Mobus
Mobus is an MCP server for dataset discovery and research.
What it can do
- Search Datasets: Search for datasets across multiple platforms (Kaggle, Hugging Face, data.gov, Zenodo, OpenML, UCI, Google, AWS, World Bank, WHO, NASA, Eurostat, Socrata, Papers with Code, Semantic S
- Get Dataset Details: Get detailed metadata for a specific dataset (columns, row count, files, popularity)
- Preview Dataset: Preview the first N rows of a dataset to inspect its data before downloading
What data it sees
Do you need an account
No: the server works without sign-in
Mobus is an MCP server for dataset discovery and research. One connector searches Kaggle, Hugging Face, data.gov, Zenodo, OpenML, NASA, WHO, World Bank, Eurostat, and many other catalogs. Use it to find datasets, inspect metadata, preview rows, build quick charts, check licenses, compare options, and generate citations. All without leaving your chat.
How to connect
How to connect Mobus to Claude
The server address to paste into Claude settings:
https://mobus--mobus.run.tools
- Open Claude (claude.ai or the desktop app).
- Go to Settings → Connectors.
- Click Add custom connector.
- Paste the server address copied below into Remote MCP server URL and click Add.
- In a chat, click + → Connectors and switch the new connector on.
Custom connectors are available on Free, Pro, Max, Team and Enterprise plans (Free is limited to one). On Team and Enterprise an organization Owner adds the connector first under Organization settings → Connectors.
Authorization
After you click Add, a sign-in window for the service opens. Sign in with your own account and approve access. Claude never sees your password.
How to connect Mobus to ChatGPT
The server address to paste into ChatGPT settings:
https://mobus--mobus.run.tools
- Open ChatGPT in a browser (chatgpt.com). A Plus, Pro, Business, Enterprise or Edu plan is required.
- Turn on developer mode once: Settings → Apps → Advanced settings → Developer mode.
- Open Settings → Connectors and click Create.
- Fill in the form: Name (anything), Description (one line about what the service does), MCP server URL (copy it below).
- Under Authentication choose OAuth if the service requires sign-in, otherwise None. Click Create.
- In a new chat open + → Apps/Connectors and enable the connector.
OpenAI has renamed this section before (Connectors → Apps/Plugins). If the label differs, search settings for "developer mode". On Business/Enterprise workspaces an admin must allow custom connectors first.
Authorization
On first use ChatGPT opens the service's sign-in window. Sign in and approve access.
How to connect Mobus to Cursor
The server address to paste into Cursor settings:
https://mobus--mobus.run.tools
Fastest: click Open in Cursor below and confirm the prompt.
Manually:
- In Cursor open Settings → Cursor Settings → MCP and click Add new global MCP server.
- Paste the JSON copied below into
~/.cursor/mcp.json(per project:.cursor/mcp.jsonin the repo root). - Save the file. The server appears in the MCP list; authorize it there if asked.
Authorization
If the service needs sign-in, an authorize button appears next to the server in the MCP list.
Server tool list (15)
Raw names from tools/list. Only developers need these.
| search_datasets | Search for datasets across multiple platforms (Kaggle, Hugging Face, data.gov, Zenodo, OpenML, UCI, Google, AWS, World Bank, WHO, NASA, Eurostat, Socrata, Papers with Code, Semantic Scholar, arXiv, Census.gov, SEC EDGAR, Crossref, Econdb, Harvard Dataverse) with optional filters |
| get_dataset_details | Get detailed metadata for a specific dataset (columns, row count, files, popularity) |
| preview_dataset | Preview the first N rows of a dataset to inspect its data before downloading |
| compare_datasets | Compare 2-5 datasets side by side: columns, sizes, licenses, and column overlap |
| check_compatibility | Check if a dataset's schema matches your expected columns and types |
| find_similar | Find datasets similar to a given dataset based on tags, name, and description |
| generate_citation | Generate a formatted citation (BibTeX, APA, or Chicago) for a dataset |
| assess_quality | Assess data quality: missing values, duplicates, basic statistics, and date freshness |
| check_license | Check if a dataset's license permits a specific use case (commercial, academic, internal, redistribution) |
| watch_query | Save, remove, list, or check dataset search watches for monitoring new datasets |
| visualize_dataset | Generate an interactive ECharts dashboard to explore a dataset visually — charts, filters, table view, and export. In remote mode returns a URL; locally opens in the browser. |
| find_research_datasets | Find datasets used in academic research for a given topic — searches Papers with Code tasks and datasets, enriches with Semantic Scholar paper metadata, and cross-references against all other DAV sources |
| get_dataset_provenance | Get the full research provenance of a dataset: which papers used it, how popular it is, venue/year/field breakdowns, top-cited papers, trend over time, and the paper that introduced it |
| trace_citation_graph | Trace the citation chain for a dataset: find the introducing paper, then follow citations to build a chronological narrative of how the dataset has been used, extended, and benchmarked over time |
| get_dataset_lineage | Get the family tree of a dataset: find all variants, extensions, subsets, and derivative datasets (e.g. ImageNet → ImageNet-V2, ImageNet-Sketch, ImageNet-A) using name matching, citation graph analysis, and abstract-based lineage detection |