Mobus

Overview

Mobus provides a unified MCP interface to discover, preview, and analyze datasets across 20+ platforms including Hugging Face, Kaggle, Zenodo, and government repositories. It offers 15 tools covering dataset discovery, evaluation, quality assessment, citation generation, and advanced research features. The server handles parallel requests across platforms gracefully, even when certain API keys are missing.

Try asking AI

After installing, here are 8 things you can ask your AI assistant:

• search_datasets

  Search all 20 platforms at once for datasets

  Try:Search for air quality datasets with a commercial licenseTry:Find climate change datasets updated after 2020
• find_research_datasets

  Find datasets used in research papers

  Try:Find research datasets related to machine learningTry:Get datasets used in papers about neural networks
• get_dataset_details

  Get full metadata for a specific dataset

  Try:Get details about that Zenodo datasetTry:Show me metadata for the Hugging Face model
• preview_dataset

  Preview the first N rows of a dataset

  Try:Preview the first 20 rows of that datasetTry:Show me a sample of the SEC filings data
• compare_datasets

  Compare 2-5 datasets side by side

  Try:Compare these three climate datasetsTry:Show me differences between the Kaggle and UCI datasets
• generate_citation

  Generate APA, BibTeX, or Chicago citations for datasets

  Try:Generate an APA citation for that datasetTry:Create a BibTeX citation for the Hugging Face model
• assess_quality

  Assess dataset quality including missing values and duplicates

  Try:Assess the quality of this datasetTry:Check for missing values and duplicates in the data
• check_license

  Check dataset license for commercial, academic, or internal use

  Try:Check if this dataset can be used commerciallyTry:Verify the license for academic use
• find_similar

  Find datasets similar to one you have

  Try:Find datasets similar to this oneTry:Show me alternatives to the Kaggle dataset
• check_compatibility

  Check schema compatibility against your schema

  Try:Check if this dataset is compatible with my schemaTry:Verify schema compatibility with this data
• visualize_dataset

  Generate interactive ECharts dashboard for a dataset

  Try:Visualize this datasetTry:Create an interactive dashboard for the climate data
• watch_query

  Monitor for new datasets matching your query

  Try:Watch for new datasets about machine learningTry:Set up a notification for new climate data

Comparable tools

Installation

git clone https://github.com/hrantvirabyan/Mobus.git
cd Mobus
npm install
cp .env.example .env   # fill in any keys you have (all optional)
npm run build

{
  "mcpServers": {
    "mobus": {
      "command": "node",
      "args": ["/absolute/path/to/Mobus/dist/main.js"]
    }
  }
}

FAQ

Do I need API keys to use Mobus?

No, all API keys are optional. The server will gracefully skip platforms that require authentication when keys aren't provided.

Which AI assistants are compatible with Mobus?

Mobus works with Claude (web, desktop, and mobile) and can be configured for other MCP-compatible AI assistants by adding the MCP server configuration.

What happens if a platform's API is down?

Mobus handles API failures gracefully and continues processing requests from other platforms without crashing.

Compare Mobus with