musharna/data-aggregator-mcp
by Various
Unified research-data acquisition MCP — search & fetch datasets across Zenodo, DataCite, NCBI omics (GEO/SRA/BioProject), and literature (PubMed/OpenAIRE) behind one normalized mod
MCP
musharna/data-aggregator-mcp
Added 8 June 2026
Overview
A unified MCP server that searches and fetches datasets across Zenodo, DataCite, NCBI omics (GEO/SRA/BioProject), and literature (PubMed/OpenAIRE). It normalizes results into a single model, enabling consistent research-data acquisition from multiple sources.
Best for
Best for
Researchers and developers building data aggregation tools for scientific datasets
Use cases
- Aggregate dataset metadata from multiple scientific repositories in one query
- Fetch normalized research data for literature and omics studies
- Integrate cross-repository search into data analysis pipelines
How to use
Install
uvx data-aggregator-mcp Tools exposed
searchresolvefetchoperaterelatelist_sources
Tested with
Claude Desktop, Claude Code, Cursor, ChatGPT
Example client config
{\n "mcpServers": {\n "data-aggregator": {\n "command": "uvx",\n "args": ["data-aggregator-mcp"],\n "env": { "NCBI_API_KEY": "your-optional-key" }\n }\n }\n} Notes
A unified MCP server that searches and fetches datasets across Zenodo, DataCite, NCBI omics (GEO/SRA/BioProject), and literature (PubMed/OpenAIRE). It normalizes results into a single model, enabling consistent research-data acquisition from multiple sources.
1 stars on GitHub. Last updated 2026-06-07. Licensed MIT.
Use cases
- Aggregate dataset metadata from multiple scientific repositories in one query
- Fetch normalized research data for literature and omics studies
- Integrate cross-repository search into data analysis pipelines
Pros
- Unifies multiple major scientific data sources behind a single interface
- Reduces boilerplate for multi-source research data retrieval
- Open source with a simple MCP protocol for integration
Cons
- Very early stage with only 1 GitHub star and limited community adoption
- Dependency on external APIs that may have rate limits or downtime
- No built-in caching or offline support for repeated queries
Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.
Pros
- Unifies multiple major scientific data sources behind a single interface
- Reduces boilerplate for multi-source research data retrieval
- Open source with a simple MCP protocol for integration
Cons
- Very early stage with only 1 GitHub star and limited community adoption
- Dependency on external APIs that may have rate limits or downtime
- No built-in caching or offline support for repeated queries
Pairs with
Other entries in the index that connect to this one. Click through to see the chain.
Get the free Developer’s Field Guide
A 27-page field guide to the AI coding workflow with Claude. Claude Code, MCP servers, the prompt patterns that work, and what to delegate. Free.
Enter your work email. We send it straight over, plus a few short notes worth knowing. Unsubscribe any time.
