Skip to content
Back to search

mcp-server-data-exploration

MCP Server for Data Exploration

Safety scan

A static text scan, not a guarantee. Select the badge to see what was scanned and every finding.

Checked today
Badge for your README
findsafeskills safety rating

Markdown

[![findsafeskills safety rating](/api/listings/reading-plus-ai--mcp-server-data-exploration/badge.svg)](/listings/reading-plus-ai--mcp-server-data-exploration)

HTML

<a href="/listings/reading-plus-ai--mcp-server-data-exploration"><img src="/api/listings/reading-plus-ai--mcp-server-data-exploration/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

What was scanned

The files the safety scan read, as written by the repository's author and shown as plain text. Lines with a finding are marked.

README.md · README · 146 lines

View this file on GitHub (read at the repository's current version: the scan did not record which commit it read)

  1. # MCP Server for Data Exploration
  2. MCP Server is a versatile tool designed for interactive data exploration.
  3. Your personal Data Scientist assistant, turning complex datasets into clear, actionable insights.
  4. <a href="https://glama.ai/mcp/servers/hwm8j9c422"><img width="380" height="200" src="https://glama.ai/mcp/servers/hwm8j9c422/badge" alt="mcp-server-data-exploration MCP server" /></a>
  5. ## 🚀 Try it Out
  6. 1. **Download Claude Desktop**
  7. - Get it [here](https://claude.ai/download)
  8. 2. **Install and Set Up**
  9. - On macOS, run the following command in your terminal:
  10. ```bash
  11. python setup.py
  12. ```
  13. 3. **Load Templates and Tools**
  14. - Once the server is running, wait for the prompt template and tools to load in Claude Desktop.
  15. 4. **Start Exploring**
  16. - Select the explore-data prompt template from MCP
  17. - Begin your conversation by providing the required inputs:
  18. - `csv_path`: Local path to the CSV file
  19. - `topic`: The topic of exploration (e.g., "Weather patterns in New York" or "Housing prices in California")
  20. ## Examples
  21. These are examples of how you can use MCP Server to explore data without any human intervention.
  22. ### Case 1: California Real Estate Listing Prices
  23. - Kaggle Dataset: [USA Real Estate Dataset](https://www.kaggle.com/datasets/ahmedshahriarsakib/usa-real-estate-dataset)
  24. - Size: 2,226,382 entries (178.9 MB)
  25. - Topic: Housing price trends in California
  26. [![Watch the video](https://img.youtube.com/vi/RQZbeuaH9Ys/hqdefault.jpg)](https://www.youtube.com/watch?v=RQZbeuaH9Ys)
  27. - [Data Exploration Summary](https://claude.site/artifacts/058a1593-7a14-40df-bf09-28b8c4531137)
  28. ### Case 2: Weather in London
  29. - Kaggle Dataset: [2M+ Daily Weather History UK](https://www.kaggle.com/datasets/jakewright/2m-daily-weather-history-uk/data)
  30. - Size: 2,836,186 entries (169.3 MB)
  31. - Topic: Weather in London
  32. - Report: [View Report](https://claude.site/artifacts/601ea9c1-a00e-472e-9271-3efafb8edede)
  33. - Graphs:
  34. - [London Temperature Trends](https://claude.site/artifacts/9a25bc1e-d0cf-498a-833c-5179547ee268)
  35. <img width="1622" alt="Screenshot 2024-12-09 at 12 48 56 AM" src="https://github.com/user-attachments/assets/9e70fe97-8af7-4221-b1e7-00197c88bb47">
  36. - [Temperature-Humidity Relationship by Season](https://claude.site/artifacts/32a3371c-698d-48e3-b94e-f7e88ce8093d)
  37. <img width="1623" alt="Screenshot 2024-12-09 at 12 47 54 AM" src="https://github.com/user-attachments/assets/f4ac60a8-30e3-4b10-b296-ba412c2922fa">
  38. - [Wind Direction Pattern by Season](https://claude.site/artifacts/32a3371c-698d-48e3-b94e-f7e88ce8093d)
  39. <img width="1622" alt="Screenshot 2024-12-09 at 12 47 00 AM" src="https://github.com/user-attachments/assets/2db01054-f948-4d2e-ba39-8de8fa59f83d">
  40. ## 📦 Components
  41. ### Prompts
  42. - **explore-data**: Tailored for data exploration tasks
  43. ### Tools
  44. 1. **load-csv**
  45. - Function: Loads a CSV file into a DataFrame
  46. - Arguments:
  47. - `csv_path` (string, required): Path to the CSV file
  48. - `df_name` (string, optional): Name for the DataFrame. Defaults to df_1, df_2, etc., if not provided
  49. 2. **run-script**
  50. - Function: Executes a Python script
  51. - Arguments:
  52. - `script` (string, required): The script to execute
  53. ## ⚙️ Modifying the Server
  54. ### Claude Desktop Configurations
  55. - macOS: `~/Library/Application\ Support/Claude/claude_desktop_config.json`
  56. - Windows: `%APPDATA%/Claude/claude_desktop_config.json`
  57. ### Development (Unpublished Servers)
  58. ```json
  59. "mcpServers": {
  60. "mcp-server-ds": {
  61. "command": "uv",
  62. "args": [
  63. "--directory",
  64. "/Users/username/src/mcp-server-ds",
  65. "run",
  66. "mcp-server-ds"
  67. ]
  68. }
  69. }
  70. ```
  71. ### Published Servers
  72. ```json
  73. "mcpServers": {
  74. "mcp-server-ds": {
  75. "command": "uvx",
  76. "args": [
  77. "mcp-server-ds"
  78. ]
  79. }
  80. }
  81. ```
  82. ## 🛠️ Development
  83. ### Building and Publishing
  84. 1. **Sync Dependencies**
  85. ```bash
  86. uv sync
  87. ```
  88. 2. **Build Distributions**
  89. ```bash
  90. uv build
  91. ```
  92. Generates source and wheel distributions in the dist/ directory.
  93. 3. **Publish to PyPI**
  94. ```bash
  95. uv publish
  96. ```
  97. ## 🤝 Contributing
  98. Contributions are welcome! Whether you're fixing bugs, adding features, or improving documentation, your help makes this project better.
  99. ### Reporting Issues
  100. If you encounter bugs or have suggestions, open an issue in the issues section. Include:
  101. - Steps to reproduce (if applicable)
  102. - Expected vs. actual behavior
  103. - Screenshots or error logs (if relevant)
  104. ## 📜 License
  105. This project is licensed under the MIT License.
  106. See the LICENSE file for details.
  107. ## 💬 Get in Touch
  108. Questions? Feedback? Open an issue or reach out to the maintainers. Let's make this project awesome together!
  109. ## About
  110. This is an open source project run by [ReadingPlus.AI LLC](https://readingplus.ai). and open to contributions from the entire community.

Ratings and comments

Sign in to rate this skill.

Sign in

Free to use. If it’s helped, pass it on.