Skip to content
Back to search

datamind-ai

An AI powered agentic data analytics platform featuring automated EDA, natural language data analysis, machine learning, anomaly detection, interactive visualizations, and custom MCP server integration.

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/shailja181--datamind-ai/badge.svg)](/listings/shailja181--datamind-ai)

HTML

<a href="/listings/shailja181--datamind-ai"><img src="/api/listings/shailja181--datamind-ai/badge.svg" alt="findsafeskills safety rating" /></a>

Install

i

Install instructions from the README

As written by the repo's author. findsafeskills has not verified these steps.

**1. Create a virtual environment**

python -m venv .venv

**2. Activate the environment**

Windows:

.venv\Scripts\activate

Linux/macOS:

source .venv/bin/activate

**3. Install backend dependencies**

pip install -r backend/requirements.txt

**4. Start the backend**

cd backend
uvicorn app.main:app --reload

**5. Start the frontend** (in a separate terminal)

cd frontend
npm install
npm run dev

**6. Run tests** (from the project root)

pytest tests -v

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 · 124 lines
  1. # DataMind AI
  2. ### Turn Data into Decisions with AI.
  3. DataMind AI is an agentic data analytics platform that combines automated data analysis, machine learning and Model Context Protocol (MCP) integration to make data exploration smarter and more accessible.
  4. **Key principle:** The LLM never calculates statistical results itself. All numerical computations are performed by a dedicated analytics engine to ensure reliable, data-driven results.
  5. ## ✨ Features
  6. - **Automated EDA:** Statistical summaries, missing-value analysis and dataset insights.
  7. - **Data Explorer:** Upload and explore structured datasets.
  8. - **AI Analyst:** Natural-language interaction with datasets.
  9. - **ML Playground:** Machine learning model training and evaluation.
  10. - **Anomaly Detection:** Identify unusual patterns and outliers.
  11. - **Interactive Visualizations:** Explore analytical results through charts.
  12. - **MCP Integration:** Expose analytics capabilities through reusable MCP tools.
  13. - **REST API:** FastAPI-powered backend with interactive API documentation.
  14. ## 🛠️ Tech Stack
  15. - **Frontend:** React.js, Vite, TypeScript, Tailwind CSS
  16. - **Backend:** Python, FastAPI
  17. - **Data Analysis:** Pandas, NumPy
  18. - **Machine Learning:** Scikit-learn
  19. - **AI Integration:** Gemini API, MCP
  20. - **Testing:** Pytest
  21. ## 📁 Project Structure
  22. ```text
  23. datamind-ai/
  24. ├── backend/
  25. │ ├── app/
  26. │ │ ├── analytics/
  27. │ │ └── main.py
  28. │ ├── data/uploads/
  29. │ └── requirements.txt
  30. ├── frontend/
  31. ├── mcp_server/
  32. │ ├── requirements.txt
  33. │ └── server.py
  34. ├── sample_data/
  35. │ └── sales.csv
  36. ├── docs/
  37. ├── tests/
  38. ├── .env.example
  39. ├── .gitignore
  40. └── README.md
  41. ```
  42. ## 🚀 Getting Started
  43. **1. Create a virtual environment**
  44. ```bash
  45. python -m venv .venv
  46. ```
  47. **2. Activate the environment**
  48. Windows:
  49. ```bash
  50. .venv\Scripts\activate
  51. ```
  52. Linux/macOS:
  53. ```bash
  54. source .venv/bin/activate
  55. ```
  56. **3. Install backend dependencies**
  57. ```bash
  58. pip install -r backend/requirements.txt
  59. ```
  60. **4. Start the backend**
  61. ```bash
  62. cd backend
  63. uvicorn app.main:app --reload
  64. ```
  65. **5. Start the frontend** (in a separate terminal)
  66. ```bash
  67. cd frontend
  68. npm install
  69. npm run dev
  70. ```
  71. **6. Run tests** (from the project root)
  72. ```bash
  73. pytest tests -v
  74. ```
  75. ## 🔌 MCP Tools
  76. - `analyze_dataset`
  77. - `get_column_summary`
  78. - `query_dataset`
  79. - `detect_anomalies`
  80. The MCP server uses STDIO transport to communicate with compatible MCP clients.
  81. ## 🗺️ Roadmap
  82. - [x] Analytics engine and FastAPI backend
  83. - [x] React frontend
  84. - [x] MCP server integration
  85. - [x] Dataset validation and automated tests
  86. - [ ] Advanced reporting and exports
  87. - [ ] Gemini-powered agent enhancements
  88. - [ ] Database persistence
  89. ## 📄 License
  90. MIT License
  91. ---
  92. **DataMind AI — Making data analysis smarter, safer, and more accessible.**

Ratings and comments

Sign in to rate this skill.

Sign in

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