Bob", "Charlie", "Diana"]
edges = [["Alice", "Bob"], ["Bob", "Charlie"], ["Alice", "Charlie"], ["Charlie", "Diana"]]

# Call: create_relationship_graph(nodes, edges, "Social Network")

Parameters:

• nodes: List of node names
• edges: List of connections (pairs of node names)
• title: Graph title (optional)
• node_size: Size of nodes (default: 1000)
• font_size: Label font size (default: 12)

2. Scatter Plot

Create basic scatter plots with optional labels and colors:

# Example: Basic scatter plot
x_data = [1, 2, 3, 4, 5]
y_data = [2, 5, 3, 8, 7]
labels = ["Point A", "Point B", "Point C", "Point D", "Point E"]

# Call: create_scatter_plot(x_data, y_data, labels, title="My Scatter Plot")

Parameters:

• x_data: X-axis values
• y_data: Y-axis values
• labels: Point labels (optional)
• colors: Point colors (optional)
• title, x_label, y_label: Chart labels
• size: Point size (default: 50)

3. Classification Scatter Plot

Visualize data points grouped by categories:

# Example: Classification visualization
x_data = [1, 2, 3, 4, 5, 6]
y_data = [2, 3, 1, 5, 4, 6]
categories = ["Type A", "Type A", "Type B", "Type B", "Type C", "Type C"]

# Call: create_classification_plot(x_data, y_data, categories)

Parameters:

• x_data: X-axis values
• y_data: Y-axis values
• categories: Category labels for each point
• title, x_label, y_label: Chart labels

4. 3D Visualization

Create 3D plots with multiple visualization types:

# Example: 3D scatter plot
x_data = [1, 2, 3, 4, 5]
y_data = [2, 4, 1, 5, 3]
z_data = [3, 1, 4, 2, 5]

# Call: create_3d_plot(x_data, y_data, z_data, plot_type="scatter")

Parameters:

• x_data, y_data, z_data: 3D coordinates
• plot_type: "scatter", "surface", or "wireframe"
• title, x_label, y_label, z_label: Chart labels

5. Additional Charts

Histogram

# create_histogram(data, bins=30, title="Distribution")

Line Plot

# create_line_plot(x_data, y_data, line_style="-", color="blue")

Heatmap

# create_heatmap(data_matrix, x_labels, y_labels, colormap="viridis")

O

... View full README on GitHub