MobusMCP
Search, preview, and analyze datasets from 20+ platforms and millions of datasets via a single MCP connector. Works with Claude instantly
What is MobusMCP?
MobusMCP is a Model Context Protocol (MCP) server that allows AI assistants like Claude, Cursor, and VS Code to search, preview, and analyze datasets from 20+ platforms and millions of datasets via a single mcp connector. works with claude instantly
Search, preview, and analyze datasets from 20+ platforms and millions of datasets via a single MCP connector. Works with Claude instantly
This server falls under the Data Science & ML category on MCPgee, the world's largest MCP server directory with 33,000+ servers.
Features
- Search, preview, and analyze datasets from 20+ platforms and
Use Cases
Maintainer
Works with
Installation
Manual Installation
npx mobusmcpConfiguration
Configuration Details
claude_desktop_config.json
Performance
Response Metrics
Resource Usage
How to Set Up and Use MobusMCP
MobusMCP is a dataset discovery and analysis connector that gives AI assistants unified access to over 20 data platforms — including Kaggle, Hugging Face, Google Dataset Search, and Socrata — through a single MCP interface. It exposes 15 tools for searching, previewing, evaluating quality, checking licenses, comparing datasets, and generating citations, making it practical for data scientists and ML engineers to source training data or research datasets directly from their AI workflow. The server connects to the hosted Mobus API and requires optional platform-specific API keys for enhanced access.
Prerequisites
- An MCP-compatible client such as Claude Desktop
- Optional: Kaggle API credentials (KAGGLE_USERNAME and KAGGLE_KEY) for Kaggle dataset access
- Optional: Hugging Face token (HF_TOKEN) for faster HuggingFace searches
- Optional: Google API key (GOOGLE_API_KEY) and Custom Search Engine ID (GOOGLE_CSE_ID) for Google Dataset Search
- Node.js 18+ if running locally via npx
Connect via the hosted Mobus MCP endpoint
The simplest setup is to point your MCP client at the hosted Mobus endpoint. In Claude.ai, go to Settings → Connectors and add the URL. For Claude Desktop, add a remote server entry.
{
"mcpServers": {
"mobus": {
"url": "https://mcp.mobus.ai/mcp"
}
}
}Alternatively, run the server locally with npx
You can also run MobusMCP locally using npx, which pulls the package without a permanent install. Configure optional API keys as environment variables for enhanced platform access.
npx mobusmcpAdd optional API keys for extended platform coverage
Without API keys, the server still searches many open platforms. Add keys for Kaggle, Hugging Face, Google, or Socrata to unlock additional dataset sources.
{
"mcpServers": {
"mobus": {
"command": "npx",
"args": ["mobusmcp"],
"env": {
"KAGGLE_USERNAME": "your_kaggle_username",
"KAGGLE_KEY": "your_kaggle_api_key",
"HF_TOKEN": "your_huggingface_token",
"GOOGLE_API_KEY": "your_google_api_key",
"GOOGLE_CSE_ID": "your_cse_id"
}
}
}
}Restart your MCP client and start discovering datasets
Restart Claude Desktop after saving the configuration. The Mobus tools will be available for dataset search, preview, quality assessment, license checking, and citation generation.
MobusMCP Examples
Client configuration
Claude Desktop configuration using the hosted Mobus endpoint — no API keys required for basic usage.
{
"mcpServers": {
"mobus": {
"url": "https://mcp.mobus.ai/mcp"
}
}
}Prompts to try
Example queries that exercise dataset search, preview, license check, citation, and comparison tools across the 20+ connected platforms.
- "Search for air quality datasets with a commercial-use license across all platforms"
- "Preview the first 20 rows of that Kaggle dataset"
- "Compare these two climate datasets side by side for schema compatibility"
- "Generate an APA citation for the dataset I just found"
- "Check whether this Hugging Face dataset can be used for commercial ML training"
- "Find datasets similar to ImageNet for image classification"Troubleshooting MobusMCP
Search returns results from only a few platforms
Results from Kaggle, Hugging Face, Google Dataset Search, and Socrata require the corresponding API keys (KAGGLE_USERNAME/KAGGLE_KEY, HF_TOKEN, GOOGLE_API_KEY/GOOGLE_CSE_ID, SOCRATA_APP_TOKEN). Add the missing keys to your environment configuration to unlock those platforms.
npx mobusmcp command not found or fails to start
Ensure Node.js 18+ is installed ('node --version'). If the package name has changed, try the hosted URL approach instead: set the server URL to https://mcp.mobus.ai/mcp in your client configuration.
Dataset preview returns an error for large datasets
Specify a row limit when requesting previews: 'Preview the first 20 rows' rather than asking for a full preview. Large datasets on some platforms require the platform's own API key for row-level access.
Frequently Asked Questions about MobusMCP
What is MobusMCP?
MobusMCP is a Model Context Protocol (MCP) server that search, preview, and analyze datasets from 20+ platforms and millions of datasets via a single mcp connector. works with claude instantly It connects AI assistants to external tools and data sources through a standardized interface.
How do I install MobusMCP?
Follow the installation instructions on the MobusMCP GitHub repository. Clone the repo, install dependencies, and add the server config to your AI client.
Which AI clients work with MobusMCP?
MobusMCP works with all major MCP-compatible AI clients including Claude Desktop, Claude Code, Cursor, VS Code (GitHub Copilot), Windsurf, and Cline.
Is MobusMCP free to use?
Yes, MobusMCP is open source and available under the MIT License license. You can use it freely in both personal and commercial projects.
MobusMCP Alternatives — Similar Data Science & ML Servers
Looking for alternatives to MobusMCP? Here are other popular data science & ml servers you can use with Claude, Cursor, and VS Code.
Ultrarag
★ 5.6kA Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines
RocketRide
★ 3.1k📇 🏠 - MCP server that exposes RocketRide AI pipelines as t
Aix Db
★ 2.1kAix-DB 基于 LangChain/LangGraph 框架，结合 MCP Skills 多智能体协作架构，实现自然语言到数据洞察的端到端转换。
NeMo Data Designer
★ 1.9k🎨 NeMo Data Designer: Generate high-quality synthetic data from scratch or from seed data.
PaperBanana
★ 1.7kOpen source implementation and extension of Google Research’s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.
MiniMax
★ 1.5kBridges MiniMax AI capabilities to the Model Context Protocol, enabling AI agents to perform image understanding, text-to-image generation, and speech synthesis. It provides a standardized interface for accessing MiniMax's core tools via JSON-RPC.
Browse More Data Science & ML MCP Servers
Explore all data science & ml servers available in the MCPgee directory. Each server includes setup guides for Claude, Cursor, and VS Code.
Set Up MobusMCP in Your Editor
Choose your AI client for step-by-step setup instructions.
Quick Config Preview
Add this to your claude_desktop_config.json or .cursor/mcp.json
Ready to use MobusMCP?
Browse our complete directory of 33,000+ MCP servers, read setup guides for your editor, and start building with the Model Context Protocol.